Cooperative AI
Joel Z. Leibo is a research scientist at DeepMind. He obtained his PhD in 2013 from MIT where he worked on the computational neuroscience of face recognition with Tomaso Poggio. Nowadays, Joel's research is aimed at the following questions:
Human intelligence employs a set of cognitive abilities and inductive biases that underlie our impressive – for a mammal – ability to cooperate with one another. I propose that we approach our goal of building cooperative AI through the lens of reverse engineering human cooperation. The reverse engineering approach is common in AI research, especially for work on the “classic” cognitive abilities like perception, attention, and memory. But I think it has been too under explored with regard to the social-cognitive abilities that underlie cooperation. We need to figure out what are the…
saved by
related reading
- [2211.13746] Melting Pot 2.0arxiv.org
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- Solipsistic Superintelligence is Unlikely to be Cooperativearxiv.org
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- John Schulman - Reinforcement Learning from Human Feedback: Progress and Challengesyoutube.com
- [2206.12765] Generalized Beliefs for Cooperative AIarxiv.org
- Learning through human feedback — Google DeepMinddeepmind.google
- PhD_thesis_Shirley_Wu_final.pdfcs.stanford.edu
- Towards Safe and Honest AI Agents with Neural Self-Other Overlaparxiv.org
- From Machine Learning to Autonomous Intelligence – AI-Talk by Prof. Dr. Yann LeCunyoutube.com
- [1903.00742] Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Researcharxiv.org
- Mehdi Azaboumehai.dev