# Blindspot

- **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:** [Will Yeadon](https://cerebralvalley.ai/u/will_yeadon)
- **GitHub:** https://github.com/WillYeadon/meta_hackathon_blindspot
- **Demo video:** https://youtu.be/F2vEr30_2fE
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/614

Blindspot is a stress-testing tool for AI systems that review scientific calculations. 

The problem is that an AI reviewer can say that a calculation is correct without us knowing how reliable that approval really is. Blindspot tests the reviewer first, using physics problems where the correct answer is independently known. 

In the demonstration, I keep a false spectral-gap claim fixed while changing only the basis used to represent the same physical system. A cheap Meta verifier rejects the false claim reliably in several representations, but in a general rational basis its error detection falls to 46.9%. A fully dense Hadamard control remains easy, showing that density alone is not the cause.

Blindspot can then add trusted intermediate facts - in this example, the exact lowest and highest energy levels. These checkpoints restore the cheap verifier to 1,680/1,680 detected errors, with only three false alarms in 480 correct controls.

The practical use is to stress-test a proposed scientific reviewer before deployment - determine where a cheaper verifier is good enough, where trusted intermediate information helps, and where difficult cases should instead be sent to a stronger model. The current build includes the guided browser application, exact mathematical validation, saved verifier outputs, model comparisons, experiment provenance and reproducible analysis. It implements one physics case study; new scientific domains require their own truth-preserving transformations and independent correctness oracle.

## More from Meta Global AI Developer Hackathon

- [Fluminaris](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/611)
- [while(1)](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/612)
- [Ninja.TEK](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/613)
- [AgencyDiff](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/615)
- [KINETICA](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/616)
- [Alien on Earth](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/617)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/614. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt