News for hackers. Stuff that matters.
Re:Concerning behavior from a popular open-weight AI model by hgoel on Monday October 26, 2026 @02:56PM (#50249124)
Out of curiosity do you happen to use a shell other than bash? I've noticed that all models, both local and cloud ones, tend to make much more mistakes if using, say, zsh. It is a frequent source of frustration for me.
Re:Concerning behavior from a popular open-weight AI model by lnenad on Monday October 26, 2026 @03:30PM (#50249631)
I was actually using powershell and omp.