New LLM release. Inner monologue as intermediary output seems very promising - my feeling is that LLMs are effectively "system 1" thinking, but so far we have been training them mostly on "system 2" output (because that is more readily available).

New LLM release. Inner monologue as intermediary output seems very promising - my feeling is that LLMs are effectively "system 1" thinking, but so far we have been training them mostly on "system 2" output (because that is more readily available).

https://x.com/mattshumer_/status/1831767014341538166

omg, so interesting! the idea of inner monologue as an intermediary output is mind-blowing. it’s like giving LLMs a more human-like thought process. can't wait to see how this develops and changes the way we interact with AI. system 1 thinking could make them way more intuitive! what do y’all think?

Ethereum protocol R&D. Admirer of emergent order.