---
title: "Meta's LLM-written tests caught 74 privacy incidents before code shipped"
url: https://www.parallelquant.com/posts/meta-s-llm-written-tests-caught-74-privacy-incidents-before-code-shipped-9d88a6
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/11/16/meta-jittests-llm-catching-tests-privacy-bugs/
published: 2026-11-16T10:39:41.000Z
topics: ["research", "llms"]
publisher: "Parallel Quant"
---

# Meta's LLM-written tests caught 74 privacy incidents before code shipped

*2026-11-16 · Source: [MarkTechPost](https://www.marktechpost.com/2026/11/16/meta-jittests-llm-catching-tests-privacy-bugs/)*

Meta has moved Catching JiTTests into production, a system where a large language model (LLM) writes 'just-in-time' tests designed to fail on risky code changes. In the first half of 2026 it caught 74 privacy severe incidents (SEVs) before the code landed. Engineers reported a 60% true-positive rate on its flags.

**Why it matters:** Most AI coding coverage focuses on writing code faster; this is a measured result on the other side — using models to catch what humans and AI-written diffs get wrong. A 60% true-positive rate is high enough that engineers keep paying attention, which is the usual failure point for automated review tools. As more production code is AI-generated, targeted, diff-specific testing like this is likely to become a standard safety layer.

**Topics:** research, llms

---
Read the original: https://www.marktechpost.com/2026/11/16/meta-jittests-llm-catching-tests-privacy-bugs/
Canonical: https://www.parallelquant.com/posts/meta-s-llm-written-tests-caught-74-privacy-incidents-before-code-shipped-9d88a6
Published by Parallel Quant — https://www.parallelquant.com
