cm0002@lemmy.world to Technology@lemmy.worldEnglish · 2 days agoAnthropic 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-square158fedilinkarrow-up1407arrow-down155
arrow-up1352arrow-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 · 2 days agomessage-square158fedilink
minus-squarekkj@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up7·1 day agoBut you wouldn’t multiply, say, 74*14 to get the answer.
minus-squareNatanael@infosec.publinkfedilinkEnglisharrow-up4·edit-222 hours agoNot, 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
minus-squareManticore@lemmy.nzlinkfedilinkEnglisharrow-up4·edit-223 hours agoI might. Then I can subtract 74 to get 74*14, and subtract 28 to get 72*13. I don’t generally do that to ‘weird’ numbers, I usually get closer to multiples of 5, 9, 10, or 11. But a computer stores information differently. Perhaps it moves closer to numbers with simpler binary addresses.
But you wouldn’t multiply, say, 74*14 to get the answer.
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
I might. Then I can subtract 74 to get 74*14, and subtract 28 to get 72*13.
I don’t generally do that to ‘weird’ numbers, I usually get closer to multiples of 5, 9, 10, or 11.
But a computer stores information differently. Perhaps it moves closer to numbers with simpler binary addresses.