Back
Stuart Russell - Personal Homepage
webpeople.eecs.berkeley.edu·people.eecs.berkeley.edu/~russell/
Stuart Russell is one of the most influential AI researchers working on safety and alignment; this homepage aggregates his research, publications, affiliations, and public talks, serving as a central reference for his work on value alignment and human-compatible AI.
Metadata
Importance: 72/100homepage
Summary
Homepage of Stuart Russell, Distinguished Professor at UC Berkeley and founder of the Center for Human-Compatible AI (CHAI), one of the most prominent figures in AI safety research. He is the author of 'Human Compatible: AI and the Problem of Control' and the leading AI textbook 'Artificial Intelligence: A Modern Approach,' and has been central to formalizing the AI alignment problem around human value uncertainty.
Key Points
- •Founder and director of the Center for Human-Compatible AI (CHAI), a leading academic AI safety research group at UC Berkeley
- •Author of 'Human Compatible' (2019), which argues AI systems must be designed to be uncertain about human preferences rather than optimizing fixed objectives
- •Co-author of 'Artificial Intelligence: A Modern Approach,' the dominant AI textbook used globally, shaping how AI is taught
- •Has addressed the UN on Lethal Autonomous Weapons Systems and delivered BBC Reith Lectures on AI, influencing policy discourse
- •Research spans value alignment, probabilistic reasoning, and the long-term safety implications of advanced AI systems
Cited by 4 pages
| Page | Type | Quality |
|---|---|---|
| Instrumental Convergence Framework | Analysis | 60.0 |
| AI Evaluation | Approach | 72.0 |
| AI-Induced Enfeeblement | Risk | 91.0 |
| AI Model Steganography | Risk | 91.0 |
Cached Content Preview
HTTP 200Fetched Apr 7, 20263 KB
Stuart Russell
Stuart Russell, OBE, FRS
Zoom link for CS294
Distinguished Professor of Computer Science , University of California, Berkeley, and
Smith-Zadeh Professor in Engineering;
Professor of Cognitive Science;
Professor of Computational Precision Health, UCSF;
and Honorary Fellow of Wadham College , Oxford
Mailing address: Computer Science Division
387 Soda Hall
University of California
Berkeley, CA 94720-1776
Office location: 8040 Berkeley Way West
Office hours: by appointment
Email: please contact my assistant, JP, at jp@humancompatible.ai
Information for prospective MS and PhD students
Information for prospective interns
Research group (Russell's Unusual Group of Students)
Research centers and affiliations:
Center for Human-Compatible AI (CHAI)
Kavli Center for Ethics, Science, and the Public (KCESP)
Berkeley Artificial Intelligence Research (BAIR)
Institute for Cognitive and Brain Sciences (ICBS)
AI Institute for Agent-Based Cyber Threat Intelligence and Operation (ACTION)
Program in Computational Precision Health (CPH)
Research areas , including publications by area
Publications in chronological order
Teaching (Fall 2018) : CS 294-149: Safety and Control for Artificial General Intelligence (co-taught by Dr. Andrew Critch) -->
CV
Biography : long (350 words) , short (175 words) , very short (75 words)
Other useful pointers:
2021 Reith Lectures: Living With Artificial Intelligence
Human Compatible: AI and the Problem of Control
Artificial Intelligence: A Modern Approach
Have the machines taken over? Video of interview by Richard Sargeant, Westminster Abbey, November 20, 2018.
Rationality and Intelligence , slides from the IJCAI 95 Computers and Thought lecture.
Learning in Rational Agents , slides from NIPS 97 invited talk.
What is to be done? , slides from AAAI 08 invited talk.
Life: Play and Win in 20 Trillion Moves , slides from SARA 2011 invited talk.
Unifying Logic and Probability; A New Dawn for AI? , slides from the Colloquium Sorbonne-Universités, Jan 2013.
The Long-Term Future of (Artificial) Intelligence , slides from AAAI 2015 invited talk.
Artificial Intelligence: Implications for Autonomous Weapons , address to the United Nations meeting on Lethal Autonomous Weapons Systems, Geneva, April 2015.
Killer Robots, the End of Humanity, and All That: What's a Good AI Researcher to Do? , slides from IJCAI 2015 invited talk.
Future of Artificial Intelligence and the Human Race , video from TEDxYouth@EB, Ecole Bilingue de Berkeley, November 14, 2015.
Three principles for creating safer AI , TED talk, Vancouver, April 25, 2017.
Provably Beneficial Artificial Intelligence (starts at 55.25), IJCAI 2017 invited talk ( slides here ) .
Uncertainty in Objectives , slides from UAI 2018 invited talk.
How Not to Destroy the World With AI , slides from AAAI 2020 keynote talk.
Artificial Intelligence: Some Thoughts? , slides from IJCAI 2022 Research Excel
... (truncated, 3 KB total)Resource ID:
2ccf0b6518e285d6 | Stable ID: sid_eNHWa6ooGD