cm0002@lemmy.world to Technology@lemmy.worldEnglish · 3か月前Anthropic has developed an AI 'brain scanner' to understand how LLMs work and it turns out the reason why chatbots are terrible at simple math and hallucinate is weirder than you thoughtwww.pcgamer.comexternal-linkmessage-square170fedilinkarrow-up1416arrow-down155
arrow-up1361arrow-down1external-linkAnthropic has developed an AI 'brain scanner' to understand how LLMs work and it turns out the reason why chatbots are terrible at simple math and hallucinate is weirder than you thoughtwww.pcgamer.comcm0002@lemmy.world to Technology@lemmy.worldEnglish · 3か月前message-square170fedilink
minus-squareNatanael@infosec.publinkfedilinkEnglisharrow-up5·edit-23か月前Not, but I’d do 75*10 + 75*4, then subtract the extra. The LLM method of doing it with multiple numbers without proper interpolation though makes it extra weird
Not, but I’d do 75*10 + 75*4, then subtract the extra.
The LLM method of doing it with multiple numbers without proper interpolation though makes it extra weird