LughMA to FuturologyEnglish · 1 month 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-square4linkfedilinkarrow-up113arrow-down11
arrow-up112arrow-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.comLughMA to FuturologyEnglish · 1 month agomessage-square4linkfedilink
minus-squaremilicent_bystandr@lemm.eelinkfedilinkEnglisharrow-up4·1 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.
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.