# RSI

- **Event:** [AI Engineer World's Fair Hackathon 2026](https://cerebralvalley.ai/e/aiewf-hackathon-2026)
- **When:** Jun 27 at 9:00 AM – Jun 28 at 5:00 PM (PDT)
- **Where:** San Francisco, CA
- **Team:** [S G](https://cerebralvalley.ai/u/whatdhack)
- **GitHub:** https://github.com/whatdhack/recursive-self-improvement
- **Demo video:** https://github.com/whatdhack/recursive-self-improvement/blob/main/rsi_explainer.mp4
- **Gallery:** https://cerebralvalley.ai/e/aiewf-hackathon-2026/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/aiewf-hackathon-2026/hackathon/gallery/3

A Recursive Self-Improving AI that fine-tunes its own weights from failures — meta agent, target agent, LoRA, repeat.

## More from AI Engineer World's Fair Hackathon 2026

- [Test Submission](https://cerebralvalley.ai/e/aiewf-hackathon-2026/hackathon/gallery/1)
- [Cowboys](https://cerebralvalley.ai/e/aiewf-hackathon-2026/hackathon/gallery/2)
- [shake](https://cerebralvalley.ai/e/aiewf-hackathon-2026/hackathon/gallery/4)
- [field-ratchet: a recursively self-improving AI for PCB design.](https://cerebralvalley.ai/e/aiewf-hackathon-2026/hackathon/gallery/5)
- [Atlantis](https://cerebralvalley.ai/e/aiewf-hackathon-2026/hackathon/gallery/6)
- [Nidra](https://cerebralvalley.ai/e/aiewf-hackathon-2026/hackathon/gallery/70)

---

Markdown version of https://cerebralvalley.ai/e/aiewf-hackathon-2026/hackathon/gallery/3. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt