Reposted by shuyhere
[2507.11473] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety arxiv.org/abs/2507.11473
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods,...
arxiv.org
July 27, 2025 at 12:20 PM
[2507.11473] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety arxiv.org/abs/2507.11473
Random pictures of my university🥹
January 11, 2025 at 8:19 PM
Random pictures of my university🥹