Donald Hobson

Featured in:

Articles

An open response to Wittkotter and Yampolskiy — LessWrong

Sep 24, 2024 | lesswrong.com | Donald Hobson

A response to this paper. https://asi-safety-lab.com/DL/Kill-Switch-For_ASI_EW_21_12_14.pdfA substantial fraction of my argument comes down to. It is plausible that a hypothetical hypercompetent civilization could coordinate to build such infrastructure. However we don't live in a hypothetical hypercompetent civilization. We are not remotely close, and any attempt to get us there will be met with almost certain failure.
Using LLM's for AI Foundation research and the Simple Solution assumption — LessWrong

Sep 24, 2024 | lesswrong.com | Donald Hobson

Current LLM based AI systems are getting pretty good at maths by writing formal proofs in Lean or similar. https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/So, how can we use these models to help align AI? The Simple Alignment Solution Assumption states that many problems in alignment, for example corrigibility or value learning, have simple solutions. I mean "simple" in the sense that logical induction is a simple solution. That expected utility maximization is.
Is this voting system strategy proof? — LessWrong

Sep 6, 2024 | lesswrong.com | Donald Hobson

My voting system works like this. Each voter expresses their preferences for all candidates on a real numbered utility scale. Then a Maximal lottery takes place over all lotteries over candidates. https://en.wikipedia.org/wiki/Maximal_lotteriesLets describe this in more detail. Suppose there are 3 candidates. A,B,C.
Two Tales of AI Takeover: My Doubts — LessWrong

Mar 5, 2024 | lesswrong.com | Gerald M. Monroe |Daniel Kokotajlo |Donald Hobson

There’s a basic high-level story which worries a lot of people. The story goes like this: as AIs become more capable, the default outcome of AI training is the development of a system which, unbeknownst to us, is using its advanced capabilities to scheme against us. The conclusion of this process likely leads to AI takeover, and thence our death. We are not currently dead. So, any argument for our death by route of AI must offer us a causal story.
AI #52: Oops — LessWrong

Feb 22, 2024 | lesswrong.com | Gerald M. Monroe |Donald Hobson

Given that humans on their own haven't yet found these better architectures, humans + imitative AI doesn't seem like it would find the problem trivial. Humans on their own already did invent better RL algorithms for optimizing at the network architecture layer. https://arxiv.org/pdf/1611.01578.pdf backgroundhttps://arxiv.org/pdf/1707.07012.pdf : page 6With NAS, the RL model learns the relationship between [architecture] and [predicted performance].
Monthly Roundup #15: February 2024 — LessWrong

Feb 20, 2024 | lesswrong.com | Donald Hobson |Gerald M. Monroe

Another month. More things. Much roundup. Bad NewsJesse Smith writes in Asterisk that our HVAC workforce is both deeply incompetent and deeply corrupt. This certainly matches my own experience. Calculations are almost always flubbed when they are done at all, outright fraudulent paperwork is standard, no one has the necessary skills. It certainly seems like the Biden Administration is doing its best to hurt Elon Musk?
Epistemic Hell - LessWrong

Jan 27, 2024 | lesswrong.com | Carl Feynman |Donald Hobson |Gordon Worley

I. From Scott Alexander’s review of Joe Henrich’s The Secret of our Success:In the Americas, where manioc was first domesticated, societies who have relied on bitter varieties for thousands of years show no evidence of chronic cyanide poisoning. In the Colombian Amazon, for example, indigenous Tukanoans use a multistep, multi-day processing technique that involves scraping, grating, and finally washing the roots in order to separate the fiber, starch, and liquid.
Muddling Along Is More Likely Than Dystopia — LessWrong

Oct 20, 2023 | lesswrong.com | Jeffrey Heninger |Roman Leventov |Donald Hobson

Summary: There are historical precedents where bans or crushing regulations stop the progress of technology in one industry, while progress in the rest of society continues. This is a plausible future for AI. Epistemic Status: My intuition strongly disagrees with other people here. I hope to explain my intuition, and provide enough historical evidence to make this intuition at least plausible. Suppose you told someone in 1978 that no new nuclear power plants would be built in the US until 2023.
Bring back the Colosseums — LessWrong

Sep 8, 2023 | lesswrong.com | Donald Hobson |Jacob Falkovich

Men want to engage in righteous combat. They want it more than they want sex or VP titles.
Contra Yudkowsky on AI Doom — LessWrong

Apr 24, 2023 | lesswrong.com | Steven Byrnes |Adele Lopez |Gordon Worley |Donald Hobson

Eliezer Yudkowsky predicts doom from AI: that humanity faces likely extinction in the near future (years or decades) from a rogue unaligned superintelligent AI system. Moreover he predicts that this is the default outcome, and AI alignment is so incredibly difficult that even he failed to solve it. EY is an entertaining and skilled writer, but do not confuse rhetorical writing talent for depth and breadth of technical knowledge.