cm0002@lemmy.world to Technology@lemmy.worldEnglish · 1 day 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-square123fedilinkarrow-up1344arrow-down137
arrow-up1307arrow-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 · 1 day agomessage-square123fedilink
minus-squarePennomi@lemmy.worldlinkfedilinkEnglisharrow-up7·1 day agoThis is great stuff. If we can properly understand these “flows” of intelligence, we might be able to write optimized shortcuts for them, vastly improving performance.
minus-squareLarmyOfLone@lemm.eelinkfedilinkEnglisharrow-up2arrow-down1·14 hours agoBetter yet, teach AI to write code replacing specific optimized AI networks. Then automatically profile and optimize and unit test!
This is great stuff. If we can properly understand these “flows” of intelligence, we might be able to write optimized shortcuts for them, vastly improving performance.
Better yet, teach AI to write code replacing specific optimized AI networks. Then automatically profile and optimize and unit test!