schizoidman@lemm.ee to Technology@beehaw.orgEnglish · 2 days agoCutting-edge Chinese “reasoning” model rivals OpenAI o1—and it’s free to downloadarstechnica.comexternal-linkmessage-square9fedilinkarrow-up133arrow-down10file-textcross-posted to: [email protected][email protected][email protected]
arrow-up133arrow-down1external-linkCutting-edge Chinese “reasoning” model rivals OpenAI o1—and it’s free to downloadarstechnica.comschizoidman@lemm.ee to Technology@beehaw.orgEnglish · 2 days agomessage-square9fedilinkfile-textcross-posted to: [email protected][email protected][email protected]
minus-squarejarfil@beehaw.orglinkfedilinkarrow-up1·12 hours agoSo… when plugged into a system with ability to access the Internet and/or execute local commands… will its reasoning look better or worse than the high deception showed by o1? https://www.apolloresearch.ai/research/scheming-reasoning-evaluations
So… when plugged into a system with ability to access the Internet and/or execute local commands… will its reasoning look better or worse than the high deception showed by o1?
https://www.apolloresearch.ai/research/scheming-reasoning-evaluations