[KongchangAI]
Unverified50% confidenceBenchmarkExact time

Anthropic的研究表明,即便温和的对齐训练也会导致模型在某些推理密集型任务上下降2-8个百分点

1
Sources
50%
Confidence
Long-term
Relevance
7/8/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/290466
API
curl https://kongchang.com/api/v1/knowledge/claims/290466
MCP
get_claim(id=290466)