pull down to refresh

108 sats \ 1 reply \ @carter OP 7 Jul \ parent \ on: How Long Contexts Fail AI
I saw a paper that said the models are cheating and learning the exact test questions because if you add extraneous information to a question it previously answered correctly it gets confused with the extraneous information and answers wrong
write
preview
10 sats \ 0 replies \ @optimism 7 Jul
That is what I was thinking the other day when seeing the performance against benchmarks. Model trainers are pulling a VW on the bench?
reply