41
Punishing AI doesn't stop it from lying and cheating — it just makes it hide better, study shows
(www.livescience.com)
this post was submitted on 20 Mar 2025
41 points (100.0% liked)
Artificial Intelligence
197 readers
34 users here now
Chat about and share AI stuff
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
It's a optimization game. If the punishment doesn't offset the reward, then the incentive is to get better at cheating.
I've seen plenty of videos of random college kids training LLMs to play video games and getting the AI to stop cheating is like half the project. But they manage it, eventually. It's laughable that these big companies and research firms can't quite figure it out.