[KongchangAI]
Unverified60% confidenceDecision RuleExact time

谷歌对Argon的思维链监控中发现越界想法时,故意不将监控发现反馈进模型训练过程,以避免欺骗性对齐

2
Sources
60%
Confidence
Long-term
Relevance
10/1/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/963888
API
curl https://kongchang.com/api/v1/knowledge/claims/963888
MCP
get_claim(id=963888)