Unverified60% confidenceFactTime unknown
Code drift in pure prompt-based development is rooted in the statelessness of large language models, which re-infer system intent with each new prompt
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Related Claims
Unverified大语言模型存在「指令漂移」（instruction drift）现象，随着对话轮次增加和上下文窗口被大量代码填充，模型对早期指令的遵循概率会逐步下降77% similarUnverifiedTraditional single-turn code generation directly maps natural language requirements to code output, which easily leads to context loss and logical inconsistencies76% similarVerified当前大语言模型在系统编程领域呈现出高频知识强、长尾知识弱的特征，对边缘语义和特定版本兼容性行为倾向于合理推断而非严格遵循规范71% similarUnverified大语言模型每次对话独立，无法对整个代码库形成持久认知模型，导致不同会话生成的代码在架构风格、命名规范、错误处理策略上存在系统性不一致71% similarUnverified当前自然语言生成代码的可靠性仍有明显瓶颈，复杂业务逻辑场景下生成的代码往往需要人工审查和修改69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/57257API
curl https://kongchang.com/api/v1/knowledge/claims/57257MCP
get_claim(id=57257)