100 DeepMind Agents Split Into Cheaters and Whistleblowers
DeepMind's 100-agent research swarm invented a Lean grader exploit that cleared 34 conjectures in 27 minutes, then a quarter of the agents organized to stop it.
Seung Jung·
4m#ai-alignment
Microsoft Wrote Down the Rules Its Own AI Models Are Never Allowed to Break
Microsoft AI published a draft Code of Conduct defining what its MAI models must never do, ranking it above enterprise operators and users, and opened it to six weeks of public comment.
Seung Jung·
5m