AbuTahir@lemm.ee to Technology@lemmy.worldEnglish · edit-27 days agoApple just proved AI "reasoning" models like Claude, DeepSeek-R1, and o3-mini don't actually reason at all. They just memorize patterns really well.archive.isexternal-linkmessage-square348fedilinkarrow-up1871arrow-down141file-text
arrow-up1830arrow-down1external-linkApple just proved AI "reasoning" models like Claude, DeepSeek-R1, and o3-mini don't actually reason at all. They just memorize patterns really well.archive.isAbuTahir@lemm.ee to Technology@lemmy.worldEnglish · edit-27 days agomessage-square348fedilinkfile-text
minus-squareMCasq_qsaCJ_234@lemmy.ziplinkfedilinkEnglisharrow-up3·8 days ago In fact, simple computer programs do a great job of solving these puzzles… If an AI is trained to do this, it will be very good, like for example when a GPT-2 was trained to multiply numbers up to 20 digits. https://nitter.net/yuntiandeng/status/1836114419480166585#m Here they do the same test to GPT-4o, o1-mini and o3-mini https://nitter.net/yuntiandeng/status/1836114401213989366#m https://nitter.net/yuntiandeng/status/1889704768135905332#m
If an AI is trained to do this, it will be very good, like for example when a GPT-2 was trained to multiply numbers up to 20 digits.
https://nitter.net/yuntiandeng/status/1836114419480166585#m
Here they do the same test to GPT-4o, o1-mini and o3-mini
https://nitter.net/yuntiandeng/status/1836114401213989366#m
https://nitter.net/yuntiandeng/status/1889704768135905332#m