ClaimsPeople

Eliezer Yudkowsky

Eliezer Yudkowsky founded the Machine Intelligence Research Institute (MIRI) and LessWrong, co-authored the best-selling book 'If Anyone Builds It, Everyone Dies' (Little, Brown, 2025), and was named to the TIME100 AI 2023 list.

2,016 claims collected, 236 researched, 79 resolved. Report of 4 November 2026, method 0.1.0+c876030c.

Scores by kind of claim

Each kind of claim is scored on its own, out of 100: the share that held up, with the range it likely falls in. Fewer resolved claims give a wider range.

  • Factual claims

    Statements about the present or the past, checked against the record: did they hold up?

    76 70 82

    High confidence, 71 factual claims resolved. From 16 documents, 2007 to 2026; 18 documents sampled from 23 candidates found.

    Not scored: 50 unresolvable, 8 checkable only against their own records.

  • Predictions

    Statements about events outside the person's control, checked once they fell due: did they come true?

    60 42 78

    Low confidence, 8 predictions resolved. From 4 documents, 2008 to 2024; 18 documents sampled from 23 candidates found.

    Not scored: 97 unresolvable. 1 more fall due later.

    Does not yet allow for how likely each prediction was when made.

All types combined: 74 (likely 68 to 80, high confidence), from 79 claims: 71 factual claims, 8 predictions. It mixes kinds of claim in different proportions for different people, so compare people kind by kind.

Eliezer Yudkowsky's claims

1,592 claims · page 12 of 16

1,592 claims, sorted by newest said. Choose a claim to read it in full.
VerdictKindSaidClaimTopic
Not checkable Not checkable 28 Feb 2018 I think they’re wrong Not checkable · 28 Feb 2018
Not checkable Not checkable 28 Feb 2018 it seems to me that it is perfectly coherent to imagine an AI that is better at everything (or almost everything) than we are Not checkable · 28 Feb 2018
Not checkable Not checkable 30 Jan 2013 Are you sure the same way of thinking wouldn’t prevent you from working on any important problem? Not checkable · 30 Jan 2013
Not checkable Not checkable 30 Jan 2013 They didn’t work like that. Not checkable · 30 Jan 2013
Not checkable Not checkable 30 Jan 2013 If you’re still like, “No, no, we must think more meta” after a year, then I don’t believe you’re the sort of person who will ever act. Not checkable · 30 Jan 2013
Not checkable Not checkable 30 Jan 2013 When people constantly say “maybe we should do some other thing,” I would say, “Come to an interim decision, start acting on the interim… Not checkable · 30 Jan 2013
Not checkable Not checkable 30 Jan 2013 If he then came up with some particular intervention which he thought was higher priority, I’d ask about the specific case. Not checkable · 30 Jan 2013
Not checkable Not checkable 30 Jan 2013 Work on whatever your current priority is, after an hour of meta reasoning but not a year of meta reasoning. Not checkable · 30 Jan 2013
Not checkable Not checkable 30 Jan 2013 Real computers don’t work very much like the formalism, but Turing’s work was useful anyway. Not checkable · 30 Jan 2013
Not checkable Not checkable 30 Jan 2013 Nick Bostrom isn’t making this mistake, either. Not checkable · 30 Jan 2013
Not checkable Not checkable 30 Jan 2013 No, this issue of trying to have an AI write a similar AI seems like a fairly fundamental one, and the Löb Problem blocks it. Not checkable · 30 Jan 2013
Not checkable Not checkable 30 Jan 2013 But if you’re the person who always tries to go meta and only thinks meta because there might be some better thing, you’re not ever going… Not checkable · 30 Jan 2013
Not checkable Not checkable 30 Jan 2013 I’d start by having them read a description of a particular technical problem we’re working on, for example the “Löb Problem.” Not checkable · 30 Jan 2013
Not checkable Not checkable 30 Jan 2013 The fact that we can’t figure out how to do these things — even given infinite computing power — is alarming. Not checkable · 30 Jan 2013
Not checkable Not checkable 30 Jan 2013 Are you sure you wouldn’t be going back in time and telling Alan Turing to not invent Turing machines because who knows whether computers… Not checkable · 30 Jan 2013
Not checkable Not checkable 30 Jan 2013 I don’t have much objection to that. Not checkable · 30 Jan 2013
Not checkable Not checkable 2008 I would be pleasantly surprised to be proven wrong about this. Not checkable · 2008
Not checkable Not checkable 2008 No system is secure that searches for ways to defeat its own security. Not checkable · 2008
Not checkable Not checkable 2008 Wason's 2-4-6 task is a "cold" form of confirmation bias; people seek confirming but not falsifying evidence. Not checkable · 2008
Not checkable Not checkable 2008 it would be nice if we knew how to build a nice AI. Not checkable · 2008
Not checkable Not checkable 2008 This statement now seems to me like complete gibberish. Not checkable · 2008
Not checkable Not checkable 2008 This does not imply the AI has the motive to change its own motives. Not checkable · 2008
Not checkable Not checkable 2008 I have given you another opportunity to fail each time you face the challenge of changing your mind. Not checkable · 2008
Not checkable Not checkable 2008 Such competence is not historically typical of human institutions, no matter how hard they try. Not checkable · 2008
Not checkable Not checkable 2008 However, ranking (8) as more probable than (6) violates the conjunction rule of probability theory which states that p(A & B) ≤ p(A). Not checkable · 2008
Not checkable Not checkable 2008 By far the greatest danger of Artificial Intelligence is that people conclude too early that they understand it. Not checkable · 2008
Not checkable Not checkable 2008 Thus, all else being equal, I would greatly prefer that Friendly AI precede nanotechnology in the ordering of technological developments. Not checkable · 2008
Not checkable Not checkable 2008 Moore’s Law of Mad Science: Every eighteen months, the minimum IQ necessary to destroy the world drops by one point. Not checkable · 2008
Not checkable Not checkable 2008 I should not have had to stumble across that reference by accident. Not checkable · 2008
Not checkable Not checkable 2008 The first AI must be Friendly. Not checkable · 2008
Not checkable Not checkable 2008 If an AI will hurt you given magic, the Friendliness architecture is wrong. Not checkable · 2008
Not checkable Not checkable 2008 Lacking the space for exposition, I can only plead with the reader to consult the primary literature. Not checkable · 2008
Not checkable Not checkable 2008 We should recognize this as a literary criticism, not a scientific one; it is about good or bad novels, not good or bad hypotheses. Not checkable · 2008
Not checkable Not checkable 2008 All else being equal, not many people would prefer to destroy the world. Not checkable · 2008
Not checkable Not checkable 2008 I am skeptical that a scholar of heuristics and biases, unable to read physics equations, could check the work of physicists who knew… Not checkable · 2008
Not checkable Not checkable 2008 Artificial Intelligence is not settled science; it belongs to the frontier, not to the textbook. Not checkable · 2008
Not checkable Not checkable 2008 There is no guarantee whatsoever that, just because we can’t manage a risk, the risk will obligingly go away. Not checkable · 2008
Not checkable Not checkable 2008 If we postulate that future minds exhibit the same mixture of foolishness and wisdom, the same mixture of heroism and selfishness, as the… Not checkable · 2008
Not checkable Not checkable 2008 We might survive for another decade, even another century, but not another million years. Not checkable · 2008
Not checkable Not checkable 2008 But if combinatorics could not correctly predict that a lottery ticket has a 10-8 chance of winning, ticket sellers would go broke. Not checkable · 2008
Not checkable Not checkable 2008 It would be, not physically impossible, but cognitively impossible. Not checkable · 2008
Not checkable Not checkable 2008 The same thing could as easily happen to the whole human species, if the human species runs into an unfair challenge. Not checkable · 2008
Not checkable Not checkable 2008 It is a risky intellectual endeavor to predict specifically how a benevolent AI would help humanity, or an unfriendly AI harm it. Not checkable · 2008
Not checkable Not checkable 2008 Philosophical failure is trying to build the wrong thing, so that even if you succeeded you would still fail to help anyone or benefit… Not checkable · 2008
Not checkable Not checkable 2008 minds do not blindly wander into attractors, they have motives. Not checkable · 2008
Not checkable Not checkable 2008 If you want to know why others aren't responding to an emergency, before you respond yourself, you may have just answered your own question. Not checkable · 2008
Not checkable Not checkable 2008 Friendly AI, as I have proposed it, requires repeated cycles of recursive self-improvement that precisely preserve a stable optimization… Not checkable · 2008
Not checkable Not checkable 2008 If the AI wants to modify itself to be no longer Friendly, then Friendliness has already failed, at the point when the AI forms that… Not checkable · 2008
Not checkable Not checkable 2008 I would not knowingly swallow a pill that made me enjoy committing murder, because currently I prefer that my fellow humans not die. Not checkable · 2008
Not checkable Not checkable 2008 Hominids have survived this long only because, for the last million years, there were no arsenals of hydrogen bombs, no spaceships to steer… Not checkable · 2008
Not checkable Not checkable 2008 The catastrophic scenario which stems from underestimating the power of intelligence is that someone builds a button, and doesn’t care… Not checkable · 2008
Not checkable Not checkable 2008 I don't know how to solve this problem. Not checkable · 2008
Not checkable Not checkable 2008 You trust that the authors didn't unconsciously look just a little bit harder for mistakes in equations that seemed to be leaning the wrong… Not checkable · 2008
Not checkable Not checkable 2008 The bystander effect is not about individual selfishness, or insensitivity to the suffering of others. Not checkable · 2008
Not checkable Not checkable 2008 It's harder to abuse heuristics and biases than psychoanalysis. Not checkable · 2008
Not checkable Not checkable 2008 Ordinarily, local strategies are most plausible. Not checkable · 2008
Not checkable Not checkable 2008 In practice it often takes a deep technical understanding to figure out what you want. Not checkable · 2008
Not checkable Not checkable 2008 Evolutionary biology offers both mathematics and case studies to help hammer out anthropomorphic bias. Not checkable · 2008
Not checkable Not checkable 2008 I can predict the outcome of a process, without being able to predict any of the intermediate steps in the process. Not checkable · 2008
Not checkable Not checkable 2008 If I am selective about which arguments I inspect for errors, or even how hard I inspect for errors, then every new rule of rationality I… Not checkable · 2008
Not checkable Not checkable 2008 A fast, nice intelligence wielding molecular nanotechnology is power on the order of getting rid of disease, not getting rid of cancer. Not checkable · 2008
Not checkable Not checkable 2008 If so, then by making you a more sophisticated arguer - by teaching you another bias of which to accuse people - I have actually harmed… Not checkable · 2008
Not checkable Not checkable 2008 Reality throws at you one challenge after another, and when you run into a challenge you can’t handle, you suffer the consequences. Not checkable · 2008
Not checkable Not checkable 2008 The one whom you must watch above all is yourself. Not checkable · 2008
Not checkable Not checkable 2008 As soon as a milestone is actually achieved, it ceases to be “AI.” This can only encourage procrastination. Not checkable · 2008
Not checkable Not checkable 2008 If we want people who can make progress on Friendly AI, then they have to start training themselves, full-time, years before they are… Not checkable · 2008
Not checkable Not checkable 2008 A good book for quickly picking up a sense of the field. Not checkable · 2008
Not checkable Not checkable 2008 You may not drive; you may not fly; you may not walk across the street even after looking both ways, for it is still too great a risk. Not checkable · 2008
Not checkable Not checkable 2008 It seems like an unfair challenge. Not checkable · 2008
Not checkable Not checkable 2008 Rather, the representativeness heuristic is what produces the intuitive sense that sequence 2 "seems more likely" than sequence 1. Not checkable · 2008
Not checkable Not checkable 2008 No more than Albert Szent-Györgyi could multiply the suffering of one human by a hundred million can I truly understand the value of clear… Not checkable · 2008
Not checkable Not checkable 2008 The folly of programming an AI to implement communism, or any other political system, is that you’re programming means instead of ends. Not checkable · 2008
Not checkable Not checkable 2008 With luck, future historians will look back and describe the present world as an awkward in-between stage of adolescence, when humankind… Not checkable · 2008
Not checkable Not checkable 2008 Now it seems to me that an AI capable of language, abstract thought, creativity, environmental interaction, originality, prediction… Not checkable · 2008
Not checkable Not checkable 2008 Each and every absence of knowledge dates back to the dawn of human curiosity; and the hole lasts through the ages, seemingly eternal… Not checkable · 2008
Not checkable Not checkable 2008 I strongly urge my readers not to start thinking up reasons why a fully generic optimization process would be friendly. Not checkable · 2008
Not checkable Not checkable 2008 Because human engineers deliberately use designs that they can understand. Not checkable · 2008
Not checkable Not checkable 2008 the ability to self-improve does not imply the choice to do so. Not checkable · 2008
Not checkable Not checkable 2008 We evaluate descriptions of events, not extensions of events. Not checkable · 2008
Not checkable Not checkable 2008 It is acceptable to fail at AI and at Friendly AI. It is acceptable to succeed at AI and at Friendly AI. Not checkable · 2008
Not checkable Not checkable 2008 But obviously it was not that improbable. Not checkable · 2008
Not checkable Not checkable 2008 It is disrespectful to human ingenuity to declare a challenge unsolvable without taking a close look and exercising creativity. Not checkable · 2008
Not checkable Not checkable 2008 Nature is, not cruel, but indifferent; a neutrality which often seems indistinguishable from outright hostility. Not checkable · 2008
Not checkable Not checkable 2008 Yet before we can pass out of that stage of adolescence, we must, as adolescents, confront an adult problem: the challenge of… Not checkable · 2008
Not checkable Not checkable 2008 Even so, I suspect that, pragmatically speaking, our alternatives boil down to becoming smarter or becoming extinct. Not checkable · 2008
Not checkable Not checkable 2008 I don’t know. I’m not that smart. Not checkable · 2008
Not checkable Not checkable 2008 But that's a technical question, not a matter of taste; no amount of psychologizing can tell you the exact slope of that curve. Not checkable · 2008
Not checkable Not checkable 2008 The point about underestimating the potential impact of Artificial Intelligence is symmetrical around potential good impacts and potential… Not checkable · 2008
Not checkable Not checkable 2008 A prospective risk going from 10,000,000 deaths to 100,000,000 deaths does not multiply by ten the strength of our determination to stop it. Not checkable · 2008
Not checkable Not checkable 2008 Halting or relinquishing an undesirable technology tends to require an impossible unanimous strategy. Not checkable · 2008
Not checkable Not checkable 2008 I call this mix of anchoring and availability the logical fallacy of generalization from fictional evidence. Not checkable · 2008
Not checkable Not checkable 2008 If you are well-calibrated, then on a test with one hundred such questions, around 2 questions will have answers that fall outside your 98%… Not checkable · 2008
Not checkable Not checkable 2008 All scientific ignorance is hallowed by ancientness. Not checkable · 2008
Not checkable Not checkable 2008 The moral may be that once you can guess what your answer will be - once you can assign a greater probability to your answering one way… Not checkable · 2008
Not checkable Not checkable 2008 Despite all dangers and temptations, it is better to know about psychological biases than to not know. Not checkable · 2008
Not checkable Not checkable 2008 It is important to understand that the authors of huge catastrophes need not be evil, nor even unusually stupid. Not checkable · 2008
Not checkable Not checkable 2008 So if we find that we cannot make progress on Friendly AI, then we need to figure out how to exit that regime as fast as possible! Not checkable · 2008
Not checkable Not checkable 2008 The calibration research is dangerous knowledge - so tempting to apply selectively. Not checkable · 2008
Not checkable Not checkable 2008 Pluralistic ignorance can explain, and individual selfishness cannot explain, subjects failing to react to a room filling up with smoke. Not checkable · 2008
Not checkable Not checkable 2008 Artificial Intelligence does not belong in the same graph that shows progress in medicine, manufacturing, and energy. Not checkable · 2008
Back to the list

Not checkable

“You may not drive; you may not fly; you may not walk across the street even after looking both ways, for it is still too great a risk.”

Eliezer Yudkowsky 2008 Artificial Intelligence as a Positive and Negative Factor in Global Risk (MIRI)

You may not drive; you may not fly; you may not walk across the street even after looking both ways, for it is still too great a risk.

Not checkable An opinion, value judgement or statement with nothing to check.

Cite this claim

Eliezer Yudkowsky, “You may not drive; you may not fly; you may not walk across the street even after looking both ways, for it is still too great a risk.” (said 2008). Verdict: not checkable. Reliability API, claim c_3169626cc9ee, method 0.1.0+c876030c. https://epistacklabs.com/claims/c_3169626cc9ee

Claims without a verdict

Is a verdict here wrong, or do you speak for Eliezer Yudkowsky? Reply on the claim's own page, with the form at its foot (how replies work). Verdicts are made automatically; how verdicts and scores are made.