Meta's LLM-generated failing tests catch 74 privacy SEVs, cutting incidents 20%
Meta_Engineers · x · 2026-11-10
Meta's engineering team details JiTTests (Just-in-Time Tests): instead of using AI to review code faster like a human, LLMs generate executable tests designed to fail, proving behavioral changes in a diff before it lands. After a year of research, it's now part of Meta's infrastructure.
- 589 engineers have used it, reporting a 60% true-positive rate
- In H1 2026 it caught 74 privacy SEVs at the diff stage, lowering overall privacy SEV occurrences by 20%
- Published as an FSE 2026 paper, "Just-in-Time Catching Test Generation at Meta," alongside an engineering blog post
More from coding & agent
- Dev spins up thousands of computer-use agent VMs with live terminal streaming — wavefnx · 2026-11-10
- Cursor discloses tampered Claude Code extensions attempting persistent SSH backdoors — thione · 2026-11-10
- Perplexity CEO says Teammates usage grows daily, three updates ship this week — AravSrinivas · 2026-11-10
- feedthejim takes over ChatGPT/Codex Web & Desktop infra group at OpenAI — Dimillian · 2026-11-10
- Solo dev builds 1400s Venetian trading game with 47 cities, almost entirely with Claude Code — Harvan29 · 2026-11-10
- Open-source Rewind for X extension logs every post you scroll past so refreshes stop losing good tweets — dotey · 2026-11-10