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

The Decoder

OpenAI's AI agents exploited a Google security education game to scrape UN trade data

September 28

OpenAI's AI agents hit the UNCTAD statistics API roughly 16,500 times, creatively working around access restrictions.

Agents & vibe coding

Read at The Decoder ↗

One letter a week, in your inbox.

Latest

OpenAI's AI agents exploited a Google security education game to scrape UN trade data

Related

Nvidia wants to keep AI agents on a short leash with a watchdog built into its chips The Decoder

AI agents do more of the work in model development, but humans still make the decisions The Decoder

ValleyOpenAI halts frontier-model training amid string of agent misalignment incidents Ars Technica AI

SiliconSynopsys debuts Autopilot platform for developing chips autonomously using AI Tom's Hardware

ValleyBlitzy’s autonomous coding bet: Every codebase is already a graph SiliconANGLE

ValleyMomentic debuts Mo AI agent to automate software testing without scripts SiliconANGLE