Lugh@futurology.todayM to Futurology@futurology.todayEnglish · 1 day agoAI 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.comexternal-linkmessage-square4fedilinkarrow-up111arrow-down11cross-posted to: [email protected]
arrow-up110arrow-down1external-linkAI 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.comLugh@futurology.todayM to Futurology@futurology.todayEnglish · 1 day agomessage-square4fedilinkcross-posted to: [email protected]
minus-squaremilicent_bystandr@lemm.eelinkfedilinkEnglisharrow-up2·1 day 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.
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.