On: 'A-team' of math proves a critical link between addition and sets

[pxeger1]

But AlphaGo etc don’t use any kind of language-based AI, so LLMs (which this thread was about) are no good.

[thisismyswamp → pxeger1]

The next step seems to be applying past advances in reinforcement learning with modern transformer based models

[mattsan → thisismyswamp]

Which multiple teams are working on - OpenAI (Q*), and Meta just released a reinforcement learning framework

[npsomaratna → mattsan]

Could you point me towards Meta's reinforcement learning framework? I'd like to see how it stacks up against the OpenAI gym.

[mattsan → npsomaratna]

Sure thing - https://pearlagent.github.io/

HN post here: https://news.ycombinator.com/item?id=38564526

[npsomaratna → mattsan]

Thank you!