Timely_Jellyfish_2077@programming.dev to Technology@lemmy.worldEnglish · 3 months agoReasoning failures highlighted by Apple research on LLMsappleinsider.comexternal-linkmessage-square59fedilinkarrow-up1233arrow-down111
arrow-up1222arrow-down1external-linkReasoning failures highlighted by Apple research on LLMsappleinsider.comTimely_Jellyfish_2077@programming.dev to Technology@lemmy.worldEnglish · 3 months agomessage-square59fedilink
minus-squareRimu@piefed.sociallinkfedilinkEnglisharrow-up8·edit-23 months 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/share/670af65d-da08-800f-8ad4-c67782ee5477 https://chatgpt.com/share/670af672-45dc-800f-ac91-cc2811fa89c7 https://chatgpt.com/share/6709e80b-e5a8-800f-90d0-1af3418675ef
minus-squaretinsukE@lemmy.worldlinkfedilinkEnglisharrow-up4arrow-down1·3 months agoI wouldn’t doubt that LLMs got some special input to deal with the specific examples of this paper, or similar enough.
minus-squarealienanimals@lemmy.worldlinkfedilinkEnglisharrow-up1·2 months agoThis is just improving LLMs, but with more steps.
minus-squareA_A@lemmy.worldlinkfedilinkEnglisharrow-up3·3 months agoErrors from your links like this : Unable to load conversation 670a…6ed2c
minus-squareA_A@lemmy.worldlinkfedilinkEnglisharrow-up3·3 months ago“… So, Mary has 190 kiwifruit.” nice 😋🥝
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/share/670af65d-da08-800f-8ad4-c67782ee5477
https://chatgpt.com/share/670af672-45dc-800f-ac91-cc2811fa89c7
https://chatgpt.com/share/6709e80b-e5a8-800f-90d0-1af3418675ef
I wouldn’t doubt that LLMs got some special input to deal with the specific examples of this paper, or similar enough.
This is just improving LLMs, but with more steps.
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 😋🥝