@[email protected] to [email protected]English • 3 months agoCutting-edge Chinese “reasoning” model rivals OpenAI o1—and it’s free to downloadarstechnica.comexternal-linkmessage-square8fedilinkarrow-up130cross-posted to: [email protected][email protected][email protected]
arrow-up130external-linkCutting-edge Chinese “reasoning” model rivals OpenAI o1—and it’s free to downloadarstechnica.com@[email protected] to [email protected]English • 3 months agomessage-square8fedilinkcross-posted to: [email protected][email protected][email protected]
minus-square@[email protected]linkfedilink1•3 months 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