Timely_Jellyfish_2077@programming.dev to Technology@lemmy.worldEnglish · 1 month agoReasoning failures highlighted by Apple research on LLMsappleinsider.comexternal-linkmessage-square55fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkReasoning failures highlighted by Apple research on LLMsappleinsider.comTimely_Jellyfish_2077@programming.dev to Technology@lemmy.worldEnglish · 1 month agomessage-square55fedilink
minus-squareRimu@piefed.sociallinkfedilinkEnglisharrow-up0·1 month agoI tried it myself (changing the name and changing the values) but lost interest after 3 attempts and always getting the right answer: https://chatgpt.com/c/6709e7a0-21c0-800f-87e1-da5f3dc9f309 https://chatgpt.com/c/670ae37b-cf94-800f-9bc8-e1aeaed6ed2c https://chatgpt.com/c/670ae42a-1c74-800f-87f0-fac54f24a7ce
minus-squareA_A@lemmy.worldlinkfedilinkEnglisharrow-up0·1 month agoErrors from your links like this : Unable to load conversation 670a…6ed2c
minus-squareRimu@piefed.sociallinkfedilinkEnglisharrow-up0·1 month agoSorry! I’ve updated my links now.
minus-squareA_A@lemmy.worldlinkfedilinkEnglisharrow-up0·1 month ago“… So, Mary has 190 kiwifruit.” nice 😋🥝
minus-squaretinsukE@lemmy.worldlinkfedilinkEnglisharrow-up0·1 month agoI wouldn’t doubt that LLMs got some special input to deal with the specific examples of this paper, or similar enough.
I tried it myself (changing the name and changing the values) but lost interest after 3 attempts and always getting the right answer:
https://chatgpt.com/c/6709e7a0-21c0-800f-87e1-da5f3dc9f309
https://chatgpt.com/c/670ae37b-cf94-800f-9bc8-e1aeaed6ed2c
https://chatgpt.com/c/670ae42a-1c74-800f-87f0-fac54f24a7ce
Errors from your links like this :
Unable to load conversation 670a…6ed2c
Sorry! I’ve updated my links now.
“… So, Mary has 190 kiwifruit.”
nice 😋🥝
I wouldn’t doubt that LLMs got some special input to deal with the specific examples of this paper, or similar enough.