Lifecoach5000@lemmy.world to Technology@lemmy.worldEnglish · 21 days agoChatGPT 'got absolutely wrecked' by Atari 2600 in beginner's chess match — OpenAI's newest model bamboozled by 1970s logicwww.tomshardware.comexternal-linkmessage-square194fedilinkarrow-up11arrow-down10cross-posted to: retrogaming@lemmy.worldtechnology@beehaw.org
arrow-up11arrow-down1external-linkChatGPT 'got absolutely wrecked' by Atari 2600 in beginner's chess match — OpenAI's newest model bamboozled by 1970s logicwww.tomshardware.comLifecoach5000@lemmy.world to Technology@lemmy.worldEnglish · 21 days agomessage-square194fedilinkcross-posted to: retrogaming@lemmy.worldtechnology@beehaw.org
minus-squareIsaamoonKHGDT_6143@lemmy.ziplinkfedilinkEnglisharrow-up0·21 days agoThey used ChatGPT 4o, instead of using o1 or o3. Obviously it was going to fail.
minus-squarewizardbeard@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up0·edit-221 days agoOther studies (not all chess based or against this old chess AI) show similar lackluster results when using reasoning models. Edit: When comparing reasoning models to existing algorithmic solutions.
They used ChatGPT 4o, instead of using o1 or o3.
Obviously it was going to fail.
Other studies (not all chess based or against this old chess AI) show similar lackluster results when using reasoning models.
Edit: When comparing reasoning models to existing algorithmic solutions.