AI · Article
Meta Uses AI-Written Tests to Catch 74 Privacy Bugs Before Release
AI 매터스 ·

At a glance
Meta said it used AI to automatically write test code that checks code changes for bugs, and that this caught 74 serious privacy-related bugs in the first half of 2026 before release. Meta also reported that serious privacy incidents fell by 20% over the same period.
Key points
- Meta applied a method called Catching JiTTests to its internal systems.
- The method uses an LLM (large language model) to create tests for each code change that reveal changed behavior.
- Riskier code changes are picked overnight, and failed tests are ranked by how likely they are to be real bugs.
- 589 engineers have responded to alerts, and 60% of the checked results turned out to be real problems.
Why it matters
It shows how AI can help find software bugs before they affect users' personal data.
Original source
메타, AI 테스트로 상반기 개인정보 중대 버그 74건 사전 차단
AI 매터스 · Nov 18, 16:01 KST
Read on AI 매터스 ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to AI 매터스.
Other coverage
More from this field
- Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST - Leaky AI Supply Chain Exposes Secret User Data at Alarming Rate
A research test sent nearly two million prompts with fake but working secrets through a network of AI services to see where they ended up. Many of the secrets were stolen, and attackers used them to reach cloud accounts. The results point to weak protection of customer data along the chain.
Ars Technica · Nov 21, 05:59 KST - OpenAI Shows How to Claim a Shopify Store in ChatGPT
This video shows how to claim your business in ChatGPT by connecting your Shopify store. You can start in Business Hub or the Shopify App Store. After connecting, you can manage your business information to control how your store appears in ChatGPT.
OpenAI 공식 YouTube · Nov 21, 05:48 KST