OmegaMouse@pawb.social to 196@lemmy.blahaj.zone · 17 days agoYou got it! rulepawb.socialexternal-linkmessage-square23fedilinkarrow-up114arrow-down10
arrow-up114arrow-down1external-linkYou got it! rulepawb.socialOmegaMouse@pawb.social to 196@lemmy.blahaj.zone · 17 days agomessage-square23fedilink
minus-squareTʜᴇʀᴀᴘʏGⒶʀʏ@lemmy.blahaj.zonelinkfedilinkarrow-up0·edit-217 days agoI had a 20 questions app I on my iPod touch like 15yrs ago that guessed it correctly every time Edit: I just tried it with GPT4 (via perplexity) and it managed to guess carrot on question #10, but it took 22 questions to get human
minus-squareTar_Alcaran@sh.itjust.workslinkfedilinkarrow-up1·17 days agoBecause 20q is basically a big decision tree. And LLMs don’t make decisions, they generate output based on what other output looks like.
I had a 20 questions app I on my iPod touch like 15yrs ago that guessed it correctly every time
Edit: I just tried it with GPT4 (via perplexity) and it managed to guess carrot on question #10, but it took 22 questions to get human
Because 20q is basically a big decision tree. And LLMs don’t make decisions, they generate output based on what other output looks like.