cm0002@lemmy.world to Technology@lemmy.worldEnglish · 3 days agoPeople are using Super Mario to benchmark AI nowtechcrunch.comexternal-linkmessage-square20fedilinkarrow-up187arrow-down17
arrow-up180arrow-down1external-linkPeople are using Super Mario to benchmark AI nowtechcrunch.comcm0002@lemmy.world to Technology@lemmy.worldEnglish · 3 days agomessage-square20fedilink
minus-squarehendrik@palaver.p3x.delinkfedilinkEnglisharrow-up3arrow-down1·3 days agoAnd with machine code, you got to keep track of what’s in the stack, CPU registers, … to make a sense of what the code and the next branch command does. It’s completely unalike processing human language. LLMs aren’t really set up to do it.
And with machine code, you got to keep track of what’s in the stack, CPU registers, … to make a sense of what the code and the next branch command does. It’s completely unalike processing human language. LLMs aren’t really set up to do it.