研究发现：LLM 发展速度已超出解释它的研究
原标题：Rapid LLM development is outrunning the research meant to explain it, study finds
AI 摘要
斯坦福研究者 Owen Queen 与 James Zou 检验了 50 条被广泛引用的 LLM 结论，在 20 个模型上复测后发现 44% 已「过期」，有预估期限的 22 条结论平均寿命仅 15.7 个月。关于模型「做不到什么」的结论失效最快，而偏好与倾向类结论更持久；幻觉引用等能力缺陷在部分新模型上消失，但不同模型间差异巨大。研究者据此呼吁论文应标注具体模型、版本与日期并公开提示词和代码，把结论视为特定时点的观察而非普遍真理。
正文节选
Rapid LLM development is outrunning the research meant to explain it, study finds Stanford researchers Owen Queen and James Zou tested 50 widely cited claims about large language models against 20 models and found that 44 percent have already "expired." Among the 22 findings with an estimated expiration date, the average lifespan was just 15.7 months. The two examined the claims using models released between July 2024 and September 2026 by eight different developers. The original effect behind t