News for hackers. Stuff that matters.
Re:Court report detailing ChatGPT's involvement with a recen... by unyttigfjelltol on Wednesday December 31, 2025 @02:24PM (#46447379)
The chats are more useful when it doesn't confirm my bias. I used LLMs less when they started just agreeing with everything I say. Some of my best experiences with LLMs involve it resisting my point of view.

There should be a dashboard indicator or toggle to visually warn when the bot is just uncritically agreeing, and if you were to asked it to "double check your work" it would immediately disavow its responses.

Re:Court report detailing ChatGPT's involvement with a recen... by aspaviento on Wednesday December 31, 2025 @03:14PM (#46447826)
I usually ask it to challenge its last response when it acts too agreeable.
Re:Court report detailing ChatGPT's involvement with a recen... by duskwuff on Thursday January 01, 2026 @10:43PM (#46461176)
> There should be a dashboard indicator or toggle to visually warn when the bot is just uncritically agreeing

I would be very surprised if it were possible to reliably detect this. In fact, I'm not certain it's a distinction which can meaningfully be made.