Tea@programming.dev to Technology@lemmy.worldEnglish · 13 days agoReasoning models don't always say what they think.www.anthropic.comexternal-linkmessage-square6fedilinkarrow-up145arrow-down119cross-posted to: hackernews
arrow-up126arrow-down1external-linkReasoning models don't always say what they think.www.anthropic.comTea@programming.dev to Technology@lemmy.worldEnglish · 13 days agomessage-square6fedilinkcross-posted to: hackernews
minus-squareDeathsEmbrace@lemm.eelinkfedilinkEnglisharrow-up3·12 days agoIt’s basically using a reference point and they want to make it sound fancier.
It’s basically using a reference point and they want to make it sound fancier.