Who's Who of AI

Vincent Conitzer

155 trust researcher @conitzer.bsky.social · 1,484 followers
AI professor. Director, Foundations of Cooperative AI Lab at Carnegie Mellon. Head of Technical AI Engagement, Institute for Ethics in AI (Oxford). Author, "Moral AI - And How We Get There." https://www.cs.cmu.edu/~conitzer/
What they're sharing

Articles & links

Emanuel Tewolde is presenting our CoopEval work at ICML on Wednesday 10:30am session (or catch him at the alignment workshop today)! presentation: icml.cc/virtual/2026... arXiv: arxiv.org/abs/2604.15267

CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas arxiv.org
AI Weekly's analysis →
  • CoopEval compares four cooperation mechanisms — repeated games, reputation, third-party mediators, and outcome-conditional contracts — applied to LLM agents.
  • The authors report that LLMs with stronger reasoning capabilities behave less cooperatively in mixed-motive games, not more.
  • Contracting and mediation worked best for capable models, while repetition-based cooperation deteriorated when co-players changed.
Read full analysis →
View on Bluesky · ♥ 8 ↻ 1 ↩ 2 · 2 from the directory shared this · 3d ago

Emanuel Tewolde is presenting our CoopEval work at ICML on Wednesday 10:30am session (or catch him at the alignment workshop today)! presentation: icml.cc/virtual/2026... arXiv: arxiv.org/abs/2604.15267

ICML Poster CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas icml.cc
AI Weekly's analysis →
  • CoopEval evaluates LLM agents across four social dilemmas layered with four cooperation-sustaining mechanisms: repetition, reputation, mediation, and contracting.
  • Contracting scored 0.801 and mediation 0.695 on a normalized cooperation scale, ahead of repetition at 0.587 and both reputation variants.
  • Repetition-based cooperation broke down when co-players changed, while higher optimization pressure amplified the effectiveness of all four mechanisms.
Read full analysis →
View on Bluesky · ♥ 8 ↻ 1 ↩ 2 · 2 from the directory shared this · 3d ago

Today (Korea time) at ICML in the 5pm session, Vijay Keswani is presenting our position paper "We Need Practical AI Alignment Methods that Mirror Human Reasoning!" presentation: icml.cc/virtual/2026... paper: openreview.net/pdf/a895d4cf...

openreview.net
View on Bluesky · ♥ 2 ↻ 0 ↩ 0 · 4h ago

Our recursive joint simulation paper (w/ Vojta and Caspar) has been accepted to Synthese! TLDR: When players in a game run a simulation of themselves (incl. further subsimulations), that's equivalent to an infinitely repeated game and so allows cooperation (folk theorems). arx…

Recursive Joint Simulation in Games arxiv.org
View on Bluesky · ♥ 7 ↻ 0 ↩ 0 · 18d ago
Their network

In Vincent Conitzer's orbit

Center = Vincent Conitzer. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.