# Cursoe-tron

- **Event:** [The Recursive Agents Hackathon](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon)
- **When:** Sat, Oct 17 at 9:00 AM – 10:00 PM (PDT)
- **Where:** San Francisco, CA
- **Team:** [Rikin Shah](https://cerebralvalley.ai/u/rikinshah787)
- **GitHub:** https://github.com/Rikinshah787/Recursive-Hackathon
- **Demo video:** https://drive.google.com/drive/folders/1mXnp3ACBRZnbMriBy42f7qPxbgENgczY?usp=drive_link
- **Gallery:** https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/93

Cursoe-tron Stunt School is a team of AI agents on Crusoe Managed Inference that teaches itself to fly a jet-powered car through stunts in a real 3D game, and it use N+1 to learn from the task till it able to do the real task like C-loop. From a one-line goal, a spec writer (Nemotron) writes executable checks, and an independent auditor (NVIDIA Nemotron-3-Super) attacks them for loopholes. A pilot (DeepSeek-V4-Flash) writes the flight program, a verifier runs it in the game's own physics, and a watchdog catches loops and drift, then decides whether to continue, re-plan, revert, stop or ping a human. Between rounds a coach runs physics experiments, rewrites the team's playbook, and must prove every new skill with a test flight; the tests are locked, so it can't game them. A rewrite is kept only if it measurably helps. On 4 stunts the team never trained on, the hidden referee's pass count went from 0/19 flights to 5/20 (mean score +85%, p = 0.02), with zero false "done" claims. Every flight replays in the 3D game

## More from The Recursive Agents Hackathon

- [Tornado](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/90)
- [Habedevs](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/91)
- [carbon scout](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/92)
- [AIZOYA](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/94)
- [polar bears](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/95)
- [Claims-bot](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/96)

---

Markdown version of https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/93. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt