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

Weights & BiasesTools

AI Guardrails for LLM applications and Agents: Mechanisms, trade-offs, and implementation patterns

08.25

A comprehensive guide to what AI Guardrails actually do, where they cost you, and when to skip them entirely.

Agents & vibe coding Articles Community Posts Safety and scoring

Read at Weights & Biases ↗

One letter a week, starting soon.

Latest

AI Guardrails for LLM applications and Agents: Mechanisms, trade-offs, and implementation patterns

Related

ResearchAgentHands: Generating interactive hand gestures for spatially grounded agent conversations in XR Google Research

ResearchGranite 4.2 brings native reasoning to enterprise agents IBM Research

ToolsHow Cursor beat Git's scalability shortcomings DevClass

ResearchSOP-Bench: A new benchmark for evaluating AI agents on real business procedures Amazon Science

EuropeSlack Code taps into collective vibe, puts AI agents into the group chat The Register AI

EuropeAgentic Search. More accurate and efficient results from your AI systems. Mistral AI