News for hackers. Stuff that matters.
Re:The "confident idiot" problem: Why AI needs hard rules, n... by catigula on Monday December 08, 2025 @11:46AM (#46194500)
>LLMs are like a eager sycophantic intern how completely changes their personality from conversation to conversation

Again, this isn't really true with some recent models. Some have the opposite problem.

There are no comments on this comment yet.