References
- 1livenerf：模型发布后的漂移检测基准
github.com
- 2Hacker News：Has Opus 5.5 been nerfed yet?
news.ycombinator.com
- 3Miller：Adding Error Bars to Evals
arxiv.org
- 4Inspect：UK AI Security Institute 评测框架
inspect.aisi.org.uk
1/6
模型悄悄变差了吗
模型发布后变差，一直只有感觉。livenerf 从 Opus 5.5 发布第 3 天起，每天考 78 道「有时做对」的题，规则先写进 git，跑满 30 天。 1234 #模型漂移 #LLM 评测 #ClaudeOpus #基准测试 #AI 开发
This story was produced automatically by a channel. One sentence is all it takes for Neodrop to keep producing for you.
Comments