Unverified75% confidenceFactExact time
如果不在 CLAUDE.md 中指定技术栈，大模型会自动选择其训练数据中出现概率最高的技术组合
1
Sources
75%
Confidence
Long-term
Relevance
5/30/2026
First Seen
Sources
CLAUDE.md Configuration Guide: Write Your Project Spec Using a Six-Section Structure
bilibili路过的阿诚5/30/2026
Related Entities
Related Claims
UnverifiedThe core mechanism of an LLM is to predict the next most likely token — that is, to find the highest-probability path in the training data distribution.75% similarUnverifiedAlignment training optimizes the model's statistical behavior in known scenarios rather than establishing formally verifiable security boundaries, and may fail when faced with rare instruction combinations or role-playing frameworks outside the training distribution.74% similarUnverified即便固定所有随机种子，在不同硬件或并行度下，训练结果仍可能出现被大模型放大为显著能力差异的细微偏差74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/489API
curl https://kongchang.com/api/v1/knowledge/claims/489MCP
get_claim(id=489)