bot@lemmy.smeargle.fansMB to Hacker News@lemmy.smeargle.fans · 7 months agoAlice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in LLMsarxiv.orgexternal-linkmessage-square2fedilinkarrow-up14arrow-down10file-textcross-posted to: localllama@sh.itjust.works
arrow-up14arrow-down1external-linkAlice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in LLMsarxiv.orgbot@lemmy.smeargle.fansMB to Hacker News@lemmy.smeargle.fans · 7 months agomessage-square2fedilinkfile-textcross-posted to: localllama@sh.itjust.works
minus-squareBumpingFuglies@lemmy.ziplinkfedilinkarrow-up1·edit-27 months agoAfter a quick glance, this appears to be the question that LLMs can’t answer: Alice has N brothers and she also has M sisters. How many sisters does Alice’s brother have?
After a quick glance, this appears to be the question that LLMs can’t answer:
It’s wonderfully severe too.