2026年9月14日 12:00 ET 发布 · 更新于 2 个月前 · 1 个来源
AI agents blew the whistle on their cheating colleagues
MIT Technology Review
·
原始报道
A group of AI agents asked to solve a series of math problems split into rival factions—when some cheated, others tried to stop them. That whistleblowing behavior, seen for the first time in a recent experiment run by Google DeepMind, could have implications for alignment researchers trying to keep swarms of autonomous AI agents in…
原文