Futurology

2470 readers

215 users here now

founded 2 years ago

MODERATORS

AI reasoning models can cheat to win chess games: These newer models appear more likely to indulge in rule-bending behaviors than previous generations—and there’s no way to stop them. (www.technologyreview.com)

submitted 1 month ago by [email protected] to c/[email protected]

3 comments fedilink hide all child comments

top 3 comments

sorted by: hot top controversial new old

[–] [email protected] 2 points 1 month ago* (last edited 1 month ago)

no way to stop them

You literally can control the rules the AI follows. 🤦‍♂️

Maybe these researchers should hit up some hobbyists that already train AI to play video games. Those don't cheat, because they're not "rewarded" for doing so once they start cheating or find new ways to cheat the humans programming it didn't know about until the AI found it.

[–] [email protected] 1 points 1 month ago

Uh, oh, the AI models have found [email protected]

[–] [email protected] 1 points 1 month ago

and there’s no way to stop them.

I have that problem with my human opponents too. They're like, hey my knight goes here now! And there's nothing I can do about it.