METR：Notes（网页）·· 13 小时前AI 评分46
METR 复现 Google DeepMind 论文：Claude、GPT、Gemini 均难以逃避思维链监控
Claude, GPT, and Gemini All Struggle to Evade Monitors August 22, 2025 Vincent Cheng and Thomas Kwa replicate a Google DeepMind paper on chain-of-thought monitoring, showing evidence that monitoring works on other companies' models. Read more
AI 导读
METR 研究者 Vincent Cheng 与 Thomas Kwa 复现了 Google DeepMind 论文第 5 节，用 Claude 4 Sonnet。
来源：METR：Notes（网页） · metr.org