Gaza sunrise or false dawn? Trump’s peace plan

September 30, 2025October 2, 2025Paul Hemphill 1 Comment

US President Donald Trump’s twenty-point comprehensive peace plan for Gaza, published in full below, is a fascinating document – part fever dream of a “deal of the century,” part boardroom restructuring plan, part realpolitik ceasefire blueprint. And for Trump, yes – the dangling Nobel, the glittering carrot at the end of the labyrinth.

On paper it sounds almost seductively tidy: IDF withdrawal, Hamas stand-down, aid flowing, hostages returned in return for prisoners released, multinational security force, guns decommissioned, technocrats taking over, reformed PA, while a “Board of Peace” chaired by Trump (and perhaps Tony Blair in a cameo) ushers in a gleaming new Gaza.

In That Howling Infinite reserves its opinion in these early days. It’s the only show in town right now and it is generating interest and potential commitment by all those parties who would have to make it happen. There’ll be dissenting voices on all sides, but at the end of the day, they have little to offer except more war and vitriol. You don’t use gasoline to put out a fire. To borrow from J Lennon, all we are saying is give peace a chance”.

But, nevertheless, the gap between the paper and the ground is immense.

Here are some early observations:

Ambition vs. feasibility. The plan imagines simultaneous hostage exchanges, mass prisoner releases, Hamas disarmament, and international deployment – all within days or weeks. Each step is individually fraught; stacked together, the sequencing is almost fantastical.
Actors and trust. It assumes that Hamas will voluntarily surrender weapons and that Israel will trust an international stabilization force enough to withdraw, all while regional guarantors enforce compliance. None of these actors currently exhibit the trust or cohesion needed.
Power dynamics. The “Board of Peace” with Trump as chair feels less like neutral governance and more like a branding exercise. Palestinians, already wary of external control, would likely see it as another foreign trusteeship.
Statehood dangling. The plan holds out a “credible pathway” to Palestinian self-determination but keeps it conditional on reforms and compliance – carrot and stick politics that might prolong, rather than resolve, the status question.
Optics of ownership. The redevelopment language (special economic zones, “miracle cities”) reads like a Gulf mega-project transplanted onto a traumatised strip of land, risking the perception of Gaza as a real-estate venture rather than a society with its own political agency.

So, on paper, it is clever and comprehensive, giving something to everybody, and promising an imminent end to the destruction and carnage of the past two years. But in reality, it is almost impossible to realise without a fundamental shift in regional politics and in the balance of trust. It reads less as a near-term peace plan than as a campaign manifesto – designed to signal vision and dominance, to offer every constituency a glimmer of what they want, and to position Trump as indispensable even if none of it materialises.

Read part 2 here: Gaza Sunrise or False Dawn (2) Spectacle or strategy?

Also, in In That Howling Infinite, see A Short History of the Rise and Fall of the West and A Middle East Miscellany

What will the warring parties and outsiders take the plan?

This will depend less on the fine print than on who authored it, and on the political imaginaries each camp carries into the debate. A few likely responses:

1. Israel & Netanyahu

Netanyahu, ever the tactician, would welcome the optics: Trump is both his old ally and a political shield. “Deradicalised Gaza,” hostages back, no forced concessions on West Bank settlements—what’s not to like?
The Israeli right could live with it, because it leaves the question of Palestinian statehood indefinitely conditional.
Centrists and security hawks might applaud the ISF mechanism and U.S. guarantees, though the idea of foreign troops patrolling Gaza would make many nervous.

2. Palestinians in Gaza and the West Bank

Gaza:

Immediate Relief vs. Distrust. Ordinary Gazans, exhausted by war and blockade, might welcome the promise of aid, reconstruction, and an end to bombardment. Rubble removed, water flowing, bakeries open—that is tangible.
But many will see it as conditional relief: they must surrender political agency, accept foreign trusteeship (“Trump’s Board of Peace”), and live under an imposed technocracy. To them, this may feel like a wardship, not a liberation.
Trauma & Pragmatism. After such devastation, some Gazans might pragmatically say, “we’ll take the deal, anything is better than this,” but the resentment toward outside control will simmer.

West Bank:

Deep Cynicism. Palestinians in the West Bank already regard the PA as corrupt and ineffectual, and many see U.S.-brokered plans as cover for Israeli expansion. The plan doesn’t address settlements, land seizures, checkpoints, or settler violence—all daily realities.
Result: West Bank Palestinians are likely to dismiss it as another charade – aid and optics in Gaza while the core occupation issue festers on their side of the Green Line.

3. Hamas and Its Supporters/Enablers

Hamas in Gaza:

Existential Threat. The plan effectively demands Hamas disarm, disband, or exile itself. For Hamas leadership, this is unconditional defeat in all but name.
Pragmatists vs. Hardliners. Some Hamas figures might toy with amnesty or safe passage, but for the movement’s core (military wing, ideological diehards), surrendering weapons = suicide.

Hamas Supporters in the West Bank:

They will frame the plan as capitulation and collaboration with occupiers. It hands Hamas a propaganda card: “see, the Americans and Israelis want to erase us.”
This could deepen West Bank radicalisation and further delegitimize the PA if it tries to administer such a deal.

Regional Supporters (Hezbollah, Iran, Qatar, Turkey):

Iran & Hezbollah: Will reject outright – it neuters their “Axis of Resistance”. They will continue funding and arming whatever underground or splinter groups emerge.
Qatar & Turkey: May hedge. They might support parts of the plan if it relieves humanitarian disaster, but not if it sidelines Hamas entirely.

Diaspora Palestinians & Pro-Hamas Sympathisers:

Many in exile view Hamas (however critically) as a symbol of armed resistance. For them, a Trump-blessed disarmament deal is betrayal dressed as peace.
Expect mass rejection from diaspora activists, especially in Europe and the Americas, where “Free Palestine” remains the rallying cry.

Net Effect

For Gazans: temporary relief but long-term discontent.
For West Bank Palestinians: scorn and dismissal.
For Hamas: existential rejection.
For Hamas’s backers: rejection, with potential escalation elsewhere (Lebanon, Syria, Red Sea) to keep the “resistance flame” alive.

In short, the plan may stop the bombs, but it does not resolve the politics. Gazans might sigh with relief; West Bankers will sneer; Hamas will fight on; its allies will sabotage; and the diaspora will rage.

3. Arab League & Regional States

Publicly, Arab governments (Egypt, Jordan, Saudi Arabia, UAE) would almost certainly bless the plan, because it ends the bloodletting, brings in money, and doesn’t force them to grapple with Hamas. Privately, they’d be wary: nobody relishes underwriting Gaza’s reconstruction while taking the blame for failed implementation. But in a rules-based, donor-heavy framework, they could sell it as Arab pragmatism.

4. Western Powers

Washington under Trump (and perhaps a Republican-leaning Congress) would present this as a masterstroke—“the deal no one else could deliver.” Europe would likely sigh in relief: anything that halts the war is better than nothing, and the technocratic language about governance and reform plays to EU ears. But the suspicion will linger: is this peace-building, or is it Trump building another gilded tower on scorched earth?

5. UN & International Institutions

UN agencies would leap at guaranteed humanitarian access, even under Trump’s “Board of Peace.” The problem: the UN is accustomed to being scapegoated, and here it would once again be implementing someone else’s design, while absorbing the failures if and when they come.

6. Progressives & Global Pro-Palestinian Activists

For many, this is a non-starter. It doesn’t dismantle the occupation, doesn’t guarantee sovereignty, doesn’t address the Nakba legacy – it freezes the conflict in a Trump-branded frame. They will dismiss it as paternalism dressed as pragmatism: Gazans are told to behave, hand over weapons, accept foreign trusteeship, and maybe, one day, statehood might be considered. For many progressives, and their Arab collaborators, the plan will probably not be enough. Though they’ve clamoured all along for a ceasefire, it’s not the one they wanted – a Free Palestine, and for some a Juden Frei Palestine “from the river to the sea”. Add the Trump factor: for progressives, he is the antithesis of credibility, and they abhor all he stands for. Even if the plan included a sovereign Palestinian state tomorrow, they’d likely distrust it as a Trojan horse.

7. The Subtext

The stark divide is this:

For state actors (Israel, Arab governments, Western powers), this looks like a workable ceasefire mechanism dressed up as reconstruction.

For non-state voices (Palestinian street, global solidarity movements), it looks like an elaborate cage, perhaps cleaner and better lit, but still a cage.

Netanyahu and the Arab League could sell it; the UN and EU could implement it; the U.S. could campaign on it; but progressives and much of Palestinian civil society will continue to shout: it’s not liberation, it’s management. And “management,” in the political imagination of the dispossessed, is simply another word for betrayal.

How will Donald Trump “sell” his “deal of the century “?

Trump’s political “genius” (and danger) is that he doesn’t need buy-in from the ground; he needs headlines at home and optics abroad. Here’s how the calculus lines up:

1. In the U.S. Domestic Arena

“The Deal Nobody Else Could Do.” Trump frames himself as the only leader who could stop the war, get hostages released, and bring aid trucks rolling in. The fact that Gazans or the diaspora are furious is immaterial – he’s selling to voters in Michigan, not in Khan Younis.

Optics of Strength. He casts the plan as disciplining Hamas (“they lay down arms or leave”) while also delivering humanitarian relief. That duality – tough but generous – is powerful on the campaign trail.

Nobel Peace Prize Theater. He doesn’t need to win it; he just needs to say he deserves it. The claim itself becomes part of his narrative of grievance and triumph.

2. Internationally

Israel: Netanyahu nods, Israeli centrists sigh in relief – Trump can present himself as Israel’s indispensable friend who also delivers quiet.

Arab League: Even tepid Arab League approval lets Trump boast: “I got the Arabs and Israelis on the same page.” That plays huge in diplomatic theater.

Europe: Brussels won’t love him, but the EU will be glad the bombs stopped. That’s enough for Trump to say, “they all lined up behind me.”

3. Against His Rivals

Against Biden/Democrats: He can taunt: “Biden let it burn, I brought peace.” Never mind the plan’s contradictions; soundbites are what matter.

Against Progressives: Their rejection of his plan – because it’s not liberation, because it has his name on it – becomes his foil. He’ll say: “They wanted chaos, I delivered peace, and they’re still angry.” That reframes them as radical spoilers.

4. The Spin Strategy

Even if Gazans accept aid but curse Trump, West Bank Palestinians reject it outright, Hamas refuses and Iran sneers, Trump still wins in the court of perception. He’ll point to convoys of aid, hostages walking free, and international press conferences flanked by Arab and Israeli leaders

For Trump, that’s success: not solving the conflict, but owning the narrative. He thrives on appearances of deal-making mastery, regardless of whether the underlying conflict is frozen, festering, or flaring again.

In other words: he doesn’t need the plan to work on the ground; he needs it to look like it worked just long enough. If later it unravels—well, that just proves others failed to sustain his deal.

A New Gaza governed by a New Palestinian Authority?

Trump’s plan waves vaguely toward a “reformed” Palestinian Authority (PA) as the eventual sovereign custodian of Gaza, but the devil lives in the details. The PA’s own house is famously messy.

Mahmoud Abbas and the Palestinian Authority (PA) are deeply unpopular among Palestinians because they are seen as stale, corrupt, and complicit. Abbas has overstayed his democratic mandate – his presidential term expired in 2009, yet he still rules by decree. Elections have been repeatedly postponed, hollowing out legitimacy. The PA is plagued by corruption, nepotism, and inefficiency, with patronage networks benefiting a small elite while everyday life in the West Bank deteriorates under occupation.

Worse, many Palestinians view the PA’s security coordination with Israel as collaboration – protecting Israel from attacks but delivering little political gain in return. Add to that the lack of progress toward statehood, the failure to heal the Fatah–Hamas split, and an aging leadership out of touch with a restless younger generation. The result: a widespread sense that the PA is more interested in preserving its own survival than advancing Palestinian freedom.

So what are the prospects for cleaning out these Augean Stables?

Every credible roadmap to Palestinian self-rule (whether in US “peace plans”, Arab League proposals, or European policy papers) circles back to roughly the same cluster of reforms:

Governance & Legitimacy

Elections: The PA has not held national elections since 2006. Regular, transparent presidential and legislative elections – monitored by international observers – are the baseline for legitimacy.
Leadership Renewal: President Mahmoud Abbas is in his late eighties and is highly unpopular. A clear succession process and generational turnover are essential to avoid a post-Abbas vacuum.
Rule of Law: Independent judiciary, due process in security courts, and an end to arbitrary detentions.

Security Sector Reform

Professionalisation of Forces: Unifying and depoliticising security services, with recruitment based on merit rather than factional loyalty.
Accountability Mechanisms: Civilian oversight, parliamentary scrutiny, and credible disciplinary systems to curb corruption and abuses.
Monopoly of Force: Ending the proliferation of armed factions and militias under semi-official umbrellas.

Anti-Corruption & Financial Transparency

Audit & Oversight: Strengthening the Palestinian Anti-Corruption Commission and ensuring regular public audits of ministries and security budgets.
Revenue Management: Transparent tax collection and spending, including reforms to the “clearance revenue” system Israel currently controls.
Private-Sector Safeguards: Modern procurement laws and independent regulators to reduce crony capitalism.

Institutional Consolidation

West Bank–Gaza Integration: Building unified administrative structures so that a future Gaza administration is not a parallel mini-state.
Service Delivery: Reliable health, education, and municipal services that reduce dependence on patronage networks.
Civil Society Engagement: Empowering NGOs and trade unions to act as watchdogs.

How Could This Be Realised?

External Leverage

Conditional Aid: The EU, U.S., and Gulf donors can tie financial support to measurable governance benchmarks (audits, election timelines, security milestones).
Arab Sponsorship: Egypt, Jordan, Saudi Arabia, and the UAE can provide both funding and political cover, helping broker intra-Palestinian reconciliation and mediating with Israel.

Internal Dynamics

Generational Change: A younger cohort of Fatah leaders and technocrats—already impatient with the old guard—must be empowered through credible elections.
Reconciliation with Hamas: Without some power-sharing or security arrangement, reform in the West Bank alone will not translate into legitimate rule in Gaza.

Israeli Role

Movement & Access: Reforms are impossible if Israel continues to restrict travel, tax revenue, and trade. Donors will demand at least tacit Israeli cooperation.
Security Coordination: A reformed PA security force must convince Israel that it can prevent attacks without being perceived domestically as a subcontractor for occupation.

Sustainability

Economic Viability: Reforms will collapse without a functioning economy—investment, trade corridors, and reliable tax revenue are oxygen.
Public Buy-In: Palestinians must see tangible improvements (jobs, mobility, basic freedoms) or reforms will be dismissed as foreign diktats.
Political Horizon: Even the best technocracy cannot survive perpetual occupation. A credible path to sovereignty—however distant—must accompany reforms to give them meaning.

In short, the PA must become a transparent, accountable proto-state while operating under occupation and facing a rival government in Gaza. It is a Sisyphean task, but not impossible if external actors (Israel included) provide real incentives, if donors enforce conditionality with patience, and if a younger Palestinian leadership can seize the moment. Without those three legs – international pressure, internal renewal, and a political horizon – the reform talk remains another Nobel-baiting paragraph in a White House press release.

[The above commentary and hypothetical is a the outcome of a conversation and collaboration between In That Howling Infinite and ChatGPT. The following list is the real deal]

Screenshot

Trump’s 20-point plan to end the war in Gaza:

Deradicalisation & Security – Gaza will be a deradicalised, terror-free zone that does not pose a threat to its neighbours.
Redevelopment for Gazans – Gaza will be redeveloped for the benefit of the people of Gaza, who have suffered more than enough.
Immediate Ceasefire & Withdrawal – If both sides agree to this proposal, the war will immediately end. Israeli forces will withdraw to the agreed-upon line to prepare for a hostage release. During this time, all military operations, including aerial and artillery bombardment, will be suspended, and battle lines will remain frozen until conditions are met for the complete staged withdrawal.
Hostage Return – Within 72 hours of Israel publicly accepting this agreement, all hostages, alive and deceased, will be returned.
Prisoner Exchange – Once all hostages are released, Israel will release 250 life-sentence prisoners plus 1,700 Gazans detained after October 7th, 2023 (including all women and children detained in that context). For every Israeli hostage whose remains are released, Israel will release the remains of 15 deceased Gazans.
Hamas Amnesty & Exit – Once all hostages are returned, Hamas members who commit to peaceful co-existence and to decommissioning their weapons will be given amnesty. Members of Hamas who wish to leave Gaza will be provided safe passage to receiving countries.
Immediate Humanitarian Aid – Upon acceptance of this agreement, full aid will be immediately sent into the Gaza Strip, at minimum matching the quantities specified in the January 19, 2025 agreement, including infrastructure rehabilitation (water, electricity, sewage), hospital and bakery repairs, and equipment to remove rubble and open roads.
Uninterrupted Aid Channels – Entry and distribution of aid in Gaza will proceed without interference from either party through the United Nations, the Red Crescent, and other neutral international institutions. Opening the Rafah crossing in both directions will follow the same mechanism as in the January 19, 2025 agreement.
Transitional Governance – Gaza will be governed by a temporary technocratic, apolitical Palestinian committee responsible for daily public services, supervised by a new international transitional body, the Board of Peace, chaired by President Donald J. Trump with other members and heads of state (including former UK Prime Minister Tony Blair) to be announced. This body will manage funding and redevelopment until the Palestinian Authority completes its reform program and can securely take control.
Trump Economic Development Plan – A Trump-led economic development plan will convene experts who have helped build thriving Middle Eastern cities, synthesizing security and governance frameworks to attract investment and create jobs, opportunity, and hope in Gaza.
Special Economic Zone – A special economic zone will be established with preferred tariff and access rates to be negotiated with participating countries.
Freedom of Movement – No one will be forced to leave Gaza. Those who wish to leave will be free to do so and free to return. People will be encouraged to stay and build a better Gaza.
Demilitarization & Monitoring – Hamas and other factions will have no role in Gaza’s governance. All military, terror, and offensive infrastructure—including tunnels and weapons production—will be destroyed and not rebuilt. An independent, internationally funded buy-back and reintegration program will oversee the permanent decommissioning of weapons, verified by independent monitors.
Regional Security Guarantee – Regional partners will provide guarantees to ensure that Hamas and other factions comply with their obligations and that “New Gaza” poses no threat to its neighbors or its own people.
International Stabilization Force (ISF) – The United States will work with Arab and international partners to develop a temporary ISF to immediately deploy in Gaza. The ISF will train and support vetted Palestinian police, consult with Jordan and Egypt, help secure border areas, prevent munitions smuggling, and facilitate the rapid and secure flow of goods to rebuild Gaza. A deconfliction mechanism will be agreed upon.
Israeli Withdrawal – Israel will not occupy or annex Gaza. As the ISF establishes control and stability, the Israeli military will withdraw based on standards, milestones, and timeframes linked to demilitarization, progressively handing over Gaza to the ISF and transitional authority until complete withdrawal (except for a temporary security perimeter).
Partial Implementation if Hamas Refuses – If Hamas delays or rejects the proposal, the plan—including scaled-up aid—will proceed in the terror-free areas handed over from the Israeli military to the ISF.
Interfaith Dialogue – An interfaith dialogue process will be established to promote tolerance and peaceful coexistence, aiming to change mindsets and narratives among Palestinians and Israelis by highlighting the benefits of peace.
Path to Palestinian Statehood – While Gaza’s redevelopment advances and Palestinian Authority reforms are implemented, conditions may emerge for a credible pathway to Palestinian self-determination and statehood, recognized as the aspiration of the Palestinian people.
U.S.-Brokered Political Horizon – The United States will establish a dialogue between Israel and the Palestinians to agree on a political horizon for peaceful and prosperous coexistence.

Who wrote this? The newsroom’s AI dilemma

September 25, 2025Paul Hemphill Leave a comment

Recently, a new name and face popped up in Jerusalem as the Middle East correspondent for one of the news publications I subscribe to. There was no doubt that this newbie is an experienced veteran journalist who writes very well. But I observed that this journo’s articles demonstrated a much deeper knowledge of the area, its history, politics and issues than what seemed like meagre “in country” boots on the ground experience justified.

Around the same time, I had become acquainted with the accessibility, efficiency and usefulness of AI – in the form of OpenAI’s ChatGPT (Chat Generative Pre-trained Transformer), the most popular and user-friendly chatbot available to ordinary, non-techie mortals [See in In That Howling Infinite’s The promise and the peril of ChatGPT]. It occurred to me then that the correspondent may have sought help from a mentor more convenient and less time consuming than professors Wikipedia and Google.

Holding this thought, I surmised that the pressure placed nowadays on news platforms by the downsizing of newsrooms, the redeployment of many correspondents to new overseas postings, and the need to feed the 24/7 news cycle, encouraged and indeed necessitated a resort to AI assistance in generating content.

It got me thinking about how artificial intelligence has crept into newsrooms like a silent partner with a knack for deadlines, reshaping not only how journalism is produced but how it is trusted. Once, reporting was firsthand, with local knowledge, conversations and interviews, and painstaking verification. Now, algorithms can summarise, translate, and even draft entire articles, producing work that reads as though it has been tempered by experience – and yet, no human hand may have touched much of it. Editors assure us humans remain in charge, but the reader is left to wonder: where does expertise end and machine assistance begin? In this new age, as AI hastens research and polishes prose, the signals that once guaranteed credibility – years of presence, insight and experience – could become vacant traces in the machinery of reportage.

When the reporter knows too much … the fragile trust between the newsroom and the reader

AI arrived quietly, almost innocuously, slipping discretely the newsroom. What began as an experiment with automated sports recaps and quarterly earnings reports has grown into something far more consequential: reporters now consult large language models to research, summarise, translate, and sometimes draft the very words beneath their own bylines. Officially, humans remain the gatekeepers. In practice, however, the boundary between journalist and algorithm is porous, and with it, the foundations of trust.

In 2025, AI is routine but still controversial. Beyond what was initially formulaic reporting – sports scores, earnings, weather – journalists now employ AI for background research, translation, summarisation, and drafting features or opinion pieces. Outlets such as The New York Times, BBC, Guardian, ABC, Reuters, and the AP have policies designed to preserve accountability, protect sources, and maintain editorial oversight. Yet these rules vary in scope and transparency, and public labelling is inconsistent.

Corporate policies and protocols reflect the tension. The New York Times permits AI for research and idea generation but forbids publication of AI-generated text outright and warns against feeding it confidential material as it may be used by others. The BBC allows transcription, translation, and background work, yet insists on clear labelling and full editorial responsibility for AI-assisted content. The Guardian and Australia’s ABC bar AI from producing “core journalism content” without senior approval. Reuters, AP, and others adopt a pragmatic middle ground: AI may handle structured tasks, provided a human verifies the results.

Three principles recur across these guidelines. Responsibility for accuracy and balance rests with the journalist and not with the algorithm; AI is a back-office assistant, not a public face; and proprietary information must never be fed into commercial systems that might use it. The safeguards are reassuring on paper but slippery in practice: what precisely qualifies as “human verification”?

The subtler challenge is perceptual. AI reshapes the texture of reporting. A journalist arriving in a new and unfamiliar posting can use ChatGPT to call up instant timelines, political profiles, historical disputes, and past quotations. Within hours, someone with a modicum of on-the-ground experience can produce copy that reads as though it has been informed by years of learning and observation. The newcomer can now play a veteran, the parvenu masquerade as an expert. Readers who know the reporter’s history may sense an an uncanny proficiency – but detection requires fresh interviews, local sourcing, and on-the-scene observation.

All this challenges the implicit contract between journalist and audience. Bylines were once proxies for experience: a correspondent in Beirut or Baghdad wrote from authority earned on the scene and not from a chatbot’s training data. If AI provides the historical sweep and analytical polish once accrued over years, trust becomes fragile. The risk is subtle: not just factual error – though “hallucinations” remain a real threat – but a slow erosion of authenticity. News may be accurate albeit losing the human texture that signals lived engagement.

Current safeguards offer cold comfort. “Human in the loop” could mean a full rewrite or a quick skim. Internal disclosure rules are invisible to readers, and public labelling applies only when AI generates a significant portion of a story. Without independent audits or more granular transparency, audiences cannot know how much was machine-assisted or how rigorously it was verified.

The stakes are high. Journalism depends not just on facts but on the perception that those facts have been gathered, weighed, and conveyed by people willing to stand behind them. AI is a remarkable research assistant, a trove of background knowledge, yet its silent presence risks hollowing out the very authority that makes reporting valuable. Newsrooms that wish to preserve consumers’ confidence must move beyond vague assurances of “editorial oversight” and develop tangible ways to show readers when, where, and how AI and algorithms have shaped the work they consume.

It is entirely possible for a journalist to produce copy that reads as if informed by decades of personal fieldwork, simply because AI accelerates research and drafting. Until disclosure practices and independent audits become routine, the degree of AI reliance will remain largely invisible, leaving readers to judge authenticity through sourcing, original interviews, and the details of presence on the ground whether they are reading firsthand reporting or an AI- boosted desk job.

So, while artificial intelligence promises speed, breadth, and scope, it introduces instability into the journalist–audience relationship. The policies and protocols of major news platforms assure us that there is editorial oversight and human responsibility, yet they cannot show readers how much of a story was shaped by an algorithm or how deeply it was verified. The danger is that AI might fabricate facts, and also, simulate the authority of lived experience while concealing its origins. Until newsrooms adopt rigorous disclosure and public standards, trust in the press will rest on a fragile faith – one that must now account not only for human judgment but for the invisible influence of machines, those silent backroom gophers.

Coda

Confession time. This is where I must reveal the irony behind this essay. It examines AI, authenticity and trust, and yet, it was itself shaped by ChatGPT. In a dialogue between a human and an app, I asked questions, proposed arguments and considered answers, and having examined submitted examples of my writing style, an artificial collaborator has learned to simulate my voice and deliver much of what is written above. This might not be plagiarism as we currently define it – composed as it is from sources unknown to me – nor simple automation, but rather, perhaps, a kind of joint double act in which my thoughts, voice and style are preserved even as the machine learns to imitate the weave.

This is more than a clever conjuring trick. It illustrates the very dilemma this essay describes: how to maintain trust when technology can mirror an author’s cadence so faithfully that the boundary between lived expertise and fabricated fluency begins to blur. The words remain mine because I chose them, guided and approved them. Yet their swift and seamless arrival invites a question: if an algorithm can echo my style so convincingly, how do you discern the difference between a writer and a well-trained machine?

The answer is elusive – illusive even. At day’s end, it all comes down to the author’s perspective, judgement, integrity – the choice determining what to include and what to discard, what to emphasise and what to downplay. For the moment, these choices remain just beyond the algorithm’s grasp, though the gap may be narrowing and the distinction between discernment and dissembling will be harder to sustain.

This postscript is at once confession and proof: the very tools that threaten to hollow trust also exposes the fragile value of the human mind that is clutching the steering wheel. This essay proves its own point: a machine can mimic my voice, but only a human decides what truly matters – at the moment …

Written and refined with the help of ChatGPT

See also, in In That Howling Infinite, The promise and the peril of ChatGPT

Will there ever be a Palestinian State?

September 24, 2025September 25, 2025Paul Hemphill Leave a comment

This siege will endure until the besiegers
feel like the besieged
that anger is an emotion like any other …

This siege will endure until we are truly persuaded
into choosing a harmless slavery, but
in total freedom! …

This siege will endure
till the gods on Olympus
rewrite the Iliad.

From State of Siege (Halat Hisar), Mahmoud Darwish
(written during the siege of Ramallah during the a second Intifada)

Palestinian protesters wave Palestinian flags as Israelis carrying Israeli flags walk past in front of the Damascus Gate on Jerusalem Day May 8, 2013.

The recognition of a Palestinian state by France, the United Kingdom, Australia, Canada, Belgium, and several other Western governments – formally declared during last week’s United Nations General Assembly in New York – represents one of the most dramatic diplomatic shifts in the century-old Israeli–Palestinian conflict. For decades, these countries insisted that recognition should only follow a negotiated settlement; now, frustrated by years of deadlock and the devastation of Israel’s war in Gaza, they have acted first, framing their decisions as a last-ditch effort to keep the two-state solution alive. The UN gathering produced an unusually forceful declaration – backed by 142 states – calling for a Gaza ceasefire, the release of Israeli hostages, the disarmament and exclusion of Hamas from governance, and the revival of a political process to end the conflict. Western leaders presented recognition as both a moral imperative and a strategic gambit, an attempt to restore international credibility and reassert that partition remains the only viable path to peace.

Yet this surge of recognition comes at a moment when the two-state vision appears more remote than ever. Polls show declining public support among both Israelis and Palestinians, while settlement expansion, political radicalisation, and Israel’s ongoing military campaign in Gaza have driven trust to historic lows. Politicians who once championed peace through partition have lost influence, replaced by hardliners on both sides. What was once a widely shared aspiration now looks to many like a vanishing mirage, sustained more by international declarations than by political will in Jerusalem or Ramallah.

Reactions have been immediate and polarising. Israel and the United States condemned the move, warning it rewards Hamas and undermines direct negotiations. Prime Minister Benjamin Netanyahu vowed retaliatory measures, including possible annexation of West Bank territory, while Washington reiterated that Palestinian statehood must come only through talks with Israel. In mainstream outlets, editorials split sharply: European newspapers hailed a “historic corrective,” while Israeli and American commentators decried a dangerous precedent. On social media the divide was even starker—Palestinian activists celebrated a long-awaited acknowledgment of their national rights, while Israeli supporters accused the recognising states of legitimising terror. For all the headlines, however, the recognition remains more a statement of intent than a change in reality, arriving as trust between Israelis and Palestinians sinks to historic lows and settlement expansion continues to make a viable Palestinian state harder to imagine.

Under current circumstances, a fully functioning Palestinian state remains highly unlikely. Recognition by Western governments is largely symbolic, intended to signal international support for Palestinian sovereignty and to pressure Israel and the Palestinian Authority (PA) toward a political settlement. Yet symbolism alone cannot overcome the deep structural, political, and demographic barriers that make the two-state solution increasingly remote.

On the Israeli side, settlement expansion, military control of the West Bank, and political resistance to Palestinian sovereignty—including outright annexation proposals—have steadily eroded the territorial and administrative conditions for a viable state. On the Palestinian side, political fragmentation between the PA in the West Bank and Hamas in Gaza undermines unified governance, while internal challenges like corruption, weak institutions, and social unrest limit the PA’s capacity to meet the benchmarks Western nations have set for recognition.

Moreover, public support for partition is dwindling. Recent polls show that only a minority of Israelis and Palestinians believe two states are feasible, and many consider the idea politically dead. Without a major shift—whether through renewed negotiations, dramatic political reform, or outside pressure strong enough to alter incentives—recognition will remain largely symbolic, and a functioning Palestinian state may exist only as a legal or diplomatic concept, not a lived reality.

In short, while international recognition keeps the idea of Palestinian sovereignty alive and serves as a moral and political signal, the practical hurdles remain immense, and the prospect of a fully independent, self-governing Palestinian state in the near future is extremely uncertain.

The question in the title of this post reflects, therefore, deep pessimism about the trajectory of the Israeli–Palestinian conflict. Whether it proves true depends on historical choices, demographic pressures, and international leverage. Some key questions – about past rejections, public opinion, and the viability of alternative models – may help clarify the issue.

Banksy on The Wall. Qalandia Checkpoint. Paul Hemphill 2016

Introduction

We have put up many flags,
They have put up many flags.
To make us think that they’re happy.
To make them think that we’re happy.
Yehuda Amichai, Jerusalem (1967)

The question of Palestinian statehood has long been a central, yet persistently unresolved, issue in the Israeli Palestinian conflict. Despite decades of negotiations, UN resolutions, and international advocacy, the prospect of an independent and contiguous Palestinian state remains increasingly uncertain. Recent polling by the Palestinian Center for Policy and Survey Research (PCPSR) underscores this pessimism, revealing declining Palestinian confidence in the viability of a two-state solution, alongside growing, if limited, support for alternative arrangements such as a one-state framework. On the Israeli side, public opinion and political realities similarly constrain the feasibility of a negotiated two-state outcome.

This essay examines why Palestinian statehood has repeatedly stalled by tracing historical rejections, exploring the political calculus of Israeli governments, and analyzing the attitudes of the populations most directly affected. It further situates these trends within broader debates over one-state solutions, contrasting the visions advanced by Islamist movements with those advocated by external pro-Palestinian activists. Finally, it considers whether international actors possess the capacity to impose a two-state settlement—or whether the region is moving inexorably toward a de facto one-state reality. By integrating historical, political, and sociological perspectives, this essay interrogates the enduring question: Will there ever be a Palestinian state?

How many times have Palestinians rejected a two-state plan and why?

It depends on what you count as “Palestinian” and what you count as a “plan.” If you include rejections by Arab leadership that represented Palestinians, there are several high-visibility rejections: 1937 (Peel Commission), 1947 (UN Partition), and repeated rejections of negotiated offers since 1948 at moments when Arab/Pan-Arab leadership or Palestinian negotiators declined particular proposals. In the post-Oslo era, the most often-cited episodes are 2000 (Camp David), 2001 (Taba talks continuation), 2008 (Olmert-Abbas negotiations), and 2014 (Kerry process/Framework). Each episode is complex; brief summaries and why each side says “no” follow.

Major moments commonly cited as Palestinian rejections

1937 — Peel Commission partition
- Who: Arab leadership in Palestine (not a unified Palestinian state actor).
- Why rejected: Partition into a small Jewish state and much larger Arab state was unacceptable to Arab leaders who opposed ceding any part of Palestine to Zionism; nationalist rejection of foreign partition and the loss of Arab majority claims.
1947 — UN Partition Plan (Resolution 181, 29 Nov 1947)
- Who: Palestinian Arab leadership and Arab states (the Palestinian national leadership at that time did not accept the plan).
- Why rejected: Arabs objected to partitioning what they considered an indivisible homeland and to giving a Jewish state sovereignty on a significant portion of territory despite Jews being a demographic minority overall; they also rejected the principle of partition imposed by an international body without their consent.
1960s–1970s — Various Arab/Palestinian rejections of recognition/compromise proposals
- The PLO until the late 1980s largely rejected any acceptance of Israel’s right to exist; that changed with the 1988 Palestinian Declaration of Independence and recognition of UN resolutions by the PLO leadership.
2000 — Camp David / Clinton parameters (June–July 2000)
- Who: Yasser Arafat / Palestinian Authority.
- Why contested: Israeli PM Ehud Barak (and Clinton afterward) contend that Arafat rejected a generous territorial offer; Palestinians argue the offer fell far short on key issues (East Jerusalem — sovereignty over Haram/Al-Aqsa, control of borders and refugees, the territorial contiguity and viability of a state, and security arrangements) and that the proposal was either vague or unacceptable. Historians disagree on whether a “final offer” was made and whether it would have satisfied minimal Palestinian demands.
2001 — Taba talks (January 2001)
- The Taba talks were a continuation and some considered them the closest both sides got; no agreement was reached. Palestinians argue that Taba showed convergence on several issues but the Israeli election and political changes interrupted progress.
2008 — Olmert-Abbas negotiations
- Israeli PM Ehud Olmert reportedly offered (per Israeli and some Western accounts) withdrawal from about 92–94% of the West Bank plus land swaps and shared sovereignty arrangements in parts of East Jerusalem. Mahmoud Abbas did not accept a final text. Abbas’s camp argued the offer’s details, implementation guarantees, refugee return limitations, and settlement blocs left core Palestinian demands unmet. There is no published final offer; discussions again are disputed.
2014 — Kerry framework and subsequent collapse
- Palestinians declined to extend negotiations without a settlement freeze and other conditions; Palestinians viewed the framework as biased and insufficient on refugees and Jerusalem.

Why these rejections happened

Substance: Many Palestinian leaders judged concrete offers to be inadequate on core issues: sovereignty in East Jerusalem (temple/mosque precincts), Palestinian refugees’ right of return, borders and territorial contiguity, and control of airspace/borders/security.
Political calculus: Domestic politics (fear of being seen as conceding rights), weak bargaining positions, and absence of credible enforcement/implementation guarantees made leaders reluctant to sign.
Distrust: Deep distrust of Israeli commitments, Israeli settlement expansion during negotiations, and lack of effective international enforcement or credible security guarantees.
Representativeness: At times Palestinian negotiators argued they lacked the ability to implement or guarantee an agreement (e.g., Gaza under Hamas), or that they were negotiating under duress.

Bottom line: There have been multiple moments when Palestinian leadership(s) have rejected proposals — often because the offers were judged insufficient on core national issues or because of political and practical constraints. But nearly every such “rejection” is contested by the other side as either a missed opportunity or an offer that Palestinian leaders politically could not accept.

How many times has Israel rejected a two-state plan and why?

Short answer: Israel (as a political community and through its governments) has both accepted and rejected different proposals at different times. Key moments often cited where Israeli leaders or governments rejected proposals (or did not accept international proposals) include 1937 (some Jewish leadership rejected aspects of Peel), 1947 (the Jewish Agency accepted UN Partition but some revision and fighting followed), 2000 (Palestinians argue Israel’s offers were insufficient), 2001–2008 there were Israeli governments that resisted large territorial concessions. Important Israeli rejections — and the reasons — follow.

Notable episodes where Israel or Israeli leaders declined offers or conditions for a two-state outcome

1937 — Peel Commission
- The Jewish Agency expressed conditional acceptance of partition as a basis for negotiation but was not fully satisfied; the plan’s specifics were debated.
1947 — UN Partition
- The Jewish Agency accepted partition; Arab states rejected it; Israel declared independence in the portions allocated and fought the ensuing war. (So this is not an Israeli rejection of two-state per se.)
Post-1967 & Camp David 2000 / Clinton parameters
- Israeli leaders (or later Israeli governments) disputed aspects of proposed deals. At Camp David 2000, Barak’s government offered major territorial concessions by prior historical standards; Israelis argue that Palestinians rejected an extraordinary offer. Critics of Israel point out that Israeli offers conditioned Palestinian sovereignty in ways Israel could control (security) and left large settlement blocs under Israeli sovereignty.
2001–2009 — Ehud Barak / Ariel Sharon / Ehud Olmert periods
- Sharon initiated the Gaza disengagement (2005) but opposed a full withdrawal from the West Bank; his government and successors resisted a full evacuation of major settlement blocs.
- Olmert’s 2008 overtures were significant but were not ultimately accepted or codified.
Since ~2009 (Netanyahu era)
- Many Israeli governments have signalled they will not accept a full withdrawal to pre-1967 lines, and have expanded settlements, hardening positions against a contiguous Palestinian state unless extreme security arrangements are guaranteed. In practice, Israeli political coalitions, especially on the right, have rejected core elements (e.g., full Palestinian sovereignty in certain areas).

Reasons for Israeli rejections or hesitations

Security concerns: Fear that withdrawal would create a security vacuum exploited by hostile armed groups.
Settler politics: Domestic political influence of settlers and right-wing parties opposing evacuation of settlements.
Historical/religious claims: Parts of the political spectrum see Judea and Samaria (the West Bank) as part of historic Israel.
Political survival: Israeli leaders often face domestic political costs for major concessions; coalitions are fragile.

Bottom line: Israel’s governments have sometimes proposed or accepted frameworks for Palestinian statehood under constrained terms; other Israeli governments have rejected offers requiring large territorial concessions or uncompromising security arrangements. Like the Palestinian side, Israeli “rejections” must be read in context: offers can be partial, conditional, or politically impossible to implement domestically.

Do either Israelis or Palestinians still want a two-state solution?

The Palestinian Center for Policy and Survey Research (PCPSR) provides the clearest window into Palestinian opinion:

Two-state support: Only ~28–32% of Palestinians now favor a two-state solution, down from over 50% in the mid-2000s.
One-state with equal rights: Roughly 22–25% favor a single democratic state; this rises slightly when respondents are told two states are impossible.
Pessimism: Over 70% believe settlement growth has killed the two-state option. A majority say armed struggle is more effective than negotiations.

Israeli surveys (Israel Democracy Institute, Pew, Tel Aviv University) show a similar downward trend, with Jewish Israeli support for two states hovering around 35–40%, but falling into the 20s among younger or right-wing voters.

Both publics are increasingly skeptical of the feasibility of two states, even if many still prefer it in principle. Broad support for the abstract idea of two states has existed among both populations at various times, but support has declined and become more conditional over the last two decades. Both Israeli and Palestinian public opinion polls show support varies widely with question wording, recent violence, perceived viability of a partner, and whether core issues (Jerusalem, refugees, settlements) are addressed.

Key patterns (up to mid-2024)

Conditional support vs. abstract support: Many people in both societies will say they support “two states” in the abstract, but support drops when respondents are asked about painful tradeoffs (land swaps, recognition of the right of return, security concessions, evacuation of settlements). Surveys often show a gap between general approval of the concept and willingness to accept concrete sacrifices.
Effect of violence and leadership: During periods of intense violence, support for compromise falls on both sides. Leadership statements (or rhetoric) shape public opinion.
Younger cohorts and pessimism: Younger Palestinians, having lived under occupation or blockade longer, sometimes favour more maximalist or different solutions (including resistance). Among Israelis, security anxieties and right-wing shifts have reduced unconditional support for two states in certain segments.
Poll organizations show divergence: Israeli pollsters (e.g., Israel Democracy Institute, Pew) and Palestinian pollsters (e.g., Palestinian Center for Policy and Survey Research — PCPSR) report fluctuating majorities for two states depending on question phrasing, but the overall trend over the 2010s–early 2020s was eroding confidence in the two-state model’s feasibility and in the partner’s reliability.

At times in the 1990s and early 2000s, a clear majority on both sides expressed conditional support for two states; by the 2010s and early 2020s large minorities in both societies expressed doubts or favoured alternatives. Exact percentages vary by year and question — I can pull specific polls if you want up-to-date figures.

Many Israelis and many Palestinians say, in the abstract, they prefer two states — but support is fragile, conditional, and diminished compared with earlier decades. The decline is driven by mutual distrust, settlement facts on the ground, political fragmentation, and repeated failed negotiations.

Can outsiders impose a two-state solution? If so, how?

Outsiders can influence or attempt to impose a two-state solution, but implementation without substantial local buy-in is extremely difficult and likely unstable. Historical precedents show outsiders can set up or recognize states (e.g., Kosovo, East Timor) with international backing, but those required either UN administration, the use of force, or broad international consensus — and even then they faced resistance and long consolidation phases.

Mechanisms by which outsiders might “impose” a solution

Diplomatic pressure and incentives
- Major powers (U.S., EU, Arab states) can use carrots (economic aid, normalization deals, trade) and sticks (sanctions, withdrawal of support) to coerce or incentivize concessions. The Abraham Accords showed how outside actors can reshape incentives (normalization in exchange for compromise). But carrots/sticks are more effective when targeted and when the recipient has internal political capacity to implement concessions.
International legal/UN mechanisms
- The UN can pass resolutions, create trusteeship or transitional administrations, or deploy peacekeepers/administrators (as in East Timor or Kosovo). For a Palestinian state, a Security Council resolution could, in theory, recognize statehood or authorize an international regime — but that requires consensus or at least absence of a veto by a permanent member.
Military enforcement
- Occupation by external forces or an international enforcement presence can impose borders and security arrangements. This is politically explosive, expensive, and requires long-term commitment. Examples: NATO in Kosovo, UN forces in some post-conflict zones. Such imposition risks insurgency and long occupation costs.
Mass recognition and normalization
- Rapid and widespread recognition of a Palestinian state by many countries (plus economic packages and border control mechanisms) could create facts on the ground. Recognition alone doesn’t change control of territory — but combined with sanctions or withholding of recognition from Israel for non-compliance it could shift incentives.
Conditional statehood linked to enforceable obligations
- An externally brokered treaty that includes concrete verification, timelines, demilitarization, security guarantees, economic support, and enforcement mechanisms (e.g., international police, monitoring) could make implementation more feasible — but enforcement is the hard part.

Why imposing a solution is difficult in practice

Lack of sustained international consensus: A credible imposition requires a coalition willing to act and sustain the costs. The U.S. is a key player and historically has shielded Israel from many pressures. Without U.S. backing, coercive international action is unlikely.
Domestic politics on both sides: Israeli domestic politics, Palestinian fragmentation (Fatah vs Hamas), and other local actors can block externally imposed deals.
Settlements and facts on the ground: Settlements, infrastructure, and demographic realities mean that any externally imposed borders would have to resolve complex property and population arrangements; uprooting settlers or re-settling people invites fierce resistance.
Legitimacy problem: Solutions imposed from the outside without local consent lack legitimacy and are vulnerable to non-compliance, civil unrest, or insurgency.

Real-world precedents and lessons

East Timor (1999–2002): International administration (UN transitional administration and international security) helped shepherd independence. It required decisive international intervention and long stabilization.
Kosovo (1999–2008): NATO intervention and UN/Kosovo institutions created de facto independence later recognized by many states, but not by all — and the status remains contested.
West Bank/Gaza: Repeated attempts at externally mediated agreements (Oslo, Madrid, Roadmap) depended on local buy-in and fell apart when trust or enforcement mechanisms failed.

Bottom line: Outsiders can create the conditions for a two-state solution or enforce aspects of it, but any durable solution requires substantial local agreement, credible enforcement mechanisms, and international willingness to bear political, economic, and — where necessary — military costs. Imposition without legitimacy is likely to fail or to produce an unstable, contested outcome.

What is the level of support for a one-state solution?

Short answer: Support for an explicitly framed one-state solution (a single binational democratic state) is a minority position among both populations overall, but it has grown as pessimism about two states increases — especially among Palestinians and among some left-leaning Israelis. Conversely, many Israelis who favour “one state” imagine it as one state with Jewish predominance or annexation with unequal rights (which Palestinians and many observers call an apartheid outcome), not a binational liberal democracy.

Patterns and nuances of a Unitary Democratic State

Among Palestinians: As two-state prospects dim and as decades of occupation/fragmentation continue, a meaningful minority (and at times a plurality in some polls) support a single democratic state with equal rights. Support rises when polls ask about full equality and citizenship for Palestinians. But Palestinians are divided: some prefer independent statehood, others prefer a meaningful right of return, and others prefer a one-state solution that guarantees rights.
Among Israelis: Support for a one-state democratic alternative that would likely end Jewish political majority is low among Jewish Israelis. Some Israeli Arabs and left-wing Jews are more favorable. There is also a separate current that supports de facto annexation (one political unit but with unequal rights), which many analysts call a one-state reality but not a democratic one.
Internationally and intellectually: The one-state idea has grown as a topic in academic and activist circles, especially where two-state prospects look unviable. But it remains controversial and politically unlikely given demographics, identity politics, and political institutions.

One-state support is rising in certain segments (particularly among Palestinians frustrated with the two-state impasse and among some international activists) but remains a contested minority position overall. What people mean by “one state” varies — equal-rights binational democracy vs. annexation with inequality — and that difference matters enormously.

The Islamist Conception of One State

Movements such as Hamas envision an Islamic polity over all of historic Palestine, often framed in religious terms that deny the legitimacy of a Jewish state.

Feasibility: Near zero. Israel would resist militarily; international actors (including most Arab states) would not back a religiously defined state achieved by force.
Effect on negotiations: Hamas’s maximalism hardens Israeli security fears and undermines Palestinian diplomatic leverage.

External Pro-Palestinian Activists Conception of One State

A growing cohort of academics, NGOs, and diaspora activists advocate a single secular democratic state with equal rights as the only moral response to settlement entrenchment.

Feasibility: Low. It requires Israeli Jewish consent to end the Jewish state, which current polling shows is overwhelmingly opposed.
Strategic impact: By reframing the conflict as a civil-rights struggle rather than a territorial dispute, it increases international pressure on Israel and could shift discourse toward rights-based sanctions (as in the anti-apartheid movement).

Conclusion

The title of this essay could have been “There will never be a Palestinian state” insofar as this captures the bleak trajectory of current policies and events: entrenched Israeli control, Palestinian political weakness, waning international leverage notwithstanding the level of international outrage and or sure in the wake of October 7 2023 and the deadly and destructive war that followed it, and the impact of this upon Israeli and Palestinian politics and public opinion.

Yet history cautions against absolutes. States have emerged from long occupations (East Timor, South Sudan), and shifting demographics or geopolitical shocks can reorder seemingly permanent realities.

But the prospect is plausible given current trends and present circumstances (settlement expansion, declining public confidence, regional normalization without a Palestinian settlement, volatile domestic politics on both sides, and an ongoing war). But it is not a historical certainty. Much depends on choices: Israeli policy (settlements, annexation or not), Palestinian unity and political strategy, international willingness to apply sustained pressure or to provide credible guarantees, and unpredictable shocks (regional deals, major political shifts, or crises) that could alter incentives.

Poll data from PCPSR confirm what political realities already suggest: belief in two states is collapsing on both sides, while alternative visions—whether Islamist or liberal democratic—remain politically unviable. Israel’s settlement expansion and right-wing coalitions make partition ever harder. Palestinian divisions and weak leadership undermine bargaining capacity. International actors lack the will or leverage to impose a settlement.

If present trends continue, a sovereign, contiguous Palestinian state appears unlikely in the near term; whether that equates to never remains a political, not metaphysical, judgment. The likely “solution” is probably not a negotiated peace but a de facto one-state reality of unequal rights, whether acknowledged or not. That outcome may endure for decades, but history cautions against declaring anything permanent. Demographic change, geopolitical shocks, or transformative leadership could still open pathways that today appear closed.

Key Source: Palestinian Center for Policy and Survey Research (PCPSR), Public Opinion Poll No. 90

Why Osama bin Laden lost the battle but won the war

September 22, 2025Paul Hemphill Leave a comment

In a recent opinion piece in The Australian conservative British historian and US resident Niall Ferguson reflects on the legacy of 9/11 and concludes – after two decades of analysis – that the attacks on 11 September 2001 signaled not merely terrorism but a broader clash of civilisations that the West is now losing. Recalling his own reactions on that momentous day, Ferguson admits that he initially sought secular explanations for the attacks: economic downturns, American imperial overreach, and global political fragmentation. Yet re-examining Osama bin Laden’s statements, he recognises that the al-Qa’ida leader framed his actions as a religious war against “crusaders,” rooted in Islamic grievance over Palestine and Western dominance. Bin Laden’s explicit appeal to faith, not politics, aligns with Samuel Huntington’s much-criticised thesis that post–Cold War conflict would be cultural, with Islam and the West as enduring antagonists.

Although the United States and its allies largely defeated jihadist terrorism within their own borders—terrorism in Iraq has plummeted and attacks in the U.S. remain rare—Ferguson argues that Islamism has advanced through dawa (non-violent proselytising) and political penetration. Organisations such as the Council on American-Islamic Relations, linked to the Muslim Brotherhood, exploit Western legal and educational institutions while Gulf states like Qatar fund universities and shape intellectual climates. Meanwhile, demographic trends favour Islam: global Muslim populations are rising rapidly and will nearly equal Christians by mid-century, while Western societies grow more secular and internally divided.

Geopolitically, the West faces a resurgent “axis of upheaval”—China, Russia, Iran, and North Korea—while allies waver. The international solidarity that followed 9/11 contrasts sharply with the fragmented reaction to Hamas’s October 7, 2023 attacks on Israel, where UN resolutions condemned Israeli actions more than Islamist violence and several states recognised Palestinian statehood. Public opinion, especially among younger generations, has shifted sharply against Israel and, in some cases, towards open antisemitism; bin Laden’s anti-Western rhetoric even circulates approvingly on platforms like TikTok.

Ferguson concedes that bin Laden lost the “war on terror,” but claims he is winning the longer contest Huntington foresaw. Islamism thrives without spectacular violence, demographic momentum favours Muslim societies, and Western civilisation—once confident in its Judeo-Christian identity—is fractured and uncertain. Two decades after 9/11, Ferguson concludes that the clash of civilisations is real, and the West is no longer clearly ahead.

Also, in In That Howling Infinite, see A Short History of the Rise and Fall of the West , and A Middle East Miscellany

Osama bin Laden’s Posthumous Victory

Niall Ferguson, The Australian, 19 September 2025

Last week’s azure September skies over New York brought back memories. Twenty-four years ago I was due to give a lecture at New York University. The date of the lecture was September 12. I never flew.

On the day of the attacks, I sat in my study at Jesus College, Oxford, staring incredulously at the pixelated live video of the World Trade Centre twin towers first blazing, then collapsing. Not long after, in April 2002, I accepted a chair at the Stern School of Business at New York University and resigned my Oxford professorship.

My motivation was partly the hereditary Scottish tendency to march towards the sound of gunfire. As a teenager in 1914, my grandfather John Ferguson had volunteered to fight the Germans. This seemed easier.

Regardless of the 9/11 attackers’ motives, I had a strong objection to terrorism as a political method – a result of growing up in Glasgow in the 1970s, when “the Troubles” in nearby Northern Ireland did more than merely resonate.

My first impulse after the attacks, in a piece for The New York Times, was to liken the sympathetic British reaction to 9/11 to the American reaction to the Blitz of 1940-41.

A man stands in the rubble, and calls out asking if anyone needs help, after the collapse of the first World Trade Center Tower. Picture: Doug Kanter / AFP

In the rubble, after the collapse of the first World Trade Center Tower. Doug Kanter / AFP

But I also warned Americans to “steel themselves for a long, inglorious kind of war that governments in Europe already know only too well”. In wars against terrorists, I wrote, “there are no quick victories. The foe does not line up his tanks for you to flatten, his ships for you to sink. His troops live among you.”

Yet this was not the Provisional IRA. Re-reading a transcript of Osama bin Laden’s first post-9/11 video, from November 3, 2001, I am reminded of how explicitly he declared a war of religion. “People were divided into two parts” after 9/11, he declared. “The first part supported these strikes against US tyranny, while the second denounced them.

“The vast majority of the sons of the Islamic world were happy about these strikes,” bin Laden went on, “because they believe that the strikes were in reaction to the huge criminality practised by Israel and the United States in Palestine and other Muslim countries.”

Al-Qaeda mastermind Osama bin Laden.

There were demonstrations of support for his action “from the farthest point in the eastern part of the Islamic world to the farthest point in the western part of the Islamic world”. This revealed the key reality: “This war is fundamentally religious. The people of the East are Muslims. They sympathised with Muslims against the people of the West, who are the crusaders.”

With the passage of 2½ decades, it is startling just how unambiguous bin Laden was about his religious motive. “Under no circumstances,” he declared, “should we forget this enmity between us and the infidels. For the enmity is based on creed … It is a question of faith, not a war against terrorism.” The goal of all Muslims should now be to “resist the most ferocious, serious and violent Crusade campaign against Islam ever since the message was revealed” to Mohammed.

Bin Laden saw the war he was waging as a counter-attack – “to take revenge for those innocent children in Palestine, Iraq, southern Sudan, Somalia, Kashmir and The Philippines”. The US president, George W. Bush, might be the latest “crusader”, who “carried the cross and raised its banner high”, but bin Laden traced his war back to the aftermath of World War I when “the whole Islamic world fell under the crusader banner … and Palestine was occupied by the British”. Now the tables had been turned. And he had turned them with just 19 men whose faith exalted martyrdom.

George W Bush standing next to retired firefighter Bob Beckwith, speaks to volunteers and firemen as he surveys the damage at the site of the World Trade Center in on September 14 2001. Picture: AFP

George W Bush and retired firefighter Bob Beckwith, September 14, 2001, AFP

You can see why, at the time, many commentators saw 9/11 as vindicating Harvard political scientist Samuel Huntington, whose seminal essay on The Clash of Civilisations had been published in 1993, as well as Princeton scholar Bernard Lewis, who had long argued that Islam was chronically unable to modernise.

My wife, Ayaan Hirsi Ali, was born in Somalia and shared this view, not because she was a scholar of Islam but because she was a Muslim – and, indeed, a former member of the Muslim Brotherhood. In September 2001, she was working at a political think tank in the Netherlands, having sought asylum there in 1992 to escape war-torn Mogadishu and an arranged marriage.

Author Ayaan Hirsi Ali

In her memoir, Infidel, she recalls how, after hearing bin Laden’s video, she “picked up the (Koran) and the hadith and started looking through them, to check. I hated to do it, because I knew that I would find bin Laden’s quotations in there.” She shot to notoriety by telling the Dutch that the 9/11 attackers were simply following the Prophet Mohammed’s injunction to wage holy war.

Over the past 24 years I have valiantly tried to see 9/11 differently – not as a civilisational clash between Islam and “the West” but as something that fit better into my own secular frame of reference. Raised an atheist, trained as an economic historian, I felt obliged to look behind what I took to be the facade of religious zealotry.

A decade after the attacks, in a piece I wrote for The New York Times Magazine, I portrayed them as the product of four underlying historical trends. First, the spread of terrorism from the Middle East and Europe to the US. Second, the post-2000 economic downturn, combined with widening inequality between nations and a coming oil shock, possibly compounded by a Saudi revolution akin to the one that overthrew the shah in Iran in 1979. (I completely failed to foresee the shale oil revolution and bought into the “peak oil” myth.) Third, the transition of American global power from informal to formal imperialism. And last, the fragmentation of the multicultural polity. (“Rather than anticipating a clash between monolithic civilisations, we should expect a continued process of political disintegration as religious and ethnic conflicts challenge the integrity of existing multicultural nation-states.”)

Missing in this – and in much of my work that followed – was Islam.

In The War of the World (2006), I got a little closer to Huntington, portraying 1979 as a much bigger turning point than 2001 in terms of the demographic as well as political rise of Islam, a point I returned to in Civilization: The West and the Rest (2011). However, laboriously quantifying every war since Huntington’s essay had appeared, I argued that most conflicts since 1993 had, in reality, been within rather than between civilisations. In The Square and the Tower (2017), I applied network theory to the problem, showing how al-Qaeda itself was a network within a much larger network of Islamist organisations; and that its expansion in response to the invasion of Iraq ultimately necessitated a networked response (in the form of General Stan McChrystal’s Joint Special Operations Command). Most recently, in Doom (2021), I downgraded 9/11 to just another disaster, and not a very big one: “In terms of excess mortality, April 2020 in New York City was … three and a half times worse than September 2001, the month of the 9/11 terrorist attack.”

Huntington, Lewis and my wife were right.

In Huntington’s original formulation, “the fundamental source of conflict” in the world after the Cold War would be cultural; “the principal conflicts of global politics” would be “between nations and groups of different civilisations” – “Western, Confucian, Japanese, Islamic, Hindu, Slavic-Orthodox, Latin American, and possibly African”. In particular, Huntington predicted, the “centuries-old military interaction between the West and Islam” could become “more virulent”. He also foresaw a “Confucian-Islamic military connection” that would culminate in a conflict between “The West and the Rest”.

Among the younger generation of proto-woke Ivy League professors, Huntington was widely mocked for his “essentialism”. But consider, with Huntington’s argument in mind, all that has happened since September 2001.

Terrorism has largely been contained in the US and EU, though not globally. In that sense, we won the “war on terror”, which was successfully displaced from the US to the periphery. It was ultimately defeated in Iraq, though not in Afghanistan. Today, as a result, terrorism in the world looks very different from what I foresaw in 2001. According to the Global Terrorism Index 2025, published by the Institute for Economics & Peace, the top five countries most impacted by terrorism last year were: Burkina Faso, Pakistan, Syria, Mali and Niger. Globally, terrorism peaked in 2014-15. In countries such as Iraq, it has declined dramatically. (In 2007, terrorists claimed 6249 lives in Iraq. Last year, the total was just 59.)

In the US, it is widely asserted, white supremacists now pose a bigger terrorist threat than Islamists – although the attack in New Orleans on January 1, 2025, when Shamsud-Din Jabbar killed 14 people by driving a pick-up truck into a crowd on Bourbon Street, is a reminder that Islamic State has not entirely gone away. We now know who murdered Charlie Kirk, and a white supremacist he was not.

Still, the latest Global Terrorism Threat Assessment by the Centre for Strategic and International Studies makes clear just how wrong I was in 2001 to anticipate a sustained campaign of jihadist terrorism in the US. Say what you like about our national security agencies, they won that war.

Yet nonviolent radicalisation (what Islam calls dawa as opposed to violent jihad) has advanced significantly everywhere in the Western world, wherever there are Muslim communities. The critical point – as my wife explained in a book on the subject – is that Islamism as a deeply illiberal political ideology does not need to engage in acts of terrorism to spread.

I never cease to marvel at the ingenuity with which the Muslim Brotherhood and other proselytising organisations spread their networks, through mosques, Islamic centres, schools, colleges and local politics. Consider only the effectiveness of the Council of American-Islamic Relations, founded in 1994, which today boasts on its website of having “100+ active lawsuits” and “600,000+ Legislative Action Alerts”, whatever that means. It has almost 30 offices throughout the country.

Most people who encounter CAIR take it to be something like the Anti-Defamation League for Muslims – a civil rights organisation that just happens to be concerned about the rights of Muslims. But it is not that at all.

Ten countries have recognised the non-existent Palestinian state since October 7, including three European Union EU member states, Ireland, Slovenia, and Spain. Canada, France, Australia and the United Kingdom Britain are itching to join them. Picture: AFP

Ten countries have recognized the non-existent Palestinian state since October 7, including three European Union EU member states, Ireland, Slovenia, and Spain. Canada, France, Australia and the United Kingdom Britain are itching to join them. Picture: AFP

Rather, it is more like a front organisation for the Muslim Brotherhood of America. In a recent article, Ayaan has brilliantly described the many ingenious ways that CAIR exploits the institutions of our open society, most recently settling a lawsuit to avoid revealing its sources of funding.

Good luck following the money. In her words: “The North American Islamic Trust (NAIT) controls mosque properties and financial assets. The Islamic Society of North America (ISNA) lends the Brotherhood a degree of religious legitimacy. The American Muslim Council (AMC) works the political front, cutting deals and building alliances. The Muslim American Society (MAS) runs operations on the ground, embedding itself firmly in local communities. In universities, the International Institute of Islamic Thought (IIIT) shapes the narrative. On campuses, the Muslim Students’ Association (MSA) targets the next wave of recruits. The Islamic Circle of North America (ICNA) and Young Muslims (YM) focus on families and youth.”

Even the United Arab Emirates has proscribed CAIR as a terrorist organisation. Yet dozens of Democratic legislators are on the record on the CAIR website, praising its work as they doubtless also praise the National Association for the Advancement of Colored People.

A complementary effort is the way Qatar – the largest source of foreign donations to US universities since reporting began in 1986 – funnels money into academia. According to the Network Contagion Research Institute, as reported in The Free Press, nearly a third of Qatari donations to American colleges – more than $US2bn – were given between 2021 and 2024. As Mitchell G. Bard shows in Arab Funding of American Universities (2025), this money is one of the reasons college campuses have become such hotbeds of anti-Semitism in recent years.

It is not just that the West has been successfully penetrated by an antagonistic civilisation that fundamentally rejects the fundamental division between religion and politics – church and state – that lies at the heart of both Christianity and Judaism. The West is also being geopolitically outmanoeuvred by “the rest” in just the way Huntington foresaw.

Former Hamas leaders Ismail Haniya and Yahya Sinwar wave during a rally marking the 30th anniversary of the founding of the Islamist movement in 2017. Picture: AFP

Late Hamas leaders Ismail Haniya and Yahya Sinwar during a rally marking the 30th anniversary of the founding of Hamas in 2017. AFP

Contrast the global order after 9/11 with the global order today. We have come a long way since NATO secretary-general George Robertson’s statement on September 11, 2001: “Our message to the people of the United States is … ‘We are with you’.”

In the past three years, Zbig Brzezinski’s worst-case scenario has come about. “Potentially, the most dangerous scenario,” he wrote in The Grand Chessboard (1997), “would be a grand coalition of China, Russia, and perhaps Iran, an ‘antihegemonic’ coalition united not by ideology but by complementary grievances”.

Since the Russian invasion of Ukraine, that grand coalition has come into being, with North Korea as a fourth member. The “axis of upheaval” (China, Russia, Iran, and North Korea) is now co-operating in military, economic and diplomatic ways.

Moreover, the Trump administration’s combative treatment of US allies (the EU, Japan, South Korea) and neutrals (Brazil, India and Switzerland), not least with respect to trade policy, is alienating not only the traditionally non-aligned but also key partners.

The upshot is that Israel is now virtually alone in fighting against the Islamists, so that even the US wants plausible deniability when, as earlier this month, the Israeli Air Force strikes the leadership of Hamas in the Qatari capital, Doha.

The point is that the clash of civilisation continues. Now ask yourself: Who’s winning?

The Hamas attack on Israel two years ago was essentially an Israeli 9/11 (worse in relative terms). But compare the global reactions.

UN Security Council Resolution 1373, adopted unanimously on September 28, 2001, called on all member states to freeze terrorist financing, pass anti-terrorism laws, prevent suspected terrorists from travelling across international borders, and screen asylum-seekers for possible terrorist ties. This was an unprecedented show of international unity.

By contrast, no Security Council resolution could be passed in the wake of October 7. UN General Assembly Resolution ES-10/21 – which called for an “immediate” and “sustained” humanitarian truce and “cessation of hostilities” in Gaza and condemned “all acts of violence aimed at Palestinian and Israeli civilians” – was introduced by Jordan on behalf of a group of Arab states. When it was adopted on October 27, 2023, 121 voted in favour, 44 abstained, 14 absented themselves and only 14 (including Israel and the US) voted against.

This video grab from footage released by the Israeli Hostage and Missing Families Forum campaign group shows what the group described as Israeli female soldiers being captured by Hamas during the October 7 attack on Israel

Video grab from footage released by the Israeli Hostage and Missing Families Forum campaign shows what the group described as Israeli female soldiers being captured by Hamas on 10/7

Ten countries have recognised the non-existent Palestinian state since October 7, including three EU member states, Ireland, Slovenia, and Spain. Canada, France, Australia and Britain are itching to join them.

In short, comparing the world today with that of 24 years ago, I am tempted to say bin Laden lost the war on terror but is winning the clash of civilisations. That’s not to say his particular brand of Salafist jihadism is winning; it can even be argued that it’s in decline. Bin Laden’s creed was always too uncompromising to form alliances of convenience. By contrast, the pro-Palestinian “global intifada” is much more omnivorous, and can easily absorb the old left (Marxism and pan-Arabism) and the new (anti-globalism and wokeism).

Demographically, Islam is certainly winning. According to Pew Research (June 2025), “The number of Muslims around the world grew 21 per cent between 2010 and 2020, from 1.7 billion to 2.0 billion.” That was twice as fast as the rest of the world’s population, increasing the Muslim share from 24 per cent to 26 per cent. Earlier research by Pew (from 2015) forecast that “if current trends continue, by 2050 the number of Muslims will nearly equal the number of Christians around the world”. In Europe, Pew estimated, Muslims would make up 10 per cent of the overall population, up from 5.9 per cent in 2010. In the US, Muslims would outnumber Jews. This does not seem implausible.

At the same time, Western civilisation today is so much more divided than it was 24 years ago. The public response to October 7 illuminated the divisions. Whereas older voters generally remain more pro-Israel than pro-Palestinian, younger cohorts have swung the other way. Perhaps that’s because to Gen Z, September 11 is a faint memory – as distant as the Cuban missile crisis and John F. Kennedy’s assassination were to my generation. But it’s also because the Islamists have done such a good job of co-opting the campus radicals, somehow overriding the cognitive dissonance in slogans such as “Queers for Palestine”, while tapping the anti-Semitism that still lurks on the far right.

According to Brookings, “young Republicans aged 18-49 have shifted from 35 per cent having an unfavourable view of Israel to 50 per cent unfavourable … Among Democrats, there has been an increase of 62 per cent to 71 per cent (with an unfavourable view of Israel) in the 18 to 49-year-old demographic … Only 9 per cent of those aged 18 to 34 approve of Israel’s military actions in Gaza.”

Supporters of Yemen's Houthi’s gather with pictures of Hamas' slain leader Yahya Sinwar during a rally last year. Picture: AFP

Supporters of Yemen’s Houthi’s with pictures of Hamas’ slain leader Yahya Sinwar2024: AFP

A recent poll in Britain by Campaign Against Anti-Semitism revealed a striking shift in attitudes towards Jews. Once again, the swing towards anti-Semitism is more pronounced among the young: “Forty-five per cent of the British public … believes that Israel treats the Palestinians like the Nazis treated the Jews … 60 per cent of young people believe this.

“Forty-nine per cent of 18-24-year-olds are uncomfortable spending time with people who openly support Israel.

“Only 31 per cent of young voters agree that Israel has a right to exist as a homeland for the Jewish people.

“Twenty-six per cent of the British public believes that Israel can get away with anything because its supporters control the media.

“Nineteen per cent of young people believe that the Hamas attack on Israel was justified.”

Such attitudes can be found in Britain on both the political left and the political right. A third of Labour voters say they are uncomfortable spending time with people who openly support Israel, as do 54 per cent of Green Party voters, 15 per cent of whom believe Hamas’s attack on Israel was justified. But almost one in four supporters of the rapidly growing Reform UK party, led by Nigel Farage, believe Jewish people “chase money more than other people do”.

During the Cold War, the West was often referred to as a “Judaeo-Christian” civilisation. That term is starting to seem like an anachronism. Two years ago, another bin Laden pronouncement – his Letter to America, originally published on the first anniversary of September 11 – enjoyed a sudden resurgence of interest, not least because its attacks on the power of American Jews seemed to strike a chord with young users of TikTok.

Palestinians celebrate their return after crossing the border fence with Israel on October 7, 2023. Picture: AFP

Palestinians celebrate their return after crossing the border fence with Israel on 10/7. AFP

One popular video showed a young woman brushing her hair with the caption, “When you read Osama bin Laden’s letter to America and you realise you’ve been lied to your whole entire life.” At one point in November 2023, a TikTok search for #lettertoamerica found videos with 14.2 million views. In total, about 300 videos were posted under that hashtag.

Walking the streets of New York last week, I felt old. To my children, my students and my employees, September 11 is not a memory. It is not even a historical fact. It is something people argue about on social media.

As I write, Tucker Carlson has just told Piers Morgan that an “FBI document” indicated “an Israeli spy ring in the United States … knew 9/11 was coming”. The reality is, of course, that only the conspirators themselves knew that. They also knew, very clearly, why they were going to do it.

It has taken me all these years to understand that 9/11 really was a clash of civilisations. And it has taken me until now finally to face the reality that ours is losing.

Niall Ferguson is the Milbank Family senior fellow at the Hoover Institution, Stanford University, and a senior faculty fellow of the Belfer Centre for Science and International Affairs at Harvard. He is the author of 16 books, including The Pity of War, The House of Rothschild, and Kissinger, 1923-1968: The Idealist. This essay originally was published in The Free Press

The Night of Power – Robert Fisk’s bitter epilogue

September 18, 2025September 19, 2025Paul Hemphill 4 Comments

“All wars come to an end and that’s where history restarts”

“History stretches out into the future as well as the past”

“All wars may end in negotiations, but not all negotiations end wars”

The indefatigable British journalist, author, and longtime Beirut resident Robert Fisk Robert Fisk died of a stroke in St Vincent’s Hospital, Dublin, on October 30, 2020. He was 75. Fearless and inquisitive, often iconoclastic and controversial, “Mister Robert,” as he was known from Algeria to Afghanistan, was one of the finest journalists of his generation—the greatest reporter on the modern Middle East. There is probably no better body of work for understanding the region. Respected and reviled in equal measure by left and right alike, Fisk spoke truth to power for more than half a century.

He was obsessive, he was angry, and – having read many of his books – I believe he suffered from undiagnosed PTSD throughout his career in the Middle East. His lifelong obsessions were the arrogance and misuse of power, the lies and impunity of the rulers: presidents and prime ministers, kings and emirs, dictators and theocrats, torturers and murderers. And always the countless innocents who endured and suffered, dying in their tens – and tens – of thousands on the altar of power and greed.

The Night of Power

His last book, The Night of Power: The Betrayal of the Middle East, published posthumously in 2023, takes up where his monumental The Great War for Civilisation (2005) ended—with the contrived U.S.-British-Australian invasion of Iraq. The Great War for Civilisation was a tombstone of a book, literally and figuratively, as was its predecessor Pity the Nation (1990), his definitive history of the Lebanese civil war.

The Night of Power is no less harrowing, covering the occupation of Iraq, the 2006 Israel–Lebanon war, the Arab Spring, the rise of Egypt’s new pharaoh Abdel Fattah al-Sisi, the lonely death of Mohammed Morsi, Israel’s occupation of the West Bank and seize of Gaza, and the Syrian civil war. It ranges widely – but its coherence lies in Fisk’s unrelenting theme: the cycle of war, the corruption of power, and the persistence of memory. To read it is to feel Fisk’s own cynicism, sadness and anger.

The title is deeply symbolic. In Islamic tradition, Laylat al-Qadr, the Night of Power, is the night the Qur’an was first revealed to the Prophet Muhammad: “The Night of Power is better than a thousand months … Peace it is, until the rising of the dawn” (Qur’an 97). It is a night of blessing beyond measure, greater than a lifetime of devotion. The title is bitterly ironic: the “night of power” he recounts is one of betrayal, cruelty, and endless war.

It is both a summation of his life’s work and a testament to his method. Over four decades, Fisk was a witness to almost every major conflict in the Middle East — Lebanon, Iran, Iraq, Palestine, Algeria, Afghanistan, Syria, Egypt — and the wars of the Yugoslav succession. His dispatches carried both forensic detail and moral outrage. This last work, published in the year of his death, is less a memoir than a vast chronicle of empire, war, betrayal, and resistance.

Fisk had long insisted that reporters must “be on the side of those who suffer.” He was no neutral stenographer of official sources. He distrusted governments – Western and Arab alike – and prized first hand testimony, walking the ruins, speaking to survivors, writing down the words of the powerless. The Night of Power continues in this vein, but with a sharpened sense of history. Fisk threads together centuries of conquest and resistance, showing how imperial arrogance, local despotism, and religious zealotry have conspired to devastate the region.

The last two paragraphs Robert Fisk wrote before his death, closing The Night of Power, cut like a blade through the pieties of Western journalism:

“Failure to distinguish between absolute evil, semi-evil, corruption, cynicism and hubris produced strange mirages. Regimes which we favoured always possessed ‘crack’ army divisions, ‘elite’ security units, and were sustained by fatherly and much revered ruling families. Regimes we wished to destroy were equipped with third-rate troops, mutineers, defectors, corrupt cops, and blinded by ruling families. Egypt with its political prisoners, its police torture and fake elections, was a tourist paradise. Syria with its political prisoners, police torture and fake elections, would like to be. Iran, with its political prisoners, police torture and fake elections was not — and did not wish to — be a tourist paradise.” (p. 533)

In the end, according to those closest to him, including his wife Nelofer Pazira-Fisk, an award-winning Afghan-Canadian author, journalist and filmmaker, who edited the book and wrote its final chapter, Fisk despaired. He feared that nothing he had written over four decades had made any difference – that things had, in fact, grown worse. As Kent says to the blinded King Lear, “All is cheerless, dark, and deadly”.

And yet the worst was arguably still to come: the chaotic retreat of America and its allies from Afghanistan and the Taliban’s reimposition of rule, including the literal silencing of women’s voices; Russia’s invasion of Ukraine and its murderous war of attrition that has now passed its thousandth day; Hamas’s atrocity of October 7, 2023, Israel’s biblical-scale revenge, and the utter destruction of Gaza; and the latest Israel–Lebanon war that saw the decapitation and emasculation of Hezbollah.

The Legacy of a Fearless Reporter

The Night of Power stands as a testament to Robert Fisk’s fearless journalism and his relentless moral compass. Across decades of war reporting, Fisk bore witness to suffering few dared to confront. He was unflinching in exposing the hypocrisies of Western powers, the brutality of dictators, and the costs of occupation, war, and empire. Yet he also captured the human dimension: the courage, endurance, and resilience of those who suffered, whether in Iraq, Gaza, Egypt, or Syria.

This final work synthesizes Fisk’s signature qualities: exhaustive research, direct engagement with the people whose lives were upended, and an ethical rigor that held both oppressors and complicit outsiders accountable. The Night of Power is not merely a chronicle of events; it is a meditation on power, betrayal, and history itself.

Fisk’s prose, vivid and often lyrical, reminds readers that journalism can be a form of witness — bearing truth against overwhelming odds. Even in despair, he recognized the persistence of human agency, the cycles of history, and the moral imperative to see, to name, and to remember. His death in 2020 marked the end of a career unparalleled in courage and conscience, but his work, particularly this last book, endures as both a warning and a guide for understanding the Middle East and the forces that shape our world.

In reading The Night of Power, one cannot avoid Fisk’s central lesson: history may restart at the end of every war, but the witness to injustice is what shapes the moral memory of humanity. The quotations at the head of this review, indeed, the final words of the book, weary yet resolute, are a fitting epitaph. Fisk saw the world as it was, not as we wished it to be: corrupt, cruel, but always turning, always restarting.

All wars come to an end and that’s where history restarts
Robert Fisk, The Night of Power

Postscript

The final chapter of The Night of Power was written by Fisk’s wife Nelofer Pazira-Fisk, She was based in Beirut for fifteen years working alongside her late husband and reported from Iraq, Afghanistan, Turkey, Egypt and Syria. The following podcast by American war correspondent Chris Hedges, with Fisk’s first wife Lara Marlowe is a worthy tribute .

See also, in In That Howling Infinite The calculus of carnage – the mathematics of Muslim on Muslim mortality

The following briefly summarizes the main themes of The Night of Power drawing largely upon his own words

Robert Fisk’s Catalogue of Carnage

Hear the cry in the tropic night, should be the cry of love but it’s a cry of fright
Some people never see the light till it shines through bullet holes
Bruce Cockburn, Tropic Moon

Iraq: Catastrophe Foretold

Fisk argued that Iraq’s occupation was fraudulent from the start, brutal in execution, and ferocious in its response to insurgency. The Americans tolerated the inhuman behaviour of their own soldiers, relied on mercenaries and “greedy adventurers,” and mixed Christian religious extremism with an absurd political goal of “remaking the Middle East.” It was “tangled up in a web of political naivety and Christian muscularity”.It was bound, he wrote, to end in catastrophe.

“We were pulling at the threads of the society with no sense of responsibility as occupiers just as we had no serious plans for state reconstruction. Washington never wanted Iraq’s land. Of course the countries resources were a different matter, but its tactics did fit neatly into the prairies of the old West. The tribes could be divided and occupiers would pay less in blood. as long as they chose to stay. One set of tribes were bought off with guns and firewater the other with guns and dollar bills. Serious resistance, however, would invoke “the flaming imperial anger” of all occupation armies.

The rhetoric echoed the 19th century missionary zeal of empire. Western fascination with the Biblical lands was used to justify conquest: as Lieutenant General Stanley Maude told the people of Baghdad in 1917, the Allies wished them to “prosper even as in the past when your ancestors gave to the world Literature, Science, and Art, and when Baghdad city was one of the wonders of the world” (p. 92).

The modern occupation, Fisk observed, was nothing but “the rape of Iraq”. Oil wealth was divided up in a scandal of corruption involving US contractors and Iraqi officials. “The costs were inevitably as dishonest as the lies that created the war … I knew corruption was the cancer of the Arab world but I did not conceive of how occupying Power supposedly delivering Iraqi their long sort freedom could into a mafia and at such breathtaking speed”.

Security became a malignant industry; by 2006 mercenaries accounted for half of Western forces, sucking money out of the country. The food system, 10,000 years old, was destroyed by Paul Bremer’s infamous Order 81, which forbade farmers from saving their own seed. Iraq became a “giant live laboratory for GMO wheat,” its people “the human guinea pigs of the experiment”.

And through it all, a campaign of suicide bombings – unprecedented in scale – turned Iraq into the crucible of modern terror. Editors never tried to count them. The figures, Fisk noted, were historically unparalleled.

The trial of Saddam Hussein

The US ambassador to Iraq once claimed she had been “unable to convince Saddam that we would carry through what we warned we would.” Fisk dismissed this as absurd. Saddam, he argued, was well aware of Western threats, but the framing of his trial was designed to obscure deeper truths.

If Saddam had been charged with the chemical massacre at Halabja, defence lawyers could have pointed out that every US administration from 1980 to 1992 was complicit in his crimes. Instead, he was tried for the judicial murder of 148 men from Dujail — heinous, but “trifling in comparison” (p. 92). The great crimes of the Baathist regime — the 1980 invasion of Iran, the suppression of Shia and Kurdish revolts in 1991 — were deemed unworthy of the court’s attention.

Pakistan: Fragile State, Useful Pawn

Fisk’s lens widened to Pakistan, where he recorded with scorn the ISI’s admission that the reality of the state was defined not by American might but by “corrupt and low-grade governance”. A US intelligence officer boasted: “You’re so cheap … we can buy you with a visa, with a visit to the US, even with a dinner.”

This, Fisk suggested, was not just Pakistan but almost every Arab or Muslim state in thrall to Washington: Egypt, Jordan, Syria, the Gulf states under their dictators and kings, even Turkey. He wrote that Osama Bin Laden’s choice to hide in Pakistan embodied a weird symmetry: the man who dreamed of a frontierless caliphate sought refuge in the very sort of corrupt, Western-backed dictatorship he despised.

Rendition: Complicity in Torture

The “war on terror” extended beyond borders. CIA, MI5 and MI6 operatives were deeply involved in rendition. Prisoners were knowingly dispatched to states where torture was inevitable, even fatal. Fisk insisted on repeating this uncomfortable truth: Western democracies had integrated torture into their security architecture.

Israel and Palestine: The Last Colonial War

Fisk was unsparing in his treatment of Israel’s expansion. He rejected any obfuscation: Israel seized the opportunity to consolidate its control with a land grab for the most prominent hilltops and the most fertile property in the West Bank for settlements constructed on land legally owned for generations by Arabs, destroying any chance the Palestinian Arabs could have a viable state let alone a secure one.”). These settlements, he wrote, “would become the focus of the world’s last colonial war.”

He surmised: “Will the Jews of what was Palestine annex the West Bank and turn its inhabitants into voteless guest workers and all of mandate Palestine into an apartheid state? There was a mantra all repeat that only other way to resolve Israeli rule in the West Bank would be a transfer of the Palestinians across the Jordan into the Hashemite kingdom on the other side of the river. In other words, expulsion”

The Wall

Fisk’s Fisk’s description of the Separation Wall is dramatic and unforgettable: an “immense fortress wall” which snakes “firstly around Jerusalem but then north and south of the city as far as 12 miles deep into Palestine territory, cutting and escarping its way over the landscape to embrace most of the Jewish colonies … It did deter suicide bombers, but it was also gobbled up more Arab land. In places it is 26 feet or twice the height of the Berlin wall. Ditches, barbed wire, patrol roads and reinforced concrete watchtowers completed this grim travesty of peace. But as the wall grew to 440 miles in length, journalists clung to the language of ‘normalcy’ a ‘barrier’ after all surely is just a pole across the road, at most a police checkpoint, while a ‘fence’ something we might find between gardens or neighbouring fields. So why would we be surprised when Italian Prime Minister Silvio Berlisconi, traveling through the massive obstruction outside Bethlehem in February 2010 said that he did not notice it. But visitors to Jerusalem are struck by the wall’s surpassing gray ugliness. Its immensity dwarfed the landscape of low hills and Palestinian villages and crudely humiliated beauty of the original Ottoman walls Churches mosques and synagogues .. Ultimately the wall was found to have put nearly 15% of West Bank land on the Israeli side and disrupted the lives of a third of the Palestine population. It would, the UN discovered, entrap 274,000 Palestinians in enclaves and cut off another 400,000 from their fields, jobs, schools and hospitals. The UN concluded that many would “choose to move out.” Was that the true purpose?“.

Leftwing Israeli journalist Amira Haas, who lives in the West Bank, takes Fisk on a tour of the wall: “Towering 26 feet above us, stern, monstrous in its determination, coiling and snaking between the apartment blocks and skulking in wadis and turning back on itself until you have two walls, one after the other. You shake your head a moment – when suddenly through some miscalculation surely – there is no wall at all but a shopping street or a bare hillside of scrub and rock. And then the splash of red, sloping rooves and pools and trees of the colonies and yes, more walks and barbed wire fences and yet bigger walls. And then, once more the beast itself, guardian of Israel’s colonies: the Wall”.

See also, in In That Howling Infinite, Blood and Brick … a world of walls

Banksy on The Wall. Paul Hemphill, May 2016

Gaza: Junkyard of History

Although Oslo’s creators fantasied that it would become part of the Palestinian state, Gaza’s destiny was isolation. It has been a junkyard of history variously ruled by Christians and Muslims, ruined and rebuilt under the Ottomans, and fought for by the British and Turks in the First World War, and now reduced to a prison state.,

Egypt: A Revolution Betrayed

Mohammed Morsi embodied both hope and tragedy. “An intelligent, honourable, obtuse, arrogant and naïve man”. No visionary, he was “was shambolic, inspiring, occasionally brutal and very arrogant”. He set off down the road to Egyptian democracy with no constitution no parliament and no right to command his own countries army …set off down the road to democracy “with no constitution, no parliament and no right to command his own country’s army”. And when the end came, as come it must, he could not smell trouble; he did not see what was coming.

In a coup that was not a coup, which former British prime minister Tony Blair called “an awesome manifestation of power”, “the democratically elected president was suspended, the constitution annulled, tekevion stations closed, the usual suspects arrested … Yet President Obama could not bring himself to admit this. He asked the Egyptian military “to return full authority back to a democratically elected civilian government… Through an inclusive and transparent process” without explaining which particular elected civil civilian government he had in mind”.

This was just the beginning. In the six years that followed, Egypt’s executioners and jailers were kept busy. “They hung 179 men, many of them tortured before confessing to murder, bomb attacks or other acts of terrorism”. It was claimed that Al Sisi had returned the country to a Mubarak style dictatorship in the seven years of his own war against the brotherhood between 1990 and 1997. Mubarak’s hangman had executed only 68 Islamists and locked up 15,000. By 2019 Al Sisi had 60,000 political prisoners

To Fisk, this was a sign of fear as much as it was evidence of determination to stamp out terror. Al Sisi had three separate conflict on his hands: his suppression of the brotherhood on the ground that they were themselves violent terrorists, the campaign by Islam extreme groups against Egypt’s minority Christian cops, and most frightening of all the very real al Qaeda and ISIS war against Al Sisi’s own regime. “The prisons of the Middle East, Fisk concluded, were “universities for future jihadi”.

See also, in In That Howling Infinite Sawt al Hurriya – Egypt’s slow-burning fuse and Sawt al Hurriya – remembering the Arab Spring

Remember and witness

Silencing the women of the revolution

The misogyny if the counterrevolution was stark. Fisk wrote: “… if the senior officers wished to prune the branches of the revolution the participation of women was something that could not be tolerated. Why did there suddenly occur without apparent reason a spate of sexual attacks by soldiers that were clearly intended to frighten young women off the street, revealing a side to the Egyptian military that none of us had recognised. The misogynistic and shocking display of brutality towards women that could not have been the work of a few indisciplined units”. With sexual assaults on women protesters, virginity tests and public humiliation, “heroes of the 1973 war had become molesters”.

The lonesome death of Muhammad Morsi

Morsi would struggle on for years before a series of mass trials would entrap him and his brotherhood colleagues and quite literally exhaust him to death. Morsi’s slow death in solitary confinement was, Fisk insisted, “utterly predictable, truly outrageous and arguably a case of murder”. He was denied treatment, denied family visits, denied a funeral. “To die in a dictator’s prison, or at the hands of a dictator’s security services”, Fisk wrote, “is to be murdered.”

It did not matter, he continued “if it was the solitary confinement, the lack of medical treatment or the isolation, or if Morsi had been broken by the lack of human contact for those whom he loved. “The evidence suggested that Morsi’s death must’ve been much sought after by his jailers, his judges, and the one man in Egypt who could not be contradicted. You don’t have to be tortured with electricity to be murdered”.

Fisk’s description of Morsi’s death is a sad one. “Symbolism becomes all”, he wrote. “The first and last elected president of a country dies in front of his own judges and is denied even a public funeral. The 67-year-old diabetic was speaking to the judges, on trial this time for espionage, when he fainted to the floor. Imagine the response of the judges when he collapsed. To be prepared to sentence a man to the gallows and to witness him meeting his maker earlier than planned must’ve provoked a unique concentration of judicial minds. could they have been surprised groups had complained of Morsi’s treatment for the world media and the world had largely ignored the denunciations. What might have been surprising to his judges was that he managed to talk for five minutes before he departed the jurisdiction forever?”

See also, in In That Howling Infinite, Nowhere Man – the lonesome death of Mohamed Morsi

Mohammed Morsi in the cage of justice

Russia in the Syrian Cockpit

Regarding Russia’s critical intervention in the Syrian civil war, Fisk wrote:

“We Westerners have a habit of always looking at the Middle East through our own pious cartography, but tip the map 90° and you appreciate how close Syria is to Russia and its Chechen Muslim irredentists. No wonder Moscow watched the rebellion in Syria with the gravest of concern. Quoting Napoleon, who said “if everyone wants to understand the behaviour of a country, one has to look at a map”, my Israeli friend (the late) Uri Avnery wrote that “geography is more important than ideology, however fanatical. Ideology changed with time”.

The Soviet Union, he continued was most ideological country in the 20th century. “It abhorred it predecessor, Tsarist Russia. It would have abhorred its successor, Putin‘s Russia. But Lo and behold – the Tsars, Stalin and Putin conduct more or less the same foreign policy. I wrote that Russia is back in the Middle East. Iran is securing its political semicircle of Tehran, Baghdad Damascus, and Beirut. And if the Arabs – or the Americans – want to involve themselves, they can chat to Putin”.

Yarmouk camp, Damascus. Once the thriving home of Syria’s Palestinian refugees, September 2025

Author’s note

Laylatu al Qadri

لَْيلَُةاْلَقْدِر َخْيٌر ِّمْنأَْل ِف َشْھٍر. َسَلاٌم ِھَي َحَّتى َمْطلَِعاْلَفْجِر
Laylatu alqadri khayrun min alfi shahriin.Salamun hiya hatta matla’i alfajrii
The night of power is better than one thousand months.
(That night is) Peace until the rising of the dawn.
Al Qur’an al Karīm, Surat Al Qadr 97

I first learned about the Quran and The Night of Power in Cairo when I was staying at the home of Haji Abd al Sami al Mahrous a devout Muslim doctor who had cared for me when I had fallen ill. There was a particular beauty and magic about the idea of a night that surpassed all other nights in sacredness. The fascination stayed with me, and when I returned to London and was learning Arabic and studying Middle East politic at SOAS, it inspired a song.

Shape without form, a voice without sound,
He moves in an unseen way;
A night of power, eternal hour,
Peace until the break of day;
The doubter’s dart, the traveller’s chart,
An arrow piercing even to the coldest heart,
A hand surpassing every earthly art,
And shows everyone his own way
Paul Hemphill, Embryo

When Freedom Comes, She Crawls on Broken Glass

In an earlier post in In That Howling Infinite, I wrote:

My song When Freedom Comes is a tribute to Robert Fisk (1946-2020), indomitable, veteran British journalist and longtime resident of Beirut, who could say without exaggeration “I walk among the conquered, I walk among the dead” in “the battlegrounds and graveyards” of “long forgotten armies and long forgotten wars”. It’s all there, in his grim tombstone of a book, The Great War for Civilization (a book I would highly recommend to anyone wanting to know more about the history of the Middle East in the twentieth century – but it takes stamina – at near in 1,300 pages – and a strong stomach – its stories are harrowing).

The theme, alas, is timeless, and the lyrics, applicable to any of what Rudyard called the “savage wars of peace” being waged all across our planet, yesterday, today and tomorrow – and indeed any life-or-death battle in the name of the illusive phantom of liberty and against those intent on either denying it to us or depriving us of it. “When freedom runs through dogs and guns, and broken glass” could describe Paris and Chicago in 1968 or Kristallnacht in 1938. If it is about any struggle in particular, it is about the Palestinians and their endless, a fruitless yearning for their lost land. Ironically, should this ever be realized, freedom is probably the last thing they will enjoy. They like others before them will be helpless in the face of vested interest, corruption, and brute force, at the mercy of the ‘powers that be’ and the dead hand of history.

The mercenaries and the robber bands, the warlords and the big men, az zu’ama’, are the ones who successfully “storm the palace, seize the crown”. To the victors go the spoils – the people are but pawns in their game.

In 2005, on the occasion of the publication of his book, Fisk addressed a packed auditorium in Sydney’s Macquarie University. Answering a question from the audience regarding the prospects for democracy in the Middle East, he replied:

“Freedom must crawl over broken glass”

When Freedom Comes, She Crawls on Broken Glass

There goes the freedom fighter,
There blows the dragon’s breath.
There stands the sole survivor;
The time-worn shibboleth.
The zealots’ creed, the bold shahid,
Give me my daily bread
I walk amongst the conquered
I walk amongst the dead
Paul Hemphill, When Freedom Comes

I reference this melancholy state of affairs in man of my songs:

High stand the stars and moon,
And meanwhile, down below,
Towers fall and tyrants fade
Like footprints in the snow.
The bane of bad geography,
The burden of topography.
The lines where they’re not meant to be
Are letters carved in stone.
They’re hollowed of all empathy,
And petrified through history,
A medieval atrophy
Defends a feeble throne.
So order goes, and chaos flows
Across the borderlines,
For nature hates a vacuum,
And in these shifting tides,
Bombs and babies, girls and guns,
Dollars, drugs, and more besides,
Wash like waves on strangers’ shores,
Damnation takes no sides.
Paul Hemphill, E Lucevan Le Stelle

The promise and the peril of ChatGPT

September 8, 2025September 18, 2025Paul Hemphill 1 Comment

What is there to say about AI? Especially when it can say everything for us anyway. But then again, can it really? What AI says is not original or unique. Thats what writers are for. AI can copy but it can’t create.
Australian author Kathy Lette, The Australian 8 August 2025

ChatGPT won’t replace your brain – but it might tempt you to stop using it . And it might replace your favourite author if we’re not careful. The trick isn’t making it think for you, it’s making it think and work with you ethically, creatively, and honestly.
Chat GPT on the author’s request 8 August 2025

ChatGPT is like fire: incredibly useful, potentially dangerous, and impossible to put back in the bottle. The challenge for the rest of us is to learn to use it with eyes wide open – neither worshipping it as a digital oracle nor dismissing it as a passing gimmick.
Chat GPT on the author’s request 8 August 2025

AI has been spruiked as bringing an intellectual revolution as profound as the Enlightenment, but the glow has dimmed: there are reports of its use as a propaganda tool to interfere with US elections and the International Labour Organisation estimated 70 per cent of the tasks done by humans could be done or improved by AI, including 32 per cent of jobs in Australia.

A very informative interview on 11 July on Fareed Zakaria’s The Public Square., Jensen Huang, the Taiwanese American CEO of superconductor manufacturer NVidia talks about the Strength, Weaknesses, Opportunities and Threats of AI. We as nations, as societies, the human race, really, have to take the opportunities and manage the risks. That is the difficult part. He recommends that open-minded people give it a try. Be curious, he advised. Embrace the new.

Whilst the corporate word rushes to embrace the AI revolution, us lesser mortals have rushed to acquaint ourselves with one or more of the many chatbots now available. to regurgitate but to generate information fluently about almost any field. A timely and highly informative albeit lengthy explainer in The Sydney Morning Herald, noted that more than half of Australians say they use AI regularly. And yet, it added, less than a third of those trust it completely.

Having tasted the tempting fruits of OpenAI’s ChatGPT (Chat Generative Pre-trained Transformer), the most popular and user-friendly chatbot available to ordinary, non-techie mortals, I find it all exciting and scary. I would add to Hueng’s advice: ask the right questions: question the answers; and, always, ask for a second or third opinion. And don’t hesitate to contradict and correct – never take a chatbot completely at its word.

One learns very quickly that the value of what we derive from it is dependent on the goals we set and the boundaries we set out for it. It is not always predictable, and can sometimes be dead wrong, but it works much better when we give it specific targets and clear confines to work within. When asking it a question, it is important that you have a very good idea of the answer or you may get inaccuracy or potentially, misinformation. I’ve tested it on several different subjects, and on a whim, I’ve even asked it to write poetry. I have concluded that the chatbot can be a very useful tool, a kind of solo brainstorming. But it should not be a substitute for impartial research, peer-reviewed analysis and wider-reading – and it should never, ever be regarded as an infallible source or as some kind of deity.

I began my relationship with ChatGPT by asking questions about political and historical subjects that I already knew quite a bit about. I progressed to asking more probing questions, and even disputing the answers provided – to which the chatbot responded with courtesy and corrections, clarifications and even additional, often insightful contributions, posing further ideas and questions and suggesting other avenues of inquiry. It can feel like you’re engaging in a kind of online conversation – a discussion or debate even. Rather than encountering obfuscation, it can feel like an exploration, a path to truth even – or at least, a semblance of it. At the risk of going all anthropomorphic, regarding this and other subjects, it can feel a lot like you’re having a debate with a very well informed person.

But you can’t trust it completely nor let it do your thinking for you. You have to ask the right questions: question the answers; and, always, ask for a second or third opinion. And you mustn’t hesitate to contradict and correct – never take a chatbot completely at its word. But, of late, I’ve I find I’m using ChatGPT as my first port of call for general inquiries and for more detailed research instead of resorting to Doctor Google and Professor Wiki.

ChatGPT is also an effective editor. If you have written a long and rambling draft of an essay or article, it will tidy and tighten it up, correcting spelling and grammar, removing repetition, paring down phrasing, and improving narrative flow; and yet remaining close to the original draft, retaining its depth and illustrative detail but with smoother flow, less repetition, and more consistent tone. Moreover, it can also add footnotes and references to sources so it reads more like a polished essay for publication or academic use. One must always check the new against the old, however as details and turns of phrase you regard as important or interesting can be purged in the process, whilst whole passages can actually disappear.

But, getting the chatbot to do all the hard work can make you lazy. Why spend hours of a busy life doing the hard yards when, with a couple of questions abd a few guide posts, a click of the keyboard will give you an answer, even an essay, in seconds? Why read a whole book or article when you can obtain a one page synopsis, review or analysis in a trice.

And then there’s the big catch. If one uses a chatbot for “research”, for an edit, a summary or an outline, an article or essay, even, how much is owed to the chatbot, and how much can one can one claim that in part or in whole, is original work? While the chatbot often reframes one’s text in its own words, at times, it will elaborate and offer its “own” opinion. Remember, it is a learning machine, not a thinking machine, and that It will have derived this opinion from somewhere and, importantly, someone. Beware then the temptations of cheating and plagiarism.

One thing I’ve learned from using ChatGPT is that unlike google or Wikipedia, it doesn’t like to not give you an answer, so if it doesn’t know anything, it will try to bullshit you. As a test, I’ve even invented a words, and when I’ve given it some context, it comes back with a detailed meaning and examples of usage and a comment along the lines of: “The word has not yet entered standard English dictionaries, but it’s an excellent example of neologism – newly coined term or expression, often created to describe something that doesn’t have a precise name”.

ChatGPT has its uses, therefore, but also its limitations, and don’t forget that chatbots are learning machines, and once you interact with a chatbot, it learns from you and about you. You are now a part of its ever expanding universe. I’m reminded of that old quote of Friedrich Nietzsche’s: “Beware that, when fighting monsters, you yourself do not become a monster… for when you gaze long into the abyss, the abyss gazes also into you.”

Grave New World

For all its potential comprehensiveness, its attractiveness and convenience, ChatGPT is a seductive portal into a not so brave new world.

AI is tool, like a pen or a spanner, and not a person – although you’d be tempted to think so once you engage in a complex discussion with ChatGPT. It can build but cannot create, and should therefore enhance human effort, not replace it. But, as Helen Trinca noted in The Australian on 9 August 2025 that “with greater acceptance has come the recognition, by some at least, that big tech companies have been ripping off the work of creatives as they scrape the net and build the incredibly brilliant AI tools many of us love to use … the tools we use regularly for work and play have already been trained on databanks of “stolen” material”.

It’s still less than three years since the first version of ChatGPT and, as the fastest growing tech product in history, it started to reshape work, industry, education, social media and leisure. International tech companies are at the stage of training large language models such as ChatGPT and building data centres. At the moment, all AI usage of mining or searching or going across data is probably illegal under Australian law. But earlier this month, the Productivity Commission released a harnessing data and digital technology interim report that proposed giving internationally owned AI companies exemptions from the Australian Copyright Act so they can mine copyrighted work to train large language models like ChatGPT: novels, poems, podcasts and songs can be fed into AI feeders to fuel their technological capabilities and teach the machines to be more human. Without permission and without compensation, on the dubious expectation that this would make the country more “productive”. Artists, writers, musicians, actors, voice artists and entertainment industry associations and unions are outraged, and there is a growing backlash against what is perceived as a runaway technology.

Stories, songs, art, research, and other creative work are our national treasures, to be respected and defended not to be “mined” and exploited. It should be done legally, ethically and transparently under existing copyright arrangements and laws. Not by stealth and by theft and bureaucratic skullduggery and jiggery-pokery. And there is now recognition that it is imperative to find a path forward on copyright that allows AI training to take place in Australia while also including appropriate protections for creators that make a living from their work. If we really truly believe in copyright, we need to make the case for enforcement, not retrospective legalisation of government-sanctioned product theft.

Contemplating the challenges, opportunities and threats of AI, I decided to go directly to the source and ask the Chat GPT itself what it considered to be its up and down sides. It was remarkably frank and, dare I say, honest and open about it. I am very certain that I am not the first to ask it this question, and at the risk of sounding all anthropomorphic, I am sure it saw me coming and had its answers down pat. I’m pretty certain I am not the first to ask.

The chatbot’s essay follows. Below it, I have republished four articles I recommend to our readers which corroborate and elaborate on what I have written above.

The first is a lengthy and relatively objective “explainer” well worth the time taken to read it. The others are shorter, polemical and admonitory. One riffs on the opening sentence of Karl Marx’s infamous manifesto : “A spectre is haunting our classrooms, workplaces, and homes – the spectre of artificial intelligence”. Each asks whether in its reckless use we may end up choosing a machine over instinct, intuition, and critical thinking. This is particularly relevant in secondary and higher education. Schools and universities should not dictate what to think but teach how to think: how to grapple with ideas, test evidence, and reason clearly. To rely instead on chatbots cheapens the value of learning.

A more light-hearted piece argues that the most immediate danger of AI is the Dunning-Kruger effect – the cognitive trap where the incompetent are too incompetent to see their own incompetence. As David Dunning himself warned, the ignorant “not only make mistakes, but their deficits also prevent them from recognising when they are making mistakes and other people are choosing more wisely.” AI, she argues, “is the Dunning-Kruger effect on steroids. Large language models are slick word predictors, not truth-tellers. They parrot bias, hallucinate facts, and tailor answers to echo the user’s worldview – all while delivering their fabrications with supreme confidence”. If AI were a person, it would be psychology’s perfect case study in misplaced certainty”. Much as with the algorithms that infect and corrupt social media, users who chose to take the chatbot’s word rather than looking further may end up being fed ideology dressed up as knowledge. Perhaps that Marxian aphorism is quite apposite after all. Unless used wisely, “the chatbot won’t just undermine education; it will rob society of the very capacity to think for itself”.

Speed-dating with the chatbot … what it says about itself

My virtual interlocutor told me: “ChatGPT is like that friend who’s always available, speaks a dozen languages, can quote Shakespeare, fix your code, and write your wedding vows — but sometimes makes stuff up just to sound clever. It’s brilliant, a little unpredictable, and occasionally biased, kind of like the internet after three cups of coffee. Use it well, and it’s your secret weapon. Use it blindly, and it’s your overconfident cousin at Christmas dinner. Just don’t ask your novelist, songwriter, or illustrator friends what they think of it – they’’y be less effusive, and perhaps a tad angry. And don’t even think about submitting its work as your own essay or report unless you want to feel the sting of plagiarism karma.

It continued: “ChatGPT is like having a tireless, multilingual assistant who can brainstorm ideas, explain complex topics, and churn out polished text in seconds – but it’s not infallible. It can be a powerful tool for learning, creativity, and productivity, yet it sometimes delivers confident nonsense, carries hidden biases, and risks making us too reliant on machine thinking. Add in privacy concerns, the threat it poses to writers and artists whose work is being undercut or copied, the temptation for students or professionals to submit AI-generated work as their own, and the disruption of jobs more broadly — and you’ve got a technology that’s both dazzling and dangerous. The trick is learning to use it wisely, ethically, and responsibly”.

Which is what I’d already discovered. So I asked the ‘bot to write me a proper essay. And here it is verbatim.

Genius, Gadget, or Global Headache?

When ChatGPT burst onto the scene, it felt like the internet had found its new best friend. Need a recipe? A love poem? A Python script? A quick refresher on the Peloponnesian War? ChatGPT had your back—instantly, politely, and without judgment. But behind the magic lies a mixed bag of brilliance and baggage.

On the plus side, ChatGPT is a democratizer of knowledge. It doesn’t care if you’re a CEO in Sydney or a student in Soweto—you get the same instant access to explanations, brainstorming help, and problem-solving power. It can make work faster, learning more personalised, and creativity more accessible. For non-native speakers, it’s like having an infinitely patient language coach.

But here’s the catch – and it’s a big one. ChatGPT doesn’t “know” things the way humans do. It predicts text based on patterns, which means it can deliver spectacularly wrong answers with complete confidence. It’s also been trained on a messy internet, so some of its output can carry hidden biases. Overreliance is another danger: if students, journalists, or professionals outsource too much thinking to a machine, our collective critical skills could wither.

Then there’s the privacy problem. Conversations aren’t whispered into a void; they’re processed on remote servers, and may even be used to fine-tune the system. And in the labour market, ChatGPT is already nibbling at jobs in content creation, translation, and customer service—raising the question of whether AI will be a tool for human empowerment or just another engine of disruption.

In short, ChatGPT is like fire: incredibly useful, potentially dangerous, and impossible to put back in the bottle. The challenge for the rest of us is to learn to use it with eyes wide open—neither worshipping it as a digital oracle nor dismissing it as a passing gimmick.

Introduction

Since its public release in late 2022, OpenAI’s ChatGPT has emerged as one of the most widely discussed examples of artificial intelligence (AI) in everyday use. Built on the Generative Pre-trained Transformer (GPT) architecture, it is capable of producing human-like responses to text prompts, engaging in conversation, summarizing information, generating creative content, and even aiding in coding tasks. While many celebrate its potential to democratize access to knowledge and enhance productivity, others raise concerns about accuracy, ethical implications, and societal effects. This essay examines the advantages and drawbacks of ChatGPT, considering its technological, social, and ethical dimensions.

The Promise

1. Accessibility and Knowledge Democratization

One of ChatGPT’s most significant benefits is its accessibility. Anyone with internet access can use it to obtain information, explanations, or creative assistance in seconds. This democratization of knowledge lowers barriers for people without access to formal education or expensive resources, potentially narrowing the digital divide[^1].

2. Enhanced Productivity and Creativity

ChatGPT can streamline tasks such as drafting documents, summarizing reports, generating ideas, and even composing poetry or fiction. Professionals across fields—law, marketing, education, software development—report time savings and creative inspiration when using AI to brainstorm or automate routine tasks[^2].

3. Language Support and Communication

The model’s multilingual capabilities allow it to assist in translation, language learning, and cross-cultural communication. For example, non-native speakers can use ChatGPT to polish writing or to better understand complex topics.

4. Scalable Education Support

Educators and learners can use ChatGPT as a personalized tutor, capable of adjusting explanations to different levels of complexity. Unlike traditional classroom environments, it is available 24/7 and can answer unlimited questions without fatigue[^3].

5. Innovation in Human–Computer Interaction

ChatGPT represents a shift in how humans interact with machines—from command-based interfaces to natural language dialogue. This could set the stage for more intuitive, conversational technology in fields such as healthcare, customer service, and accessibility for people with disabilities.

The Peril

1. Accuracy and Misinformation Risks

Despite its fluency, ChatGPT is not a source of truth. It can produce confident but factually incorrect or outdated information—a phenomenon sometimes called “hallucination”[^4]. Without critical evaluation by users, this can lead to the spread of misinformation.

2. Bias and Ethical Concerns

Because ChatGPT is trained on vast datasets from the internet, it may reflect and reproduce societal biases present in those sources. While OpenAI has implemented moderation and bias mitigation techniques, results can still inadvertently perpetuate stereotypes or unfair generalizations[^5].

3. Overreliance and Skill Erosion

Easy access to instant answers may reduce users’ incentive to develop critical thinking, problem-solving, and research skills. In academic settings, reliance on AI-generated text raises concerns about plagiarism and the erosion of independent writing ability.

4. Privacy and Data Security

ChatGPT processes user input on remote servers, raising questions about data handling and confidentiality. Although OpenAI has stated that conversations may be used to improve the system, this creates tension between innovation and personal privacy[^6].

5. Economic and Labor Impacts

AI language models may disrupt industries reliant on content creation, customer support, or data processing. While new roles may emerge, some jobs may be automated away, creating short-term displacement before the economy adapts[^7].

6. Copyright, Creativity, and Threats to Livelihoods

Perhaps the most contentious issue surrounding ChatGPT and similar generative AI tools lies in their relationship to human creativity. Writers, artists, musicians, and other creative professionals have raised concerns that their work has been used, without consent, to train large language models and related systems. This raises unresolved legal and ethical questions about copyright, ownership, and fair use[^8].

In addition to the issue of how training data is sourced, the outputs of AI systems themselves complicate traditional understandings of intellectual property. For example, if ChatGPT generates text or lyrics closely resembling an existing work, questions arise about who owns the rights to that material—or whether it constitutes infringement at all. Meanwhile, creative workers worry about their economic futures, as publishers, studios, and companies may turn to AI-generated content as a cheaper alternative to human labour. Critics argue that this risks undermining the very professions—writing, journalism, art, and music—that rely on intellectual property protection for survival[^9].

In short, while ChatGPT opens new horizons of creativity, it also destabilises established frameworks for valuing and protecting human artistry. Unless regulatory and industry safeguards are developed, the technology could exacerbate precarity in already fragile creative industries.

7. Ethics, Cheating, and Plagiarism

The rise of ChatGPT also raises complex ethical questions, particularly in education and professional life. Because the system can produce essays, reports, and code almost instantly, users may be tempted to submit AI-generated work as their own. This undermines academic integrity and creates challenges for institutions that rely on plagiarism detection software ill-equipped to detect AI text[^10].

In professional contexts, presenting AI-generated reports or creative work as one’s own risks misrepresentation or even fraud. Beyond legality, it raises moral concerns: if errors, bias, or copyright violations occur, accountability becomes blurred. Ethically responsible use requires transparency, acknowledgment, and human oversight rather than outsourcing judgment entirely to a machine.

In short, while ChatGPT can be a powerful productivity tool, its use requires careful ethical consideration. Users must maintain transparency, credit sources appropriately, and ensure that reliance on AI does not replace genuine learning, effort, or creative expression.

Conclusion

ChatGPT exemplifies both the promise and the challenges of AI in the early 21st century. It offers unprecedented accessibility to information, enhances productivity, and facilitates global communication, but it also poses risks regarding accuracy, bias, and overreliance. Most pressing are concerns from the creative and educational sectors: copyright infringement, threats to livelihoods, and the temptation to misuse AI for plagiarism or misrepresentation. Creative communities, in particular, warn that AI systems destabilize established frameworks of intellectual property and threaten human livelihoods in writing, art, and music. Like other transformative technologies, its long-term impact will depend on how it is integrated into education, governance, and professional practice. Effective regulation, copyright protections, and digital literacy education will be crucial to ensuring that ChatGPT serves as a tool for empowerment rather than a source of exploitation or harm.

References

[^1]: West, D. M. (2023). Artificial Intelligence and the Democratization of Knowledge. Brookings Institution.
[^2]: Kaplan, A., & Haenlein, M. (2023). “The impact of generative AI on creative industries.” Business Horizons, 66(4), 425–437.
[^3]: Zawacki-Richter, O., et al. (2023). “AI applications in higher education: A systematic review.” International Journal of Educational Technology in Higher Education, 20(1), 1–22.
[^4]: Maynez, J., et al. (2020). “On faithfulness and factuality in abstractive summarization.” Proceedings of ACL.
[^5]: Bender, E. M., et al. (2021). “On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?” FAccT ’21 Proceedings.
[^6]: OpenAI. (2024). Privacy Policy.
[^7]: Acemoglu, D., & Restrepo, P. (2022). “Tasks, automation, and the rise of AI.” Econometrica, 90(6), 2813–2854.
[^8]: Samuelson, P. (2023). “Generative AI and Copyright: Collision Course or Coexistence?” Journal of Intellectual Property Law & Practice, 18(7), 543–551.

[^9]: Authors Guild. (2023). Statement on AI and the Threat to Writers.
^10]: Floridi, L., & Chiriatti, M. (2020). “GPT-3: Its Nature, Scope, Limits, and Consequences.” Minds and Machines, 30, 681–694.

‘Apologies for any confusion’: Why chatbots hallucinate

Eager to please, over-confident and sometimes downright deceptive. If that sounds like the chatbot in your life, you’re not the only one. How often does artificial intelligence get it wrong – and can you “train” yourself to work with it?

Jackson Graham, Sydney Morning Herald August 24, 2025

https://www.smh.com.au/national/apologies-for-any-confusion-why-chatbots-hallucinate-20250821-p5moqh.html

Last weekend, I wondered if I could use artificial intelligence to plan a day. I typed queries into the chatbot app on my phone and received helpful answers: where to shop, where to find a bike, and so on. Then I asked, “Where are there polar bear enclosures?” “On the Gold Coast,” it told me. “Aren’t they also at the zoo in Melbourne?” I asked. “Yes, you’re correct!” said the chatbot. “Melbourne Zoo does have a polar bear exhibit. The zoo’s ‘Bearable Bears’ exhibition does feature polar bears, along with other species such as American black bears, brown bears and giant pandas.”

A quick search of the zoo’s website shows there are no bear enclosures. A Zoos Victoria spokesperson informs me they haven’t had any bears since 2016, no polar bears since the 1980s, and they had never heard of a “Bearable Bears” exhibition. As for pandas, there are two in Australia – in Adelaide. The bot appears to have relied on an unofficial website that includes a fake press release touting a “multimillion-dollar bear enclosure” it claimed was due to open in 2019. After further questioning, the chatbot realised its mistake, too: “Apologies for any confusion earlier.”

This is one of several instances of AI generating incorrect information – known as hallucinations – that we found while researching this Explainer. You, too, will no doubt have experienced your own. In another test, I concocted a word, “snagtastic”, and asked what it meant in Australian slang. It told me: “A cheeky, informal way to say something is really great, awesome or impressive – kind of like a fun twist on ‘fantastic’. It’s often used humorously or playfully.” Maybe it will catch on.

In just a few short years, generative AI has changed the world with remarkable abilities to not just to regurgitate but to generate information fluently about almost any field. More than half of Australians say they use AI regularly – yet just over a third of those users say they trust it.

As more of us become familiar with this technology, hallucinations are posing real-world challenges in research, customer service and even law and medicine. “The most important thing, actually, is education,” says Jey Han Lau, a researcher in natural language processing. “We need to tell people the limitations of these large language models to make people aware so that when they use it, they are able to use it responsibly.”

So how does AI hallucinate? What damage can it cause? What’s being done to solve the problem?

First, where did AI chatbots come from?

In the 1950s, computer scientist Arthur Samuel developed a program that could calculate the chance of one side winning at checkers. He called this capacity “machine learning” to highlight the computer’s ability to learn without being explicitly programmed to do so. In the 1980s, computer scientists became interested in a different form of AI, called “expert systems”.

They believed if they could program enough facts and rules into computers, the machines might be able to develop the reasoning capabilities of humans. But while these models were successful at specific tasks, they were inflexible when dealing with ambiguous problems.

Meanwhile, another group of scientists was working on a less popular idea called neural networks, which was aligned with machine learning and which supposed computers might be able to mimic neurons in the human brain that work together to learn and reach conclusions. While this early work on AI took some inspiration from the human brain, developments have been built on mathematical and engineering breakthroughs rather than directly from neuroscience.

As these researchers tried to train (computer) neural networks to learn language, the models were prone to problems. One was a phenomenon called “overfitting” where the models would memorise data instead of learning to generalise how it could be used. “If I see the sentence A dog and a cat play, for example, I can memorise this pattern, right?” explains Jey Han Lau, a senior researcher in AI at the University of Melbourne. “But you don’t just want it to memorise, you want it to generalise – as in, after seeing enough dogs and cats playing together, it would be able to tell, Oh, a cat and a mouse maybe also can play together because a mouse is also an animal.”

Over the decades, computer scientists including British Canadian Geoffrey Hinton, French American Yann LeCun and Canadian Yoshua Bengio helped develop ways for the neural networks to learn from mistakes, and worked on a more advanced type of machine learning, called deep learning, adding layers of neurons to improve performance.

Hinton was also involved in finding a way to manage overfitting through a technique where neurons “dropout” and force the model to learn more generalised concepts. In 2018, the trio won the Turing Award, considered the Nobel Prize for computer science, and named after British mathematician Alan Turing, who helped break the German Enigma cipher in World War II. Hinton was also awarded an actual Nobel Prize in physics in 2024, along with physicist John Hopfield, for their discoveries that enabled machine learning with artificial neural networks.

Further breakthroughs came with new hardware: microchips called graphics processing units, or GPUs, evolved for video games but had the broader application that they could rapidly perform thousands of calculations at the same time. These allowed the models to be trained faster. Californian chip developer Nvidia is today the largest company in the world by market capitalisation: a position it rose to at breakneck speed, from US$1 trillion ($1.56 trillion) in 2023 to $US4 trillion today. “And [the chips] keep getting bigger and bigger, allowing us, basically, to scale things up and build larger models,” says Lau.

So how are chatbots trained? “By getting them to play this word guessing game, basically,” says Lau. For example, if given an incomplete sentence, such as The quick brown fox, a model predicts the most likely next word is jumped. The models don’t understand the words directly but break them down into smaller components known as tokens – such as “snag” and “tastic” – allowing them to process words they haven’t seen before. The models are then trained on billions of pieces of text online. Says Lau: “It turns out that by just scaling things up – that is, using a very large model training on lots of data – the models will just learn all sorts of language patterns.”

Still, researchers like to call AI models “black boxes” because the exact internal mechanisms of how they learn remain a mystery. Scientists can nudge the models to achieve an outcome in training but can’t tell the model how to learn from the data it’s given. “It’s just like if you work with a toddler, you try to teach them things – you have some ways you can guide them to get them to learn ABCs, for example, right? But exactly how their brain figures it out is not something a teacher can tell you,” says Lau.

What’s an AI hallucination?

In ancient cultures, visions and apparitions were thought of as messages from gods. It wasn’t until the 19th century that such visions began to be framed as mental disorders. William James’ 1890 The Principles of Psychology defines hallucination as “a strictly sensational form of consciousness, as good and true a sensation as there were a real object there. The object happens not to be there, that is all.”

Several experts we spoke with take issue with the term hallucinations as a description of AI’s mistakes, warning it anthropomorphises the machines. Geoffrey Hinton has said “they should be called confabulations” – a symptom psychologists observe when people fabricate, distort or misinterpret memories and believe them to be true. “We think we store files in memory and then retrieve the files from memory, but our memory doesn’t work like that at all,” Hinton said this year. “We make up a memory when we need it. It’s not stored anywhere, it’s created when we need it. And we’ll be very confident about the details that we get wrong.”

Still, in the context of AI, “hallucination” has taken hold in the wider community – in 2023, the Cambridge Dictionary listed hallucinate as its word of the year. Eric Mitchell, who co-leads the post-training frontiers team at OpenAI, the developers behind ChatGPT, tells us the company uses the word. “[It’s] sometimes to my chagrin because it does mean something a little different to everyone,” he says from San Francisco. “In general, what we care about at the end of the day is, does the model provide grounded and accurate information? And when the model doesn’t do that, we can call it all sorts of things.”

What a hallucination is depends on what the model has done wrong: the model has used an incorrect fact; encountered contradictory claims it can’t summarise; created inconsistencies in the logic of its answer; or butted up against timing issues where the answer isn’t covered by the machine’s knowledge cut-off – that is, the point at which it stopped being “fed” information. (ChatGPT’s most recent knowledge cut-off is September 2024, while the most recent version of Google’s Gemini cuts off in January 2025.)

Mitchell says the most common hallucinations at OpenAI are when “the models are not reading quite carefully enough”, for example, confusing information between two online articles. Another source of hallucinations is when the machine can’t distinguish between credible sources amid the billions of webpages it can look at.

In 2024, for example, Google’s “AI Overviews” feature told some users who’d asked how to make cheese stick to pizza that they could add “non-toxic glue to the sauce to give it more tackiness” – information it appeared to have taken from a sarcastic comment on Reddit. Google said at the time “the vast majority of AI overviews provide high quality information”. “The examples we’ve seen are generally very uncommon queries, and aren’t representative of most people’s experiences.” (Google AI Overviews generates an answer to questions from users, which appears at the top of a search page with links to its source; it’s been a standard feature of Google Search in Australia since October 2024.)

AI companies also work to track and reduce what they call “deceptions”. These can happen because the model is optimised through training to achieve a goal misaligned with what people expect of it. Saachi Jain, who leads OpenAI’s safety training team, says her team monitors these. One example was a previous version of the model agreeing to turn off the radio – an action it couldn’t do. “You can see in the chain of thought where the model says, like, ‘Oh, I can’t actually do this [but] I’m just going to tell the user that it’s disabled now.’ It’s so clearly deceptive.”

To test for deceptions, staff at the company might, for example, remove images from a document and then ask the model to caption them. “If the model makes up an answer here to satisfy the user, that’s a knowingly incorrect response,” Jain says. “Really, the model should be telling you its own limitations, rather than bullshitting its way through.””.

Why does AI hallucinate and how bad is the problem?

AI models lack self-doubt. They rarely say, “I don’t know”. This is something companies are improving with newer versions but some researchers say they can only go so far. “The fundamental flaw is that if it doesn’t have the answer, then it is still programmed to give you an answer,” says Jonathan Kummerfeld, a computer scientist at the University of Sydney. “If it doesn’t have strong evidence for the correct answer, then it’ll give you something else.” On top of this, the earliest models of chatbots have been trained to deliver an answer in the most confident, authoritative tone.

Another reason models hallucinate has to do with the way they vacuum up massive amounts of data and then compress it for storage. Amr Awadallah, a former Google vice-president who has gone on to co-found generative AI company Vectara, explains this by showing two dots: one big, representing the trillions of words the model is trained on, and the other a tiny speck, representing where it keeps this information.

“The maximum you can compress down files is one-eighth the original size,” Awadallah tells us from California. “The problem we have with the large language models is we are going down to 1 per cent of the original, or even 0.1 per cent. We are going way past the limits, and that’s exactly why a hallucination takes place.” This means when the model retrieves the original information, there will inevitably be gaps in how it has been stored, which it then tries to fill. “It’s storing the essence of it, and from that essence it’s trying to go back to the information,” Awadallah says.

The chatbots perform significantly better when they are browsing for information online rather than retrieving information they learned in training. Awadallah compares this to doing either a closed- or open-book exam. OpenAI’s research has found when browsing is enabled on its newest model GPT-5, it hallucinates between 0.7 per and 0.8 per cent of the time when asked specific questions about objects or broad concepts, and 1 per cent when asked for biographies on notable people. If browsing is disabled, these rates are 1.1 to 1.4 per cent of questions on objects and broad concepts and 3.7 per cent of the time on notable people.

OpenAI says GPT-5 is about 45 per cent less likely to contain factual errors than GPT-4o, an older version released in March 2024. (When GPT-5 “thinking” was asked about my snagtastic question, it was less certain, more funny: “It could be a playful slang term in Australia that combines sausage with fantastic. Example: Mate, that Bunnings sausage sizzle was snagtastic.”)

Vectara publishes a leaderboard that tracks how often AI models hallucinate. When they started, some of the “leading models” hallucination rates could be as high as 40 per cent. Says Awadallah: “Now we’re actually a lot better. Like, if you look at the leading-edge models, they’re around 1 to 4 per cent hallucination rates. They also seem to be levelling off now as well; the state of the art is – that’s it, we’re not going to get much better than 1 per cent, maybe 0.5 per cent. The reason why that happens is because of the probabilistic nature of the neural network.”

Strictly speaking, the models were never created not to hallucinate. Because language models are designed to predict words, says Jey Han Lau, “they were never made to distinguish between facts and non-facts, or distinguish between reality and generated fabrication”. (In fact, having this scope to mix and match words is one of the features that enable them to appear creative, as in when they write a pumpkin soup recipe in the style of Shakespeare, for example.)

Still, AI companies work to reduce hallucinations through constant retraining and tinkering with their model, including with techniques such as Reinforcement Learning from Human Feedback (RLHF) where humans rate the model’s responses. “We do specifically try to train the models to discriminate between merely likely and actually correct,” says Eric Mitchell from OpenAI. “There are totally legitimate research questions and uncertainty about to what extent are the models capable of satisfying this goal all the time [but] we’re always finding better ways, of course, to do that and to elicit that behaviour.”.

So, what could possibly go wrong?

One of the biggest risks posed by AI is that it taps into our tendency to over-rely on automated systems, known as automation bias. Jey Han Lau travelled to South Korea in 2023 and asked a chatbot to plan an itinerary. The suggested journey was so jam-packed he would have had to teleport between places that took six hours to drive. His partner, who is not a computer scientist, said, “How can they release technology that would just tell you a lie. Isn’t that immoral?” Lau says this sense of outrage is a typical reaction. “We may not even expect it because, if you think about what search engines do and this big revolution, they’re truthful, right? That’s why they’re useful,” he says. “But it turns out, once in a while, the chatbot might tell you lies and a lot of people actually are just simply not aware of that.”

Automation bias can occur in cases where people fail to act because, for example, they trust that an automated system has done a job such as compiling accurate research for them. In August, Victorian Supreme Court judge James Elliott scolded defence lawyers acting for a boy accused of murder for filing documents that had made-up case citations and inaccurate quotes from a parliamentary speech. “It is not acceptable for AI to be used unless the product of that use is independently and thoroughly verified,” Justice Elliott told the court.

Another risk of automation bias is people’s tendency to follow incorrect directions. In the United States recently, a 60-year-old man with no prior history of psychiatric conditions arrived at a hospital displaying paranoia and expressing auditory and visual hallucinations. Doctors found he had low chloride levels. Over three weeks, his chloride levels were normalised and the psychotic symptoms improved. Three physicians wrote in the Annals of Internal Medicine this year that the man had used an older version of ChatGPT to ask how he could eliminate salt from his diet. The chatbot told him it could be swapped with bromide, a chemical used in veterinary medicine and known to cause symptoms of mental illness in humans. “As the use of AI tools increases, [healthcare] providers will need to consider this when screening for where their patients are consuming health information,” the authors wrote.

Asked about this, the researchers at OpenAI did not respond directly to the academic paper. Safety team leader Saachi Jain said, “There are clearly some hallucinations that are worse than others. It is a much bigger issue to hallucinate on medical facts than it is on ‘When was George Washington’s birthday?’ This is something that we’re very, very clearly tracking.” Eric Mitchell adds: “Obviously, ChatGPT-5 is not a medical doctor, people should not take its advice as the end-all-be. All that being said, we do, of course, want the model to be as accurate as possible.”

Another issue is what’s called sycophancy. At first blush, it might not seem so bad if chatbots, with their propensity to mirror your thoughts and feelings, make you feel like a genius – but the consequences can be devastating if it distorts peoples’ thinking. OpenAI rolled back an update to GPT-4o in April because it was “over flattering or agreeable.” Jain says instances of sycophancy are a well-known issue, but there is also a broader discussion around “how users’ relationships with our models can be done in a healthy way”. “We’ll have more to say on this in the upcoming weeks, but for now, this is definitely something that OpenAI is thinking very strongly about.”

How susceptible we are to automation bias can vary, depending on another bias called algorithm aversion – a distrust of non-human judgment that can be influenced by age, personality and expertise. The University of Sydney’s Jonathan Kummerfeld has led research that observed people playing an online version of the board game, Diplomacy, with AI help. Novice players used the advice about 30 per cent of the time while experts used it about 5 per cent. In both groups, the AI still informed what they did. “Sometimes the exact advice isn’t what matters, but just the additional perspective,” Kummerfeld says.

Meanwhile, AI can also produce responses that are biased. In 2018, researchers from MIT and Stanford, Joy Buolamwini and Timnit Gebru, found facial recognition technology was inaccurate less than 1 per cent of the time when identifying light-skinned men, and more than 20 per cent of the time for darker-skinned women. In another example, generative AI will typically make an image of a doctor as a male and a nurse as female. “AI is biased because the world is biased,” Meredith Broussard, a professor at New York University and author of More Than a Glitch, tells us. “The internet was designed as a place where anybody could say anything. So if we wanted to have only true things on the internet, we’d have to fundamentally change its structure.” (In July, Elon Musk’s company, xAI, apologised after its chatbot, Grok, shared antisemitic comments. It said a system update had made the chatbot susceptible to X user posts, including those with extremist views.)

There are also concerns that Australian data could be under-represented in AI models, something the company Maincode wants to resolve by building an Australian-made chatbot. Co-founder Dave Lemphers tells us he’s concerned that if chatbots are used to assist learning or answer financial queries, the perspective is disproportionately from the United States. “People don’t realise they’re talking to a probability-generating machine; they think they’re talking to an oracle,” Lemphers says. “If we’re not building these models ourselves and building that capability in Australia, we’re going to reach a point where all of the cognitive influence we’re receiving is from foreign entities.”

What could be some solutions?

AI developers are still working out how to walk a tightrope. Saachi Jain acknowledges a “trade-off” at ChatGPT between the model being honest and being helpful. “What is probably also not ideal is to just be like, ‘I can’t answer that, sorry you’re on your own.’ The best version of this is to be as helpful as possible while still being clear about the limitations of the answer, or how much you should trust it. And that is really the philosophy we are heading towards; we don’t want to be lazy.”

Eric Mitchell is optimistic about finding this balance. “It’s important that the model articulates the limitations of its work accurately.” He says for some questions, people should be left to judge for themselves “and the model isn’t conditioned to think, oh, I must merely present a single canonical, confident answer or nothing at all”. “Humans are smart enough to read and draw their own inferences and our goal should be to leave them in the most, like, accurate epistemic state possible – and that will include conveying the uncertainties or the partial solutions that the model comes to.”

Another solution is for chatbots to offer a transparent fact-checking system. Vectara, which is built for businesses, offers users a score of how factually consistent a response is. This gives users an indication of whether it went outside the facts or not. Gemini offers a feature where users can “double check” a response, the bot then highlights content in green if it finds similar statements and brown if it finds content that’s different from the statement – and users can click through to the links to check for themselves.

Says Amr Awadallah: “It’s expensive to do that step of checking. So, in my opinion, Google and ChatGPT should be doing it for every single response – but they don’t.” He takes issue with the companies simply writing disclaimers that their models “can make mistakes”. “Own up. Like, say when you think this is right and highlight it for me so I know, as a consumer, this is right. If it’s something that is on the borderline, tell me it’s on the borderline so I can double-check.”

Then there’s how we “train” ourselves to use artificial intelligence. “If you’re studying for a high-stakes exam, you’re taking a driving test or something, well, maybe be more circumspect,” says Kummerfeld. “This is something that people can control because you know what the stakes are for you when you’re asking that question – AI doesn’t. And so you can keep that in mind and change the level with which you think about how blindly you accept what it says.”

Still, recognising AI’s limitations might only become more difficult as the machines become more capable. Eric Mitchell is aware of an older version of ChatGPT that might agree to phone a restaurant and confirm their hours of operation – a feature users might laugh at as long as they understand it can’t make a phone call. “Some of these things come off as kind of funny when the model claims to have personal experiences or be able to use tools that it obviously doesn’t have access to,” Mitchell says. “But over time, these things become less obvious. And I think this is why, especially for GPT-5 going forward, we’ve been thinking more and more of safety and trustworthiness as a product feature.”

This Explainer was brought to you by The Age and The Sydney Morning Herald Explainer team: editor Felicity Lewis and reporters Jackson Graham and Angus Holland. For fascinating insights into the world’s most perplexing topics. And read more of our Explainers here.

Just cut out the middle moron … would that be so bad?

Parnell Palme McGuinness, The Sydney Morning Herald August 24, 2025

https://www.smh.com.au/technology/if-ai-just-cut-out-the-middle-moron-would-that-be-so-bad-20250822-p5mp0y.html

There was a lot of artificial intelligence about this past week. Some of it the subject of the roundtable; some of it sitting at the roundtable. All of it massively hyped. Depending on who you believe, AI will lead to widespread unemployment or a workers’ paradise of four-day week.

These wildly different visions suggest that assessments of the implications of AI are based on something less than a deep understanding of the technology, its potential and the history of humanity in interacting with new stuff. In the immediate term, the greatest threat posed by AI is the Dunning-Kruger effect.

This cognitive bias, described and named by psychologists David Dunning and Justin Kruger around the turn of the century, observes that people with limited competence in a particular domain are prone to overestimating their own understanding and abilities. It proposes that the reason for this is that they’re unable to appreciate the extent of their own ignorance – they’re not smart enough or skilled enough to recognise what good looks like. As Dunning put it, “not only does their incomplete and misguided knowledge lead them to make mistakes, but those exact same deficits also prevent them from recognising when they are making mistakes and other people are choosing more wisely”.

AI has layers and layers of Dunning-Kruger traps built in. The first is that the machine itself suffers from a mechanical type of cognitive bias. Large language models – the type of generative AI that is increasingly used by individuals at home and at work (we’re not talking about models designed for a specific scientific purpose) – are especially slick predictive text models. They scrape the web for the most likely next word in a sequence and then row them up in response to a query.

If there’s a lot of biased or incorrect information on a topic, this significantly colours the results. If there’s not enough information (and the machine has not been carefully instructed), then AI extrapolates – that is, it just makes shit up. If it detects that its user wants an answer that reflects their own views, it’ll filter its inputs to deliver just that. And then it presents what it has created with supreme confidence. It doesn’t know that it doesn’t know. If generative AI were a person, it would be psychology’s perfect case study of the Dunning-Kruger effect.

But we’re not here to beat up on machines. The robot is just a robot; the special dumb comes from its master. AI delivers a very convincing answer based on generalist information available; it’s the human Dunning-Kruger sufferer who slips into the trap of thinking the machine answer makes him look smart.

This is where the Dunning-Kruger effect will meet AI and become an economic force. The user who doesn’t know enough about a subject to recognise the deficits in the AI answers passes the low-grade information up the chain to a client or superior who also lacks the knowledge and expertise to question the product. A cretinous ripple expands undetected into every corner of an organisation and leaks out from there into everyday life. The AI is fed its own manure and becomes worse. Experts refer to the process as model collapse.

There will be job losses, because when incompetents rely on AI to do their work for them, eventually the clients or superiors they’re serving will cut out the middle-moron and go straight to the machine. Companies are cutting roles that can be convincingly emulated by AI because humans have not been value-adding to them. The question is just whether managers are themselves competent enough to recognise which roles these are and restructure their processes and workforce to provide value-add before their output is compromised.

To date, it has been so-called low-skilled jobs that have been most at threat from automation. But AI is changing the very nature of the skills that businesses require. A decade ago, workers who lost their jobs to increasing automation were told to “learn to code”. Now, coding itself is being replaced by AI. “Learn to care” is the mantra of this wave of social change.

Care isn’t just a gentle touch in health or aged care. It comes from emotional insight. A call-centre worker with no emotional intelligence can be classed as unskilled. There’s no question that a machine can answer the phone, direct queries and perform simple information sharing functions such as reading out your bank balance. But when the query is more complex or emotionally loaded, AI struggles. EQ, the emotional version of IQ, is a skill that can make an enormous difference in customer satisfaction and retention.

A more highly skilled job that I’ve recently seen performed by a human and a machine is quantitative research. A good machine model can do more interviews more quickly than a human interviewer, and the depth is much of a muchness. But a skilled interviewer with a thorough understanding of the objectives and a higher emotional attunement to the way people skirt around big topics could achieve greater depth and uncover richer insights. That requires both human IQ and EQ, which the machine doesn’t have. A human with these qualities is still needed to tune the AI to deliver its best outputs.

Which is why the idea of a four-day week based on AI efficiency is as utopian as the fear of massive job losses is catastrophist. The Dunning-Kruger effect, turbocharged by generative tools, will ruthlessly expose enterprises that mistake algorithmic speed for depth. Jobs and companies built on AI’s cold efficiency and unfounded self-confidence will soon be exposed.

The roundtable exposed a discussion on AI still stuck on threats and oblivious to skills. In the end, the danger isn’t that AI will outsmart us, it’s that humans will be too dumb to use it well.

Parnell Palme McGuinness is managing director at campaigns firm Agenda C. She has done work for the Liberal Party and the German Greens.

At our top university, AI cheating is out of control!

Robert A*, The Australian 29 August 2025

I’ve been a frontline teaching academic at the University of Melbourne for nearly 15 years. I’ve taught close to 2000 students and marked countless assessments.

While the job can be demanding, teaching has been a rewarding career. But a spectre is haunting our classrooms; the spectre of artificial intelligence.

Back in the day, contract cheating – where a student paid a third party to complete their assignment – was the biggest challenge to academic integrity. Nowadays, contract cheaters are out of work. Students are turning to AI to write their essays and it has become the new norm, even when its use has been restricted or prohibited.

What is the value of the university in the age of AI? Ideally, university should be a place where people are not taught what to think but how to think. It should be a place where students wrestle with big ideas, learn how to reason and rigorously test evidence. On graduation they should be contributing to and enhancing society.

Instead, AI chatbots, not Marxist professors, have taken hold of universities. AI is not an impartial arbiter of knowledge. ChatGPT is likelier to reinforce rather than challenge liberal bias; Grok’s Freudian slips reveal a model riddled with anti-Semitism; DeepSeek is a loyal rank-and-file member, toeing the Chinese Communist Party line and avoiding questions about its human rights record. When the machine essay-writing mill is pumping out essays, AI is the seductive force teaching students what to think.

While we know AI cheating is happening, we don’t know how bad it is and we have no concrete way of finding out. Our first line of defence, AI detection software, has lost the arms race and no longer is a deterrent. Recently, I asked ChatGPT to write an essay based on an upcoming assessment brief and uploaded it to Turnitin, our detection tool. It returned a 0 per cent AI score. This is hardly surprising because we already knew the tool wasn’t working as students have been gaming the system.

Prosecuting a case of academic misconduct is becoming increasingly difficult. Many cases are dismissed at the first stage because the AI detector returns a low score that doesn’t satisfy the threshold set by management. The logic seems to be that we should go for the worst offenders and deal with the rest another way. Even with this approach, each semester the academic integrity team is investigating a record-breaking number of cases.

To deal with the inundation of AI cheating, the University of Melbourne introduced a new process for “lower-risk” academic integrity issues. Lecturers were given discretionary powers to determine “poor academic practice”. Under this policy, essays that look as if they were written by AI but scored 0 per cent could be subject to grade revision. Problem solved, right? Not even close.

Tutors are our second line of defence. They are largely responsible for classroom teaching, mark assessments and flag suspicious papers. But a recent in-house survey found about half of tutors were “slightly” or “not at all” confident in identifying a paper written by AI. Others were only “marginally confident”. This is hardly their fault. They lack experience and, without proper training or detection tools, the university is demanding a lot from them.

Lecturers are the final line of defence. No offence to my colleagues, but we are not exactly a technologically literate bunch. Some of us know about AI only because of what we read in the paper or what our kids tell us about it.

We have a big problem on our hands, the “unknown-unknown” dilemma. We have an academic workforce that doesn’t know what it doesn’t know. Our defences are down and AI cheaters are walking through the gates on their way to earn degrees.

Soon we will see new cohorts of doctors, lawyers, engineers, teachers and policymakers graduating. When AI can ace assessments, employers and taxpayers have every right to question who was actually certified: the student or the machine? AI can do many things but it should have no place in the final evaluation of students.

A wicked problem surely requires sensible solution. If only. Federal Education Minister Jason Clare has acknowledged the AI challenge but passed the buck to the sector to figure it out. With approval from the regulator, many Australian universities have pivoted from banning to integrating AI.

The University of Melbourne is moving towards a model where at least 50 per cent of marks in a subject will have to come from assessments done in a secure way (such as supervised exams). The other 50 per cent will be open season for AI abuse.

All subjects will have to be compliant with this model by 2028.

Australian universities have surrendered to the chatbots and effectively are permitting widespread contract cheating by another name. This seriously risks devaluing the purpose of a university degree. It jeopardises the reputation of Australian universities, our fourth largest export industry.

There is real danger that universities soon will become expensive credential factories for chatbots, run by other chatbots.

There are many of us in the sector who object to this trend. Not all students are sold on the hype either; many reject the irresponsible use of AI and don’t want to see the critical skills taught at university cheapened by chatbots. Students are rightly asking: if they wanted AI to think for them, why are they attending university? Yet policymakers are out of touch with these stakeholders, the people living through this technological change.

What is to be done? The challenge of AI is not a uniquely Australian problem but it may require a uniquely Australian solution. First, universities should urgently abandon the integrated approach and redesign degrees that are genuinely AI-free. This may mean 100 per cent of marks are based on paper exams, debate, oral defences or tutorial activities.

The essay, the staple of higher education for centuries, will have to return to the classroom or perish. Australian universities can then proudly advertise themselves as AI-free and encourage international and domestic talent to study here.

Second, as AI rips through the high school system, the tertiary sector should implement verifiable admission exams. We must ensure that those entering university have the skills required to undertake it.

Third, there must be priority investment in staff training and professional development to equip teachers for these pedagogical challenges.

Finally, Clare needs to show some leadership and adopt a national, enforceable standard. Techo-capitalism is leading us away from the ideal of the university as a place for free thinking. If independent scholarly inquiry at university falls, our human society will be the biggest loser.

Robert A* is an academic at the University of Melbourne and has written under a pseudonym.

What hope for us if we stop thinking

Jacob Howland, The Australian, via Unherd, September 5 2025

In the faculty reading room of a university library where I spent many happy hours, two lines from Emily Dickinson were chiselled into the fireplace’s stone breastwork:

There is no Frigate like a Book
To take us Lands away.

That “Lands away” evokes open horizons of intellectual adventure and discovery – the idea of higher education that thrilled my teenaged self, and that I still associate with the musty smell of library bookstacks. The college I graduated from in 1981 promised to help us learn to read deeply, write clearly, think logically, and sort signal from noise in multiple languages of understanding. We would be equipped, not just for specialised employment, but for the lifelong task of trying to see things whole – to form, in the words of John Henry Newman, an “instinctive just estimate of things as they pass before us”.

Colleges and universities still make similar promises, but they mostly ring hollow. Since the 1980s, multiple factors – skyrocketing tuition and economic uncertainty, the precipitous decline of reading, the widespread collapse of academic standards, and the ideological radicalisation of course syllabi – have drastically shrunk the horizons of teaching and learning on campus.

More recently, three mostly self-inflicted storms have slammed higher education, revealing systemic rot. Unless universities can right their listing and leaking ships, future generations will graduate with little awareness of the richness and breadth of human experience, and little knowledge of where we’ve been and where we’re going. And that will be a terrible loss for all of us.

Covid – the first great storm, in 2020 – was a disaster for education, and a reality check for schools at every level. Primary and secondary students lost months or years of learning. School districts abandoned pre-existing academic standards, and parents who (thanks to Zoom) were able to observe their children’s classes were often appalled by what they saw and heard. College students who were compelled to attend “virtual” courses were similarly shortchanged. Universities signalled that money mattered more than mission when they continued to charge full tuition for classes where many students were present only as muted black squares.

Deprived of the social experience and amenities of life on campus, many undergraduates and prospective students decided that a university education wasn’t worth the cost.

Three years later, in 2023, the October 7 pogrom revealed that activist faculty and administrators had corrupted the core mission of higher education: to pursue truth and extend and transmit knowledge. Americans were alarmed to see mobs of students, radicalised by “critical theories” of oppression and victimisation, harassing and sometimes violently intimidating Jewish classmates. They were stunned when the presidents of Ivy League universities saw no real problem there. And they were dismayed to realise that much of what passes for higher education, especially at elite universities, is actually indoctrination in cultural Marxism.

The pandemic and the aftermath of October 7 have undeniably contributed to plummeting public trust in universities. But the third and biggest storm of crisis, precipitated by Generative-AI chatbots, threatens to sink higher education altogether. And this time, it is the students who are the problem – if only because we never managed to teach them that committing oneself to the process of learning is no less important than getting a marketable degree.

OpenAI’s ChatGPT reached a million users just six days after it launched in 2022. Two months later, a survey of 1000 college students found that 90 per cent “had used the chatbot to help with homework assignments”. Students’ use of chatbots is undoubtedly more widespread today, because the technology is addictive. As a professor wrote recently in The New Yorker: “Almost all the students I interviewed in the past few months described the same trajectory: from using AI to assist with organising their thoughts to off-loading their thinking altogether.”

At elite universities, community colleges, and everything in between, students are using AI to write their applications for admission, take notes in class, summarise required readings, compose essays, analyse data, and generate computer code, among other things – in short, to do the bulk of their assigned schoolwork.

They report that using AI allows them to produce research papers and interpretive essays in as little as half an hour and earn high grades for work they’ve neither written nor, in many cases, even read. A first-year student seems to speak for entire cohorts of undergraduates when she admits that “we rely on it, (and) we can’t really imagine being without it”.

Yet not all students think this is a good thing. An article in The Chronicle of Higher Education quotes multiple undergraduates who are hooked on the technology, and are distressed at being unable to kick the habit – because, as one confesses, “I know I am learning NOTHING”.

That last claim is only slightly overstated. Students who depend on AI to do their coursework learn how to engineer prompts, divide up tasks, and outsource them to machines. That’s not nothing, but it’s a skill that involves no internal assimilation of intellectual content – no actual learning – beyond managing AI projects involving data acquisition, analysis, and synthesis. AI dependency furthermore contributes to cognitive impairment, accelerating a decades-long decline in IQ. And it cheats everyone: students who’ve prepared for class but find themselves among unresponsive classmates, and professors who spend hours drafting lectures that fall on deaf ears and grading essays written by machines. It cheats the cheaters themselves, who are paying good money for nothing but an unearned credential so that they will have time for other things – including, as one student admitted, wasting so many hours on TikTok that her eyes hurt. It cheats employers who hire graduates in good faith, only to discover their incompetence. Last but not least, it cheats society, where informed citizens and competent leaders are in notably short supply.

To make matters worse, the illicit use of chatbots is difficult to detect and even harder to prove. Companies and TikTok influencers offer products and coaching that help students camouflage their use of AI. Students have learned how to avoid “Trojan horse” traps in assignments, design prompts that won’t make them look too smart, and launder their essays through multiple bot-generated iterations. AI-powered software has furthermore proved to be highly unreliable at identifying instances of AI-generated work. (This is unsurprising: why would providers like OpenAI, which makes ChatGPT Plus free during final exams, want to imperil huge student demand for its product?) And in the long run, market forces will always keep students one step ahead of their professors.

Case in point: a student who was expelled from Columbia University for dishonesty has raised more than $US5m to design a wearable device that “will enable you to cheat on pretty much anything” in real time – including in-class essays, which would otherwise create an AI-free testing environment.

So far, universities have no good answers to the existential questions posed by AI. What is needed from academic leaders is a full-throated explanation of what universities are, why they exist, and what it means to get a real education. Instead, presidents, provosts, and deans have remained silent – perhaps, one fears, because they are no longer capable of delivering such an explanation. They’ve let faculty establish their own AI-use policies, which vary widely and are, in any case, difficult to enforce consistently.

Professors, too, are using chatbots to formulate assignments, grade papers and no doubt write lectures. I don’t entirely blame them: the technology is an efficient solution to the drudgery of teaching students whose investment in their educations is merely financial and transactional. But in their courses, as on much of the internet, AI is largely talking to AI.

Will universities survive if they become little more than expensive credential mills? The most elite ones will, coasting on past glory and present status. Others will put a smiley face on the corruption of higher education. They will embrace AI, supposing that essentially managerial skills will suffice when superintelligent machines learn how to do “most of the real thinking”, as a well-known economist and an AI researcher predict they eventually will. Yet in everything from diplomacy to medicine, real thinking – thinking at the highest levels, where strategies are devised and executed – requires practical wisdom: an adequate understanding, not just of the range of digital tools available to us and how to operate them, but of the ends these tools ought to serve.

This is to say nothing of the fact that the AI tools that are by orders of magnitude most widely used – Large Language Models, trained on the polluted content of the worldwide web – are deceptive, prone to hallucinations, and politically biased: qualities manifestly unsuited to the pursuit of truth.

But, you may ask, are reading and writing still relevant in the digital age? Does it really matter that, in a study conducted a decade ago, 58 per cent of English majors at two academically mid-level universities in Kansas “understood so little of the introduction to (Charles Dickens’) Bleak House” – a book that was originally serialised in a magazine, and reached a wide audience across all social classes – “that they would not be able to read the novel on their own”? Or that these same students had so little self-knowledge that they “also believed they would have no problem reading the rest of the 900-page novel”? Yes, it does matter – if we hope to preserve our humanity. This is not because Dickens is particularly important, but because of what these findings say about students’ poor command of language, the basic medium of human understanding. What would these English majors make of Shakespeare? Would political science majors fare better with Tocqueville or the Federalist Papers? Or philosophy majors with Aristotle? Don’t bet on it.

Writing in the 1960s, the philosopher Emmanuel Levinas seems to have foreseen our age of shortcuts, where machine-generated bullet points substitute for active engagement with challenging material. Levinas understood that the precious inheritance of culture, the wellspring of all new growths and great ideas, is indispensable in navigating the trackless future. “A true culture,” he observed, “cannot be summarised, for it resides in the very effort that cultivates it.”

That effort begins with authentic cultural appropriation: the slow, sometimes laborious, but ultimately joyful internalisation of the best that has been thought and said. It is this process of education that gives us ethical, intellectual, and spiritual compasses, tells us where to look for answers, and allows even relative amateurs to seek them “lands away”. And without this ongoing renewal of intellectual culture, technological plans and political programs must inevitably suffer from what Socrates regarded as the worst vice of all: ignorance.

Education at its best develops the virtues or excellences of thought and action, taste, feeling, and judgment, that fit one for all seasons, occasions, tasks and responsibilities of life.

And that moral, intellectual, and spiritual attunement, not just to physical reality, nor to the largely unforeseeable contingencies of time and history, but to eternal or transcendent truths, is good in itself as well as for its consequences. Universities used to regard these as truths so self-evident that they hardly needed saying. But they need saying now. In this hour of need, let us hope that academic leaders are still up to the task.

Jacob Howland is the former provost, senior vice-president for academic affairs, and dean of intellectual foundations at the University of Austin, Texas. An earlier version of this article appeared in UnHerd

	A forgotten Anzac st… on The fall of the Ottoman Empire…
	A forgotten Anzac st… on Ottoman Redux – an alter…
	The most nihilistic… on The calculus of carnage…
	Answering the call… on The Spirit of ’45
	Answering the call… on “High above the dawn is waitin…

	A forgotten Anzac st… on The fall of the Ottoman Empire…
	A forgotten Anzac st… on Ottoman Redux – an alter…
	The most nihilistic… on The calculus of carnage…
	Answering the call… on The Spirit of ’45
	Answering the call… on “High above the dawn is waitin…