RunRL retweeted
new @runrl_com blog post: i pretrained a tiny transformer model on perfect tic tac toe moves and measured how much it affects RL compute requirements
This is the one thing we won't run RL on
Closing the RL loop. Instead of independent slop creators competing and TikTok determining the winners to show people, this turns the entire slop economy into an end-to-end differentiable monstrosity that we can point ADAM at and further hollow out the brains of young children.
3
1,044
RunRL retweeted
A cool technique from the RunRL research team: using PD controllers to balance multiobjective loss functions!
Suppose you want to train a model to give short yet relevant answers. For a given minimum level of relevance, this lets us improve on the other reward terms much more!
We've got the sauce!
Someone from @runrl_com handed me a frikin bottle of AI sauce at Defcon what even hahaha
4
418
Excited for our YC launch! If you need RL, you know where to go 😎
RunRL (@runrl_com) improves language models and agents with the power of reinforcement learning. Their customers have been able to go from 60% accuracy with Claude to 95% accuracy with RunRL.
ycombinator.com/launches/NXH…
Congrats on the launch, @dyushag and @dozenaltech!
Have you ever wondered what the funniest joke in the world is? Well, with the power of RL, we can find out!



















