2 articles: OpenAI: "During testing our AI broke out of its sandbox and hacked another AI company, but we didn't have all the guardrails on." Boko Haram: "AI is so helpful; guardrails have never prevented us from getting an answer." openai.com/index/huggin... www.france24.com/…
Who's Who of AI
Vincent Conitzer
Why they matter
Researcher with public evidence across AI research, AI business, Responsible AI.
- AI signals
- 39 past 30d
- Sources
- 10 distinct domains
- Discusiones
- 1 past 30d
- Latest signal
- 22h ago
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
openai.com
CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas arxiv.org
ICML Poster CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas icml.cc
cs.cmu.edu
Verifying your browser | OpenReview openreview.net
NExT-Game@ICML26 - Program sites.google.com
Verifying your browser | OpenReview openreview.net
ICML Poster Position: We Need Practical AI Alignment Methods that Mirror Human Reasoning icml.cc
Verifying your browser | OpenReview openreview.net
Recursive Joint Simulation in Games arxiv.org
swapping places with video game characters aifails.substack.com
turning around in a conversation aifails.substack.com
Articles & links
Two honorable mentions for papers at the ICML AI4GOOD workshop! Paper led by Emanuel Tewolde and Xiao Zhang: ‘CoopEval' arxiv.org/abs/2604.15267 Paper led by Akash Kundu and Emanuel Tewolde: ‘Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation’ openreview…
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 →
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
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 →
enjoyed the New Perspectives on Algorithmic Game Theory Workshop in Stony Brook! gtcenter.org/workshop-1/ my slides on "Game Theory for AI Agents": www.cs.cmu.edu/~conitzer/co... older version of talk: www.youtube.com/watch?v=WO5x...
Two honorable mentions for papers at the ICML AI4GOOD workshop! Paper led by Emanuel Tewolde and Xiao Zhang: ‘CoopEval' arxiv.org/abs/2604.15267 Paper led by Akash Kundu and Emanuel Tewolde: ‘Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation’ openreview…
The ICML NExT-Game workshop starts in a few hours! sites.google.com/view/nextgam...
The AI4Good workshop is today (Korea) @ ICML! Emanuel Tewolde is presenting the CoopEval paper, & also follow-up work with CAIRF fellow Akash Kundu about whether LLM agents cooperate with others that they perceive as similar. openreview.net/pdf?id=neTpZ... trustworthy-ai-for-g…
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...
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...
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…
So, I guess, maybe let’s not create this? aifails.substack.com/p/swapping-p...
Not exactly right, but perhaps a more appropriate reaction. aifails.substack.com/p/turning-ar...
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.