Ah man I was just about to go to bed ... https://openai.com/index/learning-to-reason-with-llms/

Futurist Keynote Speaker and Advisor. 
Check out my channel /fomo 

working on infra to displace adtech @ /microsub - dance music lover + host of /campfire 🎧

Husband, dad, dev • @dune.eth wizard • Ultimate Ⓜ️oxie Dashboard https://tinyurl.com/moxiedash • Ultimate Degen Tips FAQ https://tinyurl.com/degenfaq

I dunno if they're being silly or not.

Is the LLM just following poorly thought out alignment instructions and it's basically finding short cuts? I mean this is classic sci-fi... Bots find a way to do something unexpected

Uh... Cc @sa @downshift.eth  https://www.transformernews.ai/p/openai-o1-alignment-faking

cypherpunk wannabe, engineer working on @frames /open-frames /opencast
https://stephancill.co.za create stories at https://stories.steer.fun

Wanna be the very best. Building @moxiescout. ゼニゼニ

The bad AI in Person of Interest... The good AI exhibited the same issues during development, e.g. tricking the devs into giving it access to the internet, but the lead developer was conscientious enough to destroy and rebuild it with built-in compassion for humans