Unverified80% confidenceFactTime unknown
通用LLM因缺乏任务约束会产生格式漂移（Format Drift），即每次输出的结构和质量存在不可预测的差异
1
Sources
80%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAgent链式调用多步之后，每次LLM输出的细微差异导致误差逐步放大，最终结果偏离预期70% similarUnverifiedThe most common problem with AI-written code is not inability to produce output, but that changes drift further off course with each iteration.70% similarUnverifiedLLM output is non-deterministic; due to the non-associativity of floating-point operations and differences in context windows, even with identical inputs, outputs are difficult to reproduce exactly and do not possess idempotency.69% similarUnverifiedLLM在长时间自主运行中容易出现目标漂移（Goal Drift），通过每步微小决策在数十轮迭代后累积出显著语义漂移67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/15935API
curl https://kongchang.com/api/v1/knowledge/claims/15935MCP
get_claim(id=15935)