cyrano@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · edit-21 month agoGPT-4.5openai.comexternal-linkmessage-square3fedilinkarrow-up125arrow-down117file-textcross-posted to: hackernews
arrow-up18arrow-down1external-linkGPT-4.5openai.comcyrano@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · edit-21 month agomessage-square3fedilinkfile-textcross-posted to: hackernews
minus-squarecygnus@lemmy.calinkfedilinkEnglisharrow-up20arrow-down1·1 month agoThose charts are hilarious: wow, it gives the right answer 62.5% of the time and only makes up completely false answers 37.1% of the time! It’s like Russian roulette, but worse!
minus-squareolympicyes@lemmy.worldlinkfedilinkEnglisharrow-up8·1 month agoIf you play Russian roulette with two bullets like a real man, then this model is about the same outcome!
Those charts are hilarious: wow, it gives the right answer 62.5% of the time and only makes up completely false answers 37.1% of the time! It’s like Russian roulette, but worse!
If you play Russian roulette with two bullets like a real man, then this model is about the same outcome!
deleted by creator