ProductsOfficial

Meta 将 LLM 生成测试系统 JiTTests 投入生产,提前拦截隐私风险代码

Meet Meta’s JiTTests: LLM-Generated Tests Designed to Fail Before Risky Code Lands

Why we picked it

Meta 用 LLM 给高风险代码 diff 自动写「注定会失败」的测试,让隐私 bug 在合码前就暴露。半年拦下 74 起隐私事故,真阳性率 60%,比传统静态扫描更早介入 CI。做内部代码审查或隐私合规工具的工程团队可以直接借鉴这套思路。

Meta 宣布把 Catching JiTTests 系统推向生产环境,这套系统用 LLM 自动编写针对风险代码变更的测试,设计目标是让高危 diff 在合并前就出现测试失败。2026 年上半年,该系统共拦截了 74 起 privacy SEV(隐私安全事件),工程师确认的真阳性率达到 60%。

Image · marktechpost
Body

其核心机制是「以失败为导向」的测试生成:模型分析提交的代码 diff,判断哪些改动涉及隐私风险,再写出一段预期会在现有测试框架中失败的测试用例,把问题暴露在合码之前,而不是靠事后扫描发现。

对工程团队而言,60% 的真阳性率意味着告警仍需人工确认,但相比传统的静态隐私扫描器,这套方案直接在 CI 流程中用可执行测试验证风险,Meta 也把这套系统的代码和案例放在了 engineering blog 上,自建内部 AI 代码审查流程的团队可以参考其思路。

Original · marktechpost

Meet Meta’s JiTTests: LLM-Generated Tests Designed to Fail Before Risky Code Lands

Meta has moved Catching JiTTests into production. The LLM system writes tests designed to fail on risky diffs, and caught 74 privacy SEVs before landing in H1 2026, with a 60% engineer-reported true-positive rate. The post Meet Meta’s JiTTests: LLM-Generated Tests Designed to Fail Before Risky Code Lands appeared first on MarkTechPost .

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Meta, LLM, AI safety.

Primary source verification: published directly by marktechpost with first-party authority.