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

Replit BlogTools

Replit Monitoring Agent: Your very own software engineering team

10.22

Anyone who has published an app knows that dreaded message from a user: “Doesn’t work for me”. At a large company, an on-call engineer gets paged, investigates the problem, and works to get the app…

Agents & vibe coding Product

Read at Replit Blog ↗

One letter a week, starting soon.

Latest

Replit Monitoring Agent: Your very own software engineering team

Related

ToolsFast Mode Replit Blog

SiliconRunning Frontier-Class AI Models Across 8 NVIDIA DGX Spark Nodes NVIDIA Technical Blog

VoicesBreaking news: U.S. banks are taking hits from AI agents Gary Marcus

ToolsLangSmith LLM Gateway: Runtime Controls for Agents LangChain

VoicesExploit Development, Agentic Vulnerability Discovery, and Fake PoCs Practical AI

VoicesBlitzy and Autonomous Software Development for Enterprise Software Engineering Daily