AbuTahir@lemm.ee to TechnologyEnglish · edit-211 个月前Apple 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-square339linkfedilinkarrow-up1876arrow-down142file-textcross-posted to: apple_enthusiast
arrow-up1834arrow-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 TechnologyEnglish · edit-211 个月前message-square339linkfedilinkfile-textcross-posted to: apple_enthusiast
minus-squareKnock_Knock_Lemmy_InlinkfedilinkEnglisharrow-up5arrow-down2·edit-211 个月前You were starting a new argument. Let’s stay on topic. The paper implies “Reasoning” is application of logic. It shows that LRMs are great at copying logic but can’t follow simple instructions that haven’t been seen before.
You were starting a new argument. Let’s stay on topic.
The paper implies “Reasoning” is application of logic. It shows that LRMs are great at copying logic but can’t follow simple instructions that haven’t been seen before.