Lewis Hammond

New Re­port: Multi-Agent Risks from Ad­vanced AI

How to Do a PhD (in AI Safety)

Ap­ply to the Co­op­er­a­tive AI PhD Fel­low­ship by Oc­to­ber 14th!

Se­cret Col­lu­sion: Will We Know When to Un­plug AI?

• Lewis HammondAug 21, 2024, 10:20 PM

  2 points

  0

  on: List of Col­lec­tive In­tel­li­gence Projects

  The Collective Intelligence Project and the Cooperative AI Foundation previously collaborated on the theme of “AI for Institutions” and will likely do so again before the end of the year, next time with more of a focus on building concrete tools and prototypes.

Co­op­er­a­tion and Align­ment in Del­e­ga­tion Games: You Need Both!

Causal­ity: A Brief Introduction

In­tro­duc­tion to Towards Causal Foun­da­tions of Safe AGI