# Indie

- **Event:** [Meta Global AI Developer Hackathon](https://cerebralvalley.ai/e/meta-ai-developer-hackathon)
- **When:** Oct 26, 12:00 PM – Nov 4, 9:00 PM (EST)
- **Where:** Online
- **Team:** [Leo Pimentel](https://cerebralvalley.ai/u/Dokutoshi)
- **GitHub:** https://github.com/dokutoshi/zydah
- **Demo video:** https://youtu.be/Teazn0pXRHQ
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5182

Leo Pimentel, ML researcher.

If you run LLM-as-judge panels you’ve hit this: three models disagree, and you have to turn that into one decision. Averaging the scores hides the disagreement — you can’t tell “they agree it’s a 7” from “two said 9, one said 3.”

Zydah keeps the disagreement. Each judge returns a belief mass over {pass, partial, fail} plus explicit mass on “don’t know.” Conflict between judges isn’t averaged out, it accumulates as ignorance, and you get an interval instead of a point. Wide interval → escalate to a human. Narrow and high → commit.

It’s Dempster-Shafer theory with Yager’s combination rule, which is the part that makes conflict visible instead of normalizing it away.

## More from Meta Global AI Developer Hackathon

- [MailboxAI](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5179)
- [Physical prompting](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5180)
- [Si se puede: Porque somos panas](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5181)
- [NeoHuman](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5183)
- [Ludavela](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5184)
- [Centaur Video](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5185)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5182. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt