hud
@hud_evals
RL environments + evals for agents | @ycombinator | we're hiring!
10 Following 2.8K Followers
Last month the #1# ranked Catan player on came to our hackathon and RL'd a model to play Catan using hud + @FireworksAI_HQ.
So we're running it back with humans – 32-player bracket at HUD HQ. Thursday July 16th
Show more
Last weekend 200+ of the best builders showed up to our Frontier RL Environments Hackathon at @ycombinator.
The idea behind HUD is simple: anything you can simulate and grade, you can improve with RL.
Teams built RL envs for autonomous farming, gene editing, city planning, world sims, and games. Some did autonomous ML research + chip design, and used HUD to RL their own open models past Opus 4.8 in-domain.
Huge thanks to our cosponsors for making it happen!
If you want to work on RL, or just be at the frontier of AI, build with us, we're hiring:
Show more
We hosted the first RSI RL Environments hackathon with @hud_evals @ycombinator and it was a blast!
We watched builders treat RL as a general purpose tool and reach for it across domains we had not anticipated.
Teams were building for chip design, gaming, robotics, and more.
Show more
Great to be at the @hud_evals hackathon @ycombinator! We met old and new friends and were really impressed by everyone working on the hard problems in “RL” (reinforcement learning and real life)!
We’re always hiring ambitious, amazing people who’d love to bring frontier RL infra to everyone. Come build with us!
Show more
some scenes from the @hud_evals × @ycombinator Frontier RL Environments Hackathon over the weekend.
24 intense, collaborative hours with 200 of the top builders in the world turning browser-use, robotics, logistics, and worldsims into environments where models can actually learn from.
a few highlights built with MiniMax M3:
Tera — zero-token browser-use RL env, #3# overall
Warehouse AI — autonomous warehouse robot fleet coordination
Atomz — Mars construction rovers in simulation
project videos in the comments.
Show more
🙌 Huge crowd for the @googledeepmind / HUD Frontier / RSI RL Environments hackathon at @ycombinator!
Cosponsors also include @ExaAILabs @modal @AnthropicAI @FireworksAI_HQ @MiniMax_AI and more. Can't wait to see what people build with @GoogleAIStudio @googlegemma!
Show more
KBBQ Robotics Arm RL Environment is on the critical path to RSI
Didn’t expect people to hack on protein folding environments for creating mythical beasts IRL…
Come join us and celebrate this weekend at HUD's Frontier/RSI RL Environments Hackathon @ the YC HQ in San Francisco.
We have an all-star cast of cosponsors such as:
@ycombinator, @modal, @GoogleDeepMind, @OpenAI, @AnthropicAI , @daytonaio, @FireworksAI_HQ, @MiniMax_AI, @SemiAnalysis_, @hillclimbai, @withprotegeai, @AntimLabs, @sixtyfourai, @ExaAILabs, and @arcprize!
Show more
HUD has been on fire, being used by some of the largest companies in the world to build RL environments.
Congrats to @hud_evals @jayendra_ram @parth220 @seeklis on the series A from @Standard_Cap!
HUD is a very interesting company, the big idea here is to provide entrepreneurs anywhere in the world the tools and infrastructure they need to get into the data business.
HUD : ScaleAI :: Airbnb : Hilton
Show more
Come join us and celebrate this weekend at HUD's Frontier/RSI RL Environments Hackathon @ the YC HQ in San Francisco.
We have an all-star cast of cosponsors such as:
@ycombinator, @modal, @GoogleDeepMind, @OpenAI, @AnthropicAI , @daytonaio, @FireworksAI_HQ, @MiniMax_AI, @SemiAnalysis_, @hillclimbai, @withprotegeai, @AntimLabs, @sixtyfourai, @ExaAILabs, and @arcprize!
Show more
Announcing HUD's RL environments for RSI hackathon! 🎉
Join us June 20–21 in SF if you're interested in RL and want to push the frontier forward!
(w/$100,000+ in prizes and compute credits 👀)
Show more
