The name is the button.

An agent writes the code now, and a human thumb hovers over Accept all a hundred times a day. The honest question of this decade is what, exactly, you just accepted. So I read the diff.

Eight years as a backend engineer in Stockholm, back in Tokyo since 2023, and I still ship something small most nights, usually badly. My one rule: the only real review of a model is the thing you built with it. That is why there is no leaderboard on this site.

Around a hundred and forty sources come through — the labs' own posts, the papers, the tools, the runtimes and languages nobody is watching yet, the chip under the demo, and the newsletters people actually forward. What is moving gets counted so the week reads at a glance, and every few days I explain one mechanism in plain words.

A story here is a headline, a short excerpt, one image and the link to whoever wrote it. We never reproduce the post; the images belong to their authors. A post written in Japanese appears in Japanese, exactly as it was published, and the link goes to the original.

— Yuki Halvorsen, Tokyo

← Accept All Archive

Meta EngineeringLabs

Catching Bugs Before They Land: JiTTesting’s Human-on-the-Loop Approach at Full Scale

10.29

Over the last year we’ve been sharing our work leveraging large language models to catch bugs on the fly — a novel approach we call Catching Just-in-Time Tests (JiTTests).

Read at Meta Engineering ↗

One letter a week, starting soon.

Latest

Catching Bugs Before They Land: JiTTesting’s Human-on-the-Loop Approach at Full Scale

More from Meta Engineering on Accept All

LabsMeta Andromeda: Powering the Next Generation of Ads Retrieval Through Model-System Co-Design Meta Engineering

LabsPrivacyLib: Privacy Controls at the Data Access Boundary Meta Engineering

LabsPython Typing Survey 2026: AI Tools and the Shifting Checker Landscape Meta Engineering

LabsMeta Networking at the 2026 OCP Global Summit: Open Innovation for Scale-Up, Scale-Out, and Scale-Across AI Networks Meta Engineering

LabsGenRecs Tokenization: Transforming Ads Recommendation at Meta with Stable Model Vocabulary Meta Engineering

LabsThe Thin Orchestrator: How We Made Our AI Agents More Reliable by Giving the Router Less to Do Meta Engineering