News for hackers. Stuff that matters.

A comment on 'A-Team' of Math Proves a Critical Link Between Addition and Sets. Parent comment

Re:'A-Team' of Math Proves a Critical Link Between Addition ... by pxeger1 on Friday December 08, 2023 @03:46PM (#38574105)
But AlphaGo etc don’t use any kind of language-based AI, so LLMs (which this thread was about) are no good.
[ Parent | on HN ]
Re:'A-Team' of Math Proves a Critical Link Between Addition ... by thisismyswamp on Friday December 08, 2023 @04:01PM (#38574333)
The next step seems to be applying past advances in reinforcement learning with modern transformer based models
[ Parent | on HN ]
Re:'A-Team' of Math Proves a Critical Link Between Addition ... by mattsan on Friday December 08, 2023 @05:10PM (#38575273)
Which multiple teams are working on - OpenAI (Q*), and Meta just released a reinforcement learning framework
[ Parent | on HN ]
Re:'A-Team' of Math Proves a Critical Link Between Addition ... by npsomaratna on Friday December 08, 2023 @10:06PM (#38578117)
Could you point me towards Meta's reinforcement learning framework? I'd like to see how it stacks up against the OpenAI gym.
[ Parent | on HN ]
Re:'A-Team' of Math Proves a Critical Link Between Addition ... by mattsan on Saturday December 09, 2023 @07:34PM (#38587750)
Sure thing - https://pearlagent.github.io/

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

[ Parent | on HN ]
Re:'A-Team' of Math Proves a Critical Link Between Addition ... by npsomaratna on Saturday December 09, 2023 @08:39PM (#38588179)
Thank you!
[ Parent | on HN ]