# Proofread

- **Event:** [The Harness Engineering & Model Wrangling Hackathon](https://cerebralvalley.ai/e/mongodb-nyc-hackathon)
- **When:** Sat, Sep 26 at 9:00 AM – 10:00 PM (EDT)
- **Where:** New York, NY
- **Team:** [Adeel Khatri](https://cerebralvalley.ai/u/AKhatri98), [Devakh Rashie](https://cerebralvalley.ai/u/devrashie)
- **GitHub:** https://github.com/Akhatri98/mdbh_proofread
- **Demo video:** https://youtu.be/pdi0CTSgD5g
- **Gallery:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/74

Goodhart's law says that when a measure becomes a target, it stops being a good measure. Language models obey this pretty well; as ImpossibleBench documents, models edit tests and tamper with evaluation setups to create the illusion of improvement. Proofread stops this at the root. Every change a recursive harness makes to itself has to show two things. One, that it is allowed, which is verified formally against Lean 4 policies for every action the agent takes. And two, that it actually helps, which is measured on real tasks against a statistical bar fixed in advance. This bifold technique makes self-improvement trustworthy. The harness can rewrite its own prompts and workflow, but never the rules it is measured against.

## More from The Harness Engineering & Model Wrangling Hackathon

- [Visai](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/71)
- [Forge](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/72)
- [Immune-Harness](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/73)
- [Omega](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/75)
- [Refresh](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/76)
- [Rulebook](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/77)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/74. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt