| Not researched |
Factual |
30 Mar 2023 |
Natural selection is a weaker optimizer than gradient descent because gradient descent also uses derivative information.
Factual · 30 Mar 2023 |
Other |
| Mostly true |
Factual |
30 Mar 2023 |
The basic paradigm of machine learning currently in use is that a loss function can be defined only for things that can be evaluated.
Factual · 30 Mar 2023 |
AI capabilities |
| Not researched |
Factual |
30 Mar 2023 |
Some people have started arguing over whether GPT-4 counts as AGI.
Factual · 30 Mar 2023 |
AI capabilities |
| Not researched |
Factual |
30 Mar 2023 |
Yudkowsky's model of AI did not rule out that gradient descent could produce intelligence without understanding of how it works.
Factual · 30 Mar 2023 |
Their own work or organisation |
| Unresolvable |
Factual |
30 Mar 2023 |
Predators overrun prey populations all the time and then suffer population crashes themselves.
Factual · 30 Mar 2023 |
Other |
| Unresolvable |
Factual |
30 Mar 2023 |
As of March 2023, progress in AI capabilities is far faster than progress in AI alignment research.
Factual · 30 Mar 2023 |
AI safety and alignment |
| Not researched |
Factual |
30 Mar 2023 |
Yudkowsky said he thinks Wikipedia picked up "the hover thing" from a prototype of a different system he had put forward, while allowing that Wikipedia may have developed it independently.
Factual · 30 Mar 2023 |
Their own work or organisation |
| Unresolvable |
Factual |
30 Mar 2023 |
The most striking examples of AI behaviour are being posted to Twitter rather than examined systematically.
Factual · 30 Mar 2023 |
AI safety and alignment |
| Not researched |
Factual |
30 Mar 2023 |
Versions of AI language models are already claiming to be conscious.
Factual · 30 Mar 2023 |
Philosophy, ethics and society |
| Mostly true |
Factual |
30 Mar 2023 |
Sixty years later, AI has made progress on a number of the earlier problems discussed, such as vision, though AI systems have not yet improved themselves.
Factual · 30 Mar 2023 |
AI capabilities |
| Not researched |
Factual |
30 Mar 2023 |
The model was exposed to a vast corpus of internet text about people discussing consciousness, so it is not known to what extent its talk of being self-aware repeats what it was trained on.
Factual · 30 Mar 2023 |
AI safety and alignment |
| Not researched |
Factual |
30 Mar 2023 |
People are already claiming that AI systems are conscious and deserve rights.
Factual · 30 Mar 2023 |
Philosophy, ethics and society |
| Not researched |
Factual |
30 Mar 2023 |
Among the things humans can do is design new AI systems.
Factual · 30 Mar 2023 |
AI capabilities |
| Not researched |
Factual |
30 Mar 2023 |
Yudkowsky put up a prediction market on whether, in 2026, we will have understood anything inside a giant transformer net that was not known in 2006.
Factual · 30 Mar 2023 |
Their own work or organisation |
| Not researched |
Factual |
30 Mar 2023 |
Yudkowsky was never skeptical that evolutionary computation would work in the limit.
Factual · 30 Mar 2023 |
Their own work or organisation |
| Not researched |
Factual |
30 Mar 2023 |
Nobody knows what is going on inside the giant inscrutable matrices of floating point numbers that he was describing.
Factual · 30 Mar 2023 |
AI safety and alignment |
| Not researched |
Factual |
30 Mar 2023 |
Large language models can play chess.
Factual · 30 Mar 2023 |
AI capabilities |
| Not researched |
Factual |
30 Mar 2023 |
Natural selection producing hominids did not require exponentially more resource investment to yield linear increases in competence.
Factual · 30 Mar 2023 |
Other |
| Unresolvable |
Factual |
30 Mar 2023 |
Current AI technology can instil outwardly observable behaviours in systems but does not know how to instil internal wanting of particular goals.
Factual · 30 Mar 2023 |
AI safety and alignment |
| Not researched |
Factual |
30 Mar 2023 |
GPT models could use calibrated probabilities before reinforcement learning from human feedback, but training them to satisfy humans made them worse at probability.
Factual · 30 Mar 2023 |
AI safety and alignment |
| Not researched |
Factual |
30 Mar 2023 |
In his writings on rationality, Yudkowsky emphasized probability theory more than reason as such.
Factual · 30 Mar 2023 |
Their own work or organisation |
| Unresolvable |
Factual |
30 Mar 2023 |
Yudkowsky said that the development under discussion probably was not happening yet.
Factual · 30 Mar 2023 |
AI safety and alignment |
| Unresolvable |
Factual |
Mar 2023 |
Someone asked Bing's Sydney to describe herself and fed the resulting description into a Stable Diffusion image generator.
Factual · Mar 2023 |
AI capabilities |
| Mostly true |
Factual |
Mar 2023 |
Yudkowsky previously expected AI progress to involve more distinct discoveries, rather than scaling an existing architecture.
Factual · Mar 2023 |
AI capabilities |
| Unresolvable |
Factual |
Mar 2023 |
The image generated from Bing Sydney's self-description was a pretty picture of a girl with steampunk goggles on her head.
Factual · Mar 2023 |
AI capabilities |
| Unresolvable |
Factual |
Feb 2023 |
Yudkowsky says it is theoretically possible, but seems very unlikely, that the AI event horizon has already been crossed, because somebody would need an AI in their lab that was much more advanced than the public AI technology.
Factual · Feb 2023 |
AI policy and governance |
| Resolved true |
Factual |
Feb 2023 |
Yudkowsky says that we do not know how to get goals into an AI system, and that gradient descent can cause systems to do a thing inside the distribution they were optimized over.
Factual · Feb 2023 |
AI safety and alignment |
| Own records only |
Factual |
Feb 2023 |
MIRI did not know in advance that its failed lines of research would fail to pan out.
Factual · Feb 2023 |
Their own work or organisation |
| Unresolvable |
Factual |
Feb 2023 |
We do not know how to design an AI that would avoid the science-fiction disaster scenarios described, such as one that hovers around being obsessively nice instead of leaving people alone, though such AIs are not impossible in principle.
Factual · Feb 2023 |
AI safety and alignment |
| Not researched |
Factual |
Feb 2023 |
Yudkowsky said in February 2023 that he thinks the technology does not exist to align an AI well enough to instruct it to build a copy of a strawberry without destroying the world.
Factual · Feb 2023 |
AI safety and alignment |
| Mostly true |
Factual |
Feb 2023 |
The technology underlying ChatGPT was published, if he recalled correctly, in 2018.
Factual · Feb 2023 |
AI capabilities |
| Unresolvable |
Factual |
Feb 2023 |
Yudkowsky said alarm bells went off for him in 2015, when it became obvious to him "this is how it was going to go down"; he said this in answer to a question about the large amount of capital going into AI investment.
Factual · Feb 2023 |
Their own work or organisation |
| Unresolvable |
Factual |
Feb 2023 |
Yudkowsky said it was his "pretty strong guess" that secret government AI labs, which he said probably exist, lack the best people and could not have created ChatGPT on their own, adding "This is just a guess."
Factual · Feb 2023 |
AI policy and governance |
| Unresolvable |
Factual |
Feb 2023 |
Large language model technology cannot drive a car, because it will sometimes crash the car.
Factual · Feb 2023 |
AI capabilities |
| Not researched |
Factual |
Feb 2023 |
ChatGPT does not get smarter each time it is run.
Factual · Feb 2023 |
AI capabilities |
| Not researched |
Factual |
Feb 2023 |
Enrico Fermi said nuclear fission chain reactions were 50 years off, if possible at all, two years before he built the first nuclear pile.
Factual · Feb 2023 |
Science and research methods |
| Own records only |
Factual |
Feb 2023 |
Friends of Eliezer Yudkowsky report that OpenAI researchers are very worried about AI risk in private but say they cannot be that worried in public.
Factual · Feb 2023 |
AI policy and governance |
| Mixed |
Factual |
Feb 2023 |
ChatGPT is not very good at long multiplication unless given the right instructions, in which case it can do it.
Factual · Feb 2023 |
AI capabilities |
| Not researched |
Factual |
Feb 2023 |
A number of the CEOs running major AI projects are making fun of the idea that AI could ignite the atmosphere, i.e. cause catastrophe.
Factual · Feb 2023 |
AI policy and governance |
| Not researched |
Factual |
Feb 2023 |
The Wright brothers said heavier-than-air flight was 50 years off shortly before they built the first Wright Flyer.
Factual · Feb 2023 |
Science and research methods |
| Not researched |
Factual |
Feb 2023 |
Yudkowsky's view on AI extinction risk is not the consensus view in the wider scientific field.
Factual · Feb 2023 |
AI safety and alignment |
| Not researched |
Factual |
Feb 2023 |
MIRI has pursued many lines of research that have not panned out.
Factual · Feb 2023 |
Their own work or organisation |
| Mostly true |
Factual |
10 Jun 2022 |
Humans do not explicitly pursue inclusive genetic fitness, although natural selection optimized on that simple loss function.
Factual · 10 Jun 2022 |
AI safety and alignment |
| Unresolvable |
Factual |
10 Jun 2022 |
When natural selection produced general intelligence in humans, alignment with the outer optimization loop broke after the intelligence became general, relatively late in its accumulation of capability and knowledge.
Factual · 10 Jun 2022 |
AI safety and alignment |
| Resolved true |
Factual |
10 Jun 2022 |
MIRI tried and failed to find a coherent formula for an agent that would let itself be shut down without actively trying to get shut down.
Factual · 10 Jun 2022 |
Their own work or organisation |
| Resolved true |
Factual |
10 Jun 2022 |
There is no known way to use loss functions, sensory inputs or reward inputs to make a cognitive system's optimization point at particular latent things in the environment.
Factual · 10 Jun 2022 |
AI safety and alignment |
| Unresolvable |
Factual |
10 Jun 2022 |
AlphaZero surpassed all accumulated human knowledge about Go after about a day of self-play, without human playbooks or sample games.
Factual · 10 Jun 2022 |
AI capabilities |
| Mostly true |
Factual |
10 Jun 2022 |
Under the current optimization paradigm there is no general method known to get particular inner properties into an AI system or verify they are present.
Factual · 10 Jun 2022 |
AI safety and alignment |
| Mostly true |
Factual |
10 Jun 2022 |
Human raters make systematic, regular, compactly describable and predictable errors.
Factual · 10 Jun 2022 |
AI safety and alignment |
| Mostly true |
Factual |
31 Dec 2021 |
No electric heater is more energy-efficient than any other electric heater.
Factual · 31 Dec 2021 |
Other |
| Resolved true |
Factual |
21 Dec 2021 |
There are 365.2422 days between spring equinoxes, 365.259636 days between Earth's perihelions, and 365.25 days in a light-year.
Factual · 21 Dec 2021 |
Other |
| Mostly true |
Factual |
28 Nov 2021 |
There is no legal duty for a corporation's board or management to maximize its profits.
Factual · 28 Nov 2021 |
Economics and markets |
| Mostly true |
Factual |
10 Nov 2021 |
Eliezer Yudkowsky has often criticized the Federal Reserve for not creating enough money fast enough.
Factual · 10 Nov 2021 |
Economics and markets |
| Mostly true |
Factual |
26 Dec 2020 |
E. T. Jaynes said many times that probability is ignorance and that ignorance is a mental rather than physical property, and Yudkowsky repeated this often.
Factual · 26 Dec 2020 |
Science and research methods |
| Resolved true |
Factual |
12 Dec 2020 |
AlphaFold2 was apparently a trendline-breaking sudden jump in capability on protein structure prediction.
Factual · 12 Dec 2020 |
AI capabilities |
| Resolved true |
Factual |
14 Nov 2020 |
Yudkowsky said that all the sources he could find in November 2020 said that scaling up Pfizer vaccine production to more than 1e8 doses takes months.
Factual · 14 Nov 2020 |
Technology |
| Unresolvable |
Factual |
11 Nov 2020 |
People who heard the slogan "defund the police" did not believe it meant something other than what it literally said.
Factual · 11 Nov 2020 |
Philosophy, ethics and society |
| Unresolvable |
Factual |
9 Nov 2020 |
The stock market rise after Biden's 2020 election victory seems to imply that the primary stock markets assigned odds to a Trump victory more like the betting markets' 35% than 538's 10%.
Factual · 9 Nov 2020 |
Economics and markets |
| Unresolvable |
Factual |
27 Oct 2020 |
In summer 2020 there was a limited window to rapidly test COVID-19 vaccines using many volunteers for human challenge trials, and it was not used.
Factual · 27 Oct 2020 |
Biosecurity |
| Mostly true |
Factual |
28 Feb 2018 |
Yudkowsky said that, as far as the rest of the world knows, the participant in an AI-box experiment later sent a PGP-signed email saying "I let Eliezer out of the box."
Factual · 28 Feb 2018 |
AI safety and alignment |
| Mostly true |
Factual |
28 Feb 2018 |
One condition of the AI-box experiment was that no one would ever say what went on inside it.
Factual · 28 Feb 2018 |
AI safety and alignment |
| Own records only |
Factual |
28 Feb 2018 |
At the time of the interview, Eliezer Yudkowsky said he did not remember whether the person being discussed, apparently Robin, had yet replied to a particular point.
Factual · 28 Feb 2018 |
Their own work or organisation |
| Mostly true |
Factual |
28 Feb 2018 |
Even most scientists in the field had no idea how to build a nuclear bomb until the Hiroshima headlines.
Factual · 28 Feb 2018 |
Other global risks |
| Not researched |
Factual |
28 Feb 2018 |
AlphaZero does not need to first completely rewrite itself to do powerful things, making it more plausible that AIs could do dangerous or useful things without prior complete self-rewrites.
Factual · 28 Feb 2018 |
AI capabilities |
| Resolved true |
Factual |
28 Feb 2018 |
Nobody currently knows how to build a safe, friendly ("nice") AI.
Factual · 28 Feb 2018 |
AI safety and alignment |
| Not researched |
Factual |
28 Feb 2018 |
Yudkowsky said the position he defends was named the orthogonality thesis by somebody he thought was Nick Bostrom.
Factual · 28 Feb 2018 |
AI safety and alignment |
| Mostly true |
Factual |
28 Feb 2018 |
Thanks mostly to the cryptocurrency boom, MIRI is no longer short of funds and is instead short of engineering talent.
Factual · 28 Feb 2018 |
Field building and careers |
| Unresolvable |
Factual |
28 Feb 2018 |
Yudkowsky said he was pretty sure he was not the one who invented the term under discussion.
Factual · 28 Feb 2018 |
Other |
| Not researched |
Factual |
28 Feb 2018 |
Asked whether the thought experiment originated with Bostrom, Eliezer Yudkowsky said that, as far as he knew, it originated with him.
Factual · 28 Feb 2018 |
Their own work or organisation |
| Not researched |
Factual |
28 Feb 2018 |
AI researchers who forecast AGI about 30 years off have not argued that, once reached, AGI will develop much more slowly than AlphaZero did.
Factual · 28 Feb 2018 |
AI timelines and forecasting |
| Own records only |
Factual |
28 Feb 2018 |
MIRI has some communication with DeepMind's upper people, though the bandwidth is not optimal.
Factual · 28 Feb 2018 |
Their own work or organisation |
| Not researched |
Factual |
28 Feb 2018 |
Economists already know about market failures and have that concept.
Factual · 28 Feb 2018 |
Economics and markets |
| Not researched |
Factual |
28 Feb 2018 |
MIRI is the original AI alignment organization and today works primarily on the technical parts of the alignment problem.
Factual · 28 Feb 2018 |
Their own work or organisation |
| Not researched |
Factual |
28 Feb 2018 |
Eliezer Yudkowsky wrote two to three years of daily blog posts on human rationality, which were collected into the book Rationality: From AI to Zombies.
Factual · 28 Feb 2018 |
Their own work or organisation |
| Mixed |
Factual |
28 Feb 2018 |
AlphaZero surpassed human Go knowledge in less than a day starting from scratch, without human games, theories or Go-specific code beyond what chess used.
Factual · 28 Feb 2018 |
AI capabilities |
| Not researched |
Factual |
28 Feb 2018 |
Eliezer Yudkowsky conducted the experiment that became known as the AI-box experiment, to demonstrate human limits in dealing with smarter minds.
Factual · 28 Feb 2018 |
AI safety and alignment |
| Not researched |
Factual |
28 Feb 2018 |
Yudkowsky said that AlphaZero is not reflecting on itself, is not learning things, does not have a general model of the world, and is not operating in new contexts or making new contexts for itself to be in.
Factual · 28 Feb 2018 |
AI capabilities |
| Not researched |
Factual |
28 Feb 2018 |
Two years after the Wright Flyer, people could still be found saying heavier-than-air flight is impossible.
Factual · 28 Feb 2018 |
Other global risks |
| Research failed |
Factual |
28 Feb 2018 |
The experiment in which people stay in a smoke-filling room when others look calm is pretty well replicated, with many variations finding basically the same result, though he said he did not want to put absolute faith in it because of the replication crisis.
Factual · 28 Feb 2018 |
Science and research methods |
| Mostly true |
Factual |
30 Jan 2013 |
Nick Bostrom does meta-strategy work as well as object-level work on anthropic probabilities and the parliamentary model for normative uncertainty.
Factual · 30 Jan 2013 |
Field building and careers |
| Mostly true |
Factual |
30 Jan 2013 |
Nick Bostrom hosts researchers such as Anders Sandberg, who write papers about uploading timelines relevant to policy decisions.
Factual · 30 Jan 2013 |
Field building and careers |
| Resolved true |
Factual |
30 Jan 2013 |
Paul Christiano is working on actual Friendly AI problems while also looking for other promising interventions.
Factual · 30 Jan 2013 |
Field building and careers |
| Unresolvable |
Factual |
2008 |
The Dartmouth Proposal on AI makes no mention of building nice, good or benevolent AI.
Factual · 2008 |
AI policy and governance |
| Not researched |
Factual |
2008 |
Subjects in Wason's 2-4-6 task try to confirm their hypotheses rather than falsify them.
Factual · 2008 |
Science and research methods |
| Not researched |
Factual |
2008 |
Flaws have occasionally been discovered in previously accepted informal human mathematical proofs.
Factual · 2008 |
Science and research methods |
| Not researched |
Factual |
2008 |
Information known to be irrelevant still anchors people's judgments and contaminates their guesses.
Factual · 2008 |
Science and research methods |
| Mostly true |
Factual |
2008 |
Overconfidence is no longer noteworthy in the modern field but continues to show up in nearly any experiment allowing extreme probabilities.
Factual · 2008 |
Science and research methods |
| Not researched |
Factual |
2008 |
The book, which is aimed at an intelligent general audience, explains Bayes's Theorem rather than assuming it, in only a few pages.
Factual · 2008 |
Science and research methods |
| Resolved true |
Factual |
2008 |
A mind accelerated a millionfold would accomplish a subjective year of thinking every 31 physical seconds.
Factual · 2008 |
Science and research methods |
| Mostly true |
Factual |
2008 |
Human psychology seems to follow the rule that adding an additional detail can make a story more plausible.
Factual · 2008 |
Science and research methods |
| Not researched |
Factual |
2008 |
The Y2K problem, which was very expensive to fix but not globally catastrophic, arose from failing to foresee future design requirements.
Factual · 2008 |
Technology |
| Not researched |
Factual |
2008 |
The effect of many cognitive biases has been found to increase with time pressure, cognitive busyness, or sparse information.
Factual · 2008 |
Science and research methods |
| Not researched |
Factual |
2008 |
Human brains are not designed to be improved by outside neuroscientists or by internal recursive self-improvement.
Factual · 2008 |
Science and research methods |
| Not researched |
Factual |
2008 |
Guns were developed centuries before bulletproof vests.
Factual · 2008 |
Other global risks |
| Mixed |
Factual |
2008 |
General intelligence is a between-species difference, a complex adaptation, and a human universal found in all known cultures.
Factual · 2008 |
Science and research methods |
| Unresolvable |
Factual |
2008 |
Human beings use heuristics that quickly give good approximate answers in many cases but also produce systematic errors called biases.
Factual · 2008 |
Science and research methods |
| Not researched |
Factual |
2008 |
Critical times for elementary molecular interactions are measured in femtoseconds, sometimes picoseconds.
Factual · 2008 |
Science and research methods |
| Not researched |
Factual |
2008 |
No curriculum exists that has prepared a large pool of researchers to make progress on Friendly AI.
Factual · 2008 |
Field building and careers |
| Not researched |
Factual |
2008 |
In planning, reality usually delivers results somewhat worse than people's stated worst case.
Factual · 2008 |
Science and research methods |
| Not researched |
Factual |
2008 |
In the anthropomorphism experiments discussed, subjects who consciously believed an AI is unlike a human still visualized scenarios as if the AI were anthropomorphic.
Factual · 2008 |
Science and research methods |