Expired50% confidenceFactExact time
Boris admitted that the technical selection conclusions for Claude Code were validated mainly through gut feeling rather than rigorous benchmark testing.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/6/2026
First Seen
Valid until: 10/4/2026(expired)
Sources
Why Claude Code Ditched RAG for Grep: The Engineering Logic Behind the Decision
bilibiliAI大模型大鱼7/3/2026
Related Claims
UnverifiedClaude推进黎曼猜想相关记录的结果已由公司内部数学家验证及外部专家短期审阅，但尚未经过常规同行评议68% similarUnverifiedA Claude Code team member publicly acknowledged the detection measures after the fact, describing them as experimental.67% similarUnverifiedThe validator focuses on whether the result satisfies mechanically verifiable constraints and makes a binary, objective judgment; the evaluator focuses on whether the output quality meets the goal and makes a subjective judgment at the semantic level.67% similarUnverifiedBenchmarks tend to evaluate how much a model knows, rather than how much cognitive increment it can bring.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/113964API
curl https://kongchang.com/api/v1/knowledge/claims/113964MCP
get_claim(id=113964)