Unverified85% confidenceFactTime unknown

Anthropic发布过关于模型内部表征的可解释性研究（'用显微镜观察Claude'系列研究）

1

Sources

85%

Confidence

Long-term

Relevance

6/1/2026

First Seen

Sources

Claude's Sycophancy Rate Hits 38% on Spirituality Topics: Anthropic Research Reveals the Truth About AI People-Pleasing Behavior

rss

Related Entities

Anthropiccompany Claudemodel

Related Claims

UnverifiedAnthropic has released Claude Science, an application built specifically for scientific research, which is currently in beta.73% similar Unverified上下文蒸馏由 Anthropic 在训练 Claude 系列模型时广泛采用71% similar VerifiedAnthropic published mechanistic interpretability research on the internal feature interpretation of Claude in 2024, discovering millions of interpretable feature units.70% similar UnverifiedAnthropic发布了Model Spec文档，详细规定了Claude在面对不确定性时的行为准则70% similar VerifiedAnthropic is the developer of the Claude model series.69% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/34148

API

curl https://kongchang.com/api/v1/knowledge/claims/34148

MCP

get_claim(id=34148)