# Meta says AI-generated tests caught 74 serious privacy bugs before production

_Published Thursday, October 29, 2026 at 12:21 PM EDT · AI, Security · Latest · Tier 2 — Notable_

![Meta says AI-generated tests caught 74 serious privacy bugs before production — Primary](https://engineering.fb.com/wp-content/uploads/2026/10/Catching-JiTTests-Hero-3.png)

Meta reported that its AI-generated testing system helped catch 74 serious privacy bugs before code reached production in the first half of 2026, lowering privacy incident occurrence by 20% during that period. The company published results from its production deployment of Catching Just-in-Time Tests.

The system runs overnight on spare capacity, targeting code changes judged risky. Language models generate executable tests to expose behavioral changes, while model-based assessments and deterministic rules filter likely false positives before contacting engineers.

Meta said 589 engineers, representing 64% of its outreach, engaged with the system and reported a 60% true-positive rate. The approach requires more computational steps than language-model code review.

## Sources

- [Engineering at Meta](https://engineering.fb.com/2026/10/29/security/catching-bugs-before-they-land-jittestings-human-on-the-loop-approach-at-full-scale/)

---
Canonical: https://techandbusiness.org/newswire/Y2wBqumb7lfuCIzEzDbHin
Published: 2026-10-29T16:21:48.681Z
Story chronology: 2026-10-29T16:00:12.000Z
Retrieved: 2026-10-29T18:47:08.226Z
Publisher: Tech & Business (techandbusiness.org)