Unverified50% confidenceFactExact time
Anthropic在2023年发表了'表征工程'研究，Turner等人发表了'激活加法'工作，都是该技术范式的代表性成果
1
Sources
50%
Confidence
Long-term
Relevance
8/6/2026
First Seen
Sources
Related Claims
UnverifiedThe field of mechanistic interpretability was largely founded by the Anthropic research team (especially Chris Olah) around 2021 through the "Transformer Circuits" series of papers.71% similarUnverifiedIn 2023, Stanford University published the paper 'Generative Agents,' marking the transition of Agents from an academic concept to engineering practice.68% similarUnverifiedAnthropic研究团队2023年发表了关于奉承性偏差的系统性分析64% similarUnverifiedIn June 2025, Anthropic published a blog post titled 'A Harness for Every Task' introducing Claude Code's dynamic workflow mechanism.63% similarUnverifiedAnthropic has released a 36-page "Founder's Handbook for AI-Native Startups."63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/695774API
curl https://kongchang.com/api/v1/knowledge/claims/695774MCP
get_claim(id=695774)