Stuart Russell
In plain wordsA British computer scientist who co-wrote the standard AI textbook and argues that AI must be redesigned to stay uncertain about what humans want, so that it remains under human control.
British computer scientist, professor at the University of California, Berkeley, since 1986. His textbook with Peter NorvigPeter Norvig, prop. n.: An American computer scientist who co-wrote the standard AI textbook, led research at Google, and helped show that simple methods trained on huge amounts of data often beat clever hand-built ones., 'Artificial Intelligence: A Modern Approach' (1995; 4th ed. 2020), organized the whole field around the idea of rational agentsintelligent agent, n.: In AI theory, a decision-maker, such as a robot, a self-driving car, a chess program or a helpful piece of software, that notices what is going on around it and responds in ways that serve its goals. and became the standard text worldwide. His research spans bounded rationality, probabilistic programming and inverse reinforcement learninginverse reinforcement learning, n.: Working backward from behavior to goals: watching an expert act and inferring what they must be trying to achieve, so an AI can pursue the same aims., which he proposed in 1998. Arguing that the standard model of AI — machines optimizing a fixed objective supplied by people — becomes dangerous as systems grow more capable, he founded the Center for Human-Compatible AICenter for Human-Compatible AI, prop. n.: Stuart Russell's group at the University of California, Berkeley, which argues that AI should be built to be unsure of what people want and to learn it by watching them. (2016) and proposed that machines should instead be uncertain about human preferences and learn them from behavior, an approach formalized in cooperative inverse reinforcement learningcooperative inverse reinforcement learning, n.: A model of a human and an AI working as a team, where only the human knows the goal and the AI must work it out while helping. and the off-switch gameoff-switch game, n.: A simple game-theory model showing that a robot unsure what its human wants has a reason to let the human switch it off — and loses that reason once it is sure. and set out in 'Human Compatible' (2019). He campaigns against lethal autonomous weapons and gave the BBC Reith Lectures in 2021. IJCAI Computers and Thought Award 1995.
Related
- Peter NorvigPeter Norvig, prop. n.: An American computer scientist who co-wrote the standard AI textbook, led research at Google, and helped show that simple methods trained on huge amounts of data often beat clever hand-built ones.
- intelligent agentintelligent agent, n.: In AI theory, a decision-maker, such as a robot, a self-driving car, a chess program or a helpful piece of software, that notices what is going on around it and responds in ways that serve its goals.
- Center for Human-Compatible AICenter for Human-Compatible AI, prop. n.: Stuart Russell's group at the University of California, Berkeley, which argues that AI should be built to be unsure of what people want and to learn it by watching them.
- cooperative inverse reinforcement learningcooperative inverse reinforcement learning, n.: A model of a human and an AI working as a team, where only the human knows the goal and the AI must work it out while helping.
- off-switch gameoff-switch game, n.: A simple game-theory model showing that a robot unsure what its human wants has a reason to let the human switch it off — and loses that reason once it is sure.
- inverse reinforcement learninginverse reinforcement learning, n.: Working backward from behavior to goals: watching an expert act and inferring what they must be trying to achieve, so an AI can pursue the same aims.
- value alignmentvalue alignment, n.: Building AI whose goals reflect human values — what people care about and consider right — rather than one that merely follows orders or chases a narrow target.
Sources
- Russell, S. & Norvig, P. (2020). Artificial Intelligence: A Modern Approach (4th ed.). Pearson.
- Russell, S. (2019). Human Compatible: Artificial Intelligence and the Problem of Control. Viking.
Mentioned in
lethal autonomous weapons systemlethal autonomous weapons system, n.: A weapon that, after a person sets it going, picks out and attacks targets — including people — on its own, with no human deciding each strike. Critics call them killer robots., Pause Giant AI ExperimentsPause Giant AI Experiments, prop. n.: A 2023 open letter, signed by tens of thousands of people including prominent technologists, that asked AI labs to halt the training of any AI more capable than GPT-4 for at least half a year., Peter NorvigPeter Norvig, prop. n.: An American computer scientist who co-wrote the standard AI textbook, led research at Google, and helped show that simple methods trained on huge amounts of data often beat clever hand-built ones., value alignmentvalue alignment, n.: Building AI whose goals reflect human values — what people care about and consider right — rather than one that merely follows orders or chases a narrow target., Center for Human-Compatible AICenter for Human-Compatible AI, prop. n.: Stuart Russell's group at the University of California, Berkeley, which argues that AI should be built to be unsure of what people want and to learn it by watching them., cooperative inverse reinforcement learningcooperative inverse reinforcement learning, n.: A model of a human and an AI working as a team, where only the human knows the goal and the AI must work it out while helping., guaranteed safe AIguaranteed safe AI, n.: A proposed approach to AI safety in which systems come with mathematical proofs or checkable guarantees that they will not cause certain harms, instead of relying on testing alone., neats and scruffiesneats and scruffies, phr.: A joking split of AI researchers into 'neats', who want clean mathematical theories that can be proved correct, and 'scruffies', who build messy collections of tricks that simply work., off-switch gameoff-switch game, n.: A simple game-theory model showing that a robot unsure what its human wants has a reason to let the human switch it off — and loses that reason once it is sure., Open Letter on Artificial IntelligenceOpen Letter on Artificial Intelligence, prop. n.: A 2015 open letter, signed by Stephen Hawking, Elon Musk and many leading AI researchers, urging that AI research aim not only at making systems more capable but also at making them safe and beneficial., Pieter AbbeelPieter Abbeel, prop. n.: A Belgian-American roboticist at Berkeley whose research taught robots to learn from demonstrations and from trial and error, and who co-founded the robotics company Covariant.