News for hackers. Stuff that matters.
Re:The "confident idiot" problem: Why AI needs hard rules, n... by __turbobrew__ on Monday December 08, 2025 @01:12PM (#46195656)
The day when the LLM responds to my question with another question will be quite interesting. Especially at work, when someone asks me a question I need to ask for clarifying information to answer the original question fully.
Re:The "confident idiot" problem: Why AI needs hard rules, n... by djeastm on Monday December 08, 2025 @05:59PM (#46198861)
Have you tried adding a system prompt asking for this behavior? They seem to readily oblige when I ask for this (e.g. brainstorming)