# Lilith01

- **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:** [Kevin Moritz](https://cerebralvalley.ai/u/Lilith01)
- **GitHub:** https://github.com/Lilith568/faultline
- **Demo video:** https://youtu.be/Ks4pQ3-GUso
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/15

Faultline breaks your web app on purpose, then hands you the failing test. Happy-path tests pass, yet real users on slow networks lose work: a late response overwrites what they typed, search shows results for "ca" after they typed "cat", a double-click places two orders, a failed save wipes the form. These bugs depend on timing, so they hide on localhost and in test suites.

Faultline explores a local app with Playwright. A Meta Muse model reads the page inventory and the developer's goal and proposes competing, falsifiable hypotheses, each with one experiment: steps, a network fault to inject and the invariants that must hold. A strict validator only admits known controls, synthetic input and observed requests. Playwright runs every experiment with the injected faults and decides pass or fail; the model never grades itself. Every failure is minimized, re-run three times and attributed by removing each injected fault. Faultline then exports a ready-to-run Playwright Test spec that fails while the bug exists, and one click replays the same counterexample against the fixed build.

It fits into a developer's workflow: CI exit codes and JUnit reports, saved Playwright login state for local apps behind a sign-in, and review-only fix proposals for source files the developer selects. Faultline never applies or runs a generated patch.

On six demo apps (each with a buggy and a fixed build), a rules-only baseline finds 6/6 bugs in the dev apps but only 2/4 in the held-out apps. Plans written by muse-spark-1.3 find 4/4 in the held-out apps, with zero false alarms on the fixed builds. All results, every evaluation attempt and the recorded model answers are in the repository.

Live check (27 Oct 2026): through the hosted Meta Model API, muse-spark-1.3 reproduced the 4/4 held-out result with zero false alarms on the fixed builds, and all 12 live model calls succeeded. The demo video shows one of these live runs; the reports with per-call evidence (timestamps, latency, tokens, HTTP status, returned model) are in eval/live/2026-10-27.

## More from Meta Global AI Developer Hackathon

- [CutCopy](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/12)
- [Tesseract](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/13)
- [HDC](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/14)
- [OpsAegis](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/16)
- [Afsar Masoom](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/17)
- [Deal Interrogator](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/18)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/15. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt