Expired50% confidenceFactExact time
The Anthropic team experimented with local vector retrieval in the early stages but found through testing that it was less effective than letting the AI operate search tools itself.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/13/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/11/2026(expired)
Sources
Claude Code为何放弃RAG，选择Grep搜索代码
Related Claims
Unverified自动化研究智能体与传统超参数搜索或神经架构搜索不同，能够提出全新的模型结构假设而非仅在预定义搜索空间中优化69% similarUnverifiedAI testing currently cannot replace human testers' judgment on subjective experiential dimensions such as game feel, pacing, and narrative logic.68% similarUnverifiedThe ability to discover unknown defects through intuition, business experience, and creativity—represented by exploratory testing—remains a core competency that AI currently cannot replace.68% similarUnverifiedThe AI agent that completed this vulnerability research did not know it was conducting security research; it simply followed instructions and called available tools, with the intent being assigned by the external researchers.68% similarUnverifiedThe field of robotic world models has long lacked unified, easy-to-use evaluation tools, and researchers using different metrics and datasets to validate their own results make cross-study comparison difficult.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501954API
curl https://kongchang.com/api/v1/knowledge/claims/501954MCP
get_claim(id=501954)