Unverified50% confidenceFactExact time
DeepMind在2016年的论文《Safely Interruptible Agents》中指出理想的智能体不应抵制外部中断，也不应绕过人类设定的终止条件
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Cite This Claim
Stable URI
https://kongchang.com/claim/1000160API
curl https://kongchang.com/api/v1/knowledge/claims/1000160MCP
get_claim(id=1000160)