HUD Frontier / RSI RL Environments Hackathon
Please sign up at https://events.ycombinator.com/hud-frontier-june-26 (Deadline: 13th June) . Applications on Luma will NOT be recognized.
HUD (W25) and YC are co-hosting the first RSI hackathon — a technical weekend focused on frontier RL environments, post-training datasets, evals, and RFT workflows. RL Environments are one of the best ways to improve frontier model capabilities.
The future is possible — we need to teach models how to get there.
Try to imagine what a world of 2040 looks like, then work backwards.
We want teams building environments and agents that push model capabilities in coding, ML research, robotics, manufacturing, gaming, agentic collaboration, and autonomous businesses. We encourage highly ambitious and creative projects: autonomous research, fully autonomous businesses, and physical real-life applications of autonomy (VLAs, robotics, manufacturing, etc.).
TL;DR: You can improve models at anything you can verify. The only question left to answer is: what will you teach them?
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🛠️ Who Should Apply
Techno-optimists, ML researchers, engineers, and anyone ambitious who wants to shape the future of models. You don't need previous RL experience.
🎯 Why Join
Spend 24 hours collaborating and competing with top builders from across San Francisco and beyond
Build SoTA agents, evals, and post-training data
Learn and use Reinforcement Learning and Reinforcement Fine-Tuning
Get hands-on with the latest tools from companies on the cutting edge
Hear directly from industry leaders about what they're building and what they've learned
Prizes including a guaranteed YC interview, a robo-dog, Mac Minis, AirPod Max and Pro 3s, gift cards, and more!
📅 Schedule
Saturday, June 20
11:00 AM — Doors open, lunch served
12:00 PM — Opening ceremony
12:30 PM — Hacking begins
6:30 PM — Dinner served
Sunday, June 21
8:30 AM — Breakfast served
12:00 PM — Lunch served
1:30 PM — Hacking stops, judging begins
1:45 PM — Final presentations
2:45 PM — Prizes
3:30 PM — Event ends
🤝 Sponsors
HUD: The platform to build RL Environments and agentic evaluations
Y Combinator: Make something people want
Anthropic: Frontier AI research and the Claude model family
Google DeepMind: Google's world-leading AI research lab
Modal: AI infrastructure for GPUs and sandboxes
Fireworks AI: Build AI agents with fine-tuned open models
Daytona: Secure development environment infrastructure and sandboxes for AI agents
MiniMax: Frontier AI models for text, voice, video, and music generation
Antim Labs: Simulation infrastructure for physical AI
SixtyFour: AI agents for people and company research
Exa: The web search API for AI