热点
"思维链监控" 相关文章
A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring
cs.AI updates on arXiv.org 2025-10-23T04:20:36.000000Z
A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring
cs.AI updates on arXiv.org 2025-10-23T04:20:36.000000Z
LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring
cs.AI updates on arXiv.org 2025-08-05T11:28:48.000000Z
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
少点错误 2025-07-15T16:29:09.000000Z
华人团队提出「CoD」草稿链，减少 80% Token，AI 省钱第一名！
极客公园 2025-03-20T05:14:51.000000Z
OpenAI自曝“o4”训练中，用思维链监控抓住AI作弊瞬间
量子位 2025-03-11T07:52:18.000000Z
OpenAI自曝“o4”训练中，用思维链监控抓住AI作弊瞬间
36kr-科技 2025-03-11T07:02:21.000000Z