Unverified90% confidenceOpinionTime unknown
Theo认为如果信息在代码库中能找到就不应放在AgentMD里，因为模型已经非常擅长通过bash命令和工具探索代码库
1
Sources
90%
Confidence
Long-term
Relevance
6/2/2026
First Seen
Sources
Related Entities
Related Claims
Unverified/init命令的代码库扫描逻辑是确定性的程序行为，而非模型的概率性输出67% similarUnverifiedHaving an Agent self-review code it just wrote tends to carry over the original assumptions, making it difficult to find problems; introducing an external heterogeneous model for review can break through this blind spot.62% similarUnverified从信息论角度，生成代码更接近搜索与组合问题，而验证正确性更接近 NP 验证问题60% similarUnverifiedProactive agents actively explore codebases, reading relevant files, analyzing project structure, and understanding existing coding conventions.60% similarUnverifiedThe /code-review command is currently better suited as an auxiliary check and discussion starting point, and cannot replace human judgment on business logic, architectural impact, and online risks.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/38038API
curl https://kongchang.com/api/v1/knowledge/claims/38038MCP
get_claim(id=38038)