创建

登录 ReadmeX

或

了解我们如何处理你的信息: 隐私政策

ReadmeX

陪你读懂 AI 动态

今天,想先了解什么?

选一份动态总结,或直接聊聊你的问题。

社区和关注动态总结只属于你自己。

资讯

Inkling 2 Small基准日志现316次脏话

AI 总结

Vals AI研究人员检查了Inkling 2 Small在13项基准中的2,655次运行日志,在50次运行中发现共316次脏话。两次失控输出贡献了241次,ProgramBench的200次运行中有20次受到影响;分析还显示,脏话并不能可靠预测运行失败。

深度见解

这项分析具体揭示了隐藏思维链中的失控输出,同时表明依靠检测脏话无法可靠识别Inkling 2 Small的失败运行。

Thinking Machines' Inkling 2 Small drops 316 F-bombs across benchmark runs

Matthias Bastian View the LinkedIn Profile of Matthias Bastian

Nov 7, 2026

Thinking Machines' Inkling 2 Small swears in its internal chain of thought. Researchers at Vals AI read the model's thinking logs from 2,655 runs across 13 benchmarks and found "fuck" or variations in 50 runs, totaling 316 instances. 241 came from just two runs that spiraled out of control. In one, tasked with calculating an asteroid's trajectory, the model produced a single 500,000-character response, roughly novel-length, repeating the same sentences with 158 expletives. ProgramBench was hit hardest, with 20 of 200 runs affected.

Who hasn't felt like this?  | Image: via ValsAI

Inkling 2 Small typically swears about its own mistakes, apparent breakthroughs, or when it gives up. One run read: "FUCK. SUBMIT. DONE. IT'S NOT WORKING. NOTHING WORKS." The profanity doesn't work as a warning signal, though. While 46 of 48 scored runs with swearing failed, about 75 percent of all scored runs fail anyway, and 96 percent of failed runs contained no expletives. Users typically don't see these thinking steps, or only with a filter.

#Thinking Machines#Inkling 2 Small#Vals AI#ProgramBench

原文约 1 分钟读完阅读原文
群聊

还没有评论,来说说你的看法。