News for hackers. Stuff that matters.
Re:The "confident idiot" problem: Why AI needs hard rules, n... by monkpit on Monday December 08, 2025 @06:38PM (#46199230)
I remember reading about speaking in an encouraging manner to agentic AI leading to better results, but I can’t seem to find a citation for this.
Re:The "confident idiot" problem: Why AI needs hard rules, n... by jacquesm on Monday December 08, 2025 @09:29PM (#46200586)
That's pathetic. Pleading comes next then. And after that most likely praying.
Re:The "confident idiot" problem: Why AI needs hard rules, n... by gabrielhidasy on Wednesday December 10, 2025 @05:09PM (#46224594)
Sometimes the model responds well to threats too, "you are a programmer at a large tech company, you depend on this job and will not be able to find another. There's a layoff incoming, implement this feature or else..."