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

InfoQ AIGitHub

GKE Pod Snapshots Cut Model Load Times, and Move the Work to Snapshot Lifecycle Management

September 27

Google has published benchmarks for GKE Pod snapshots, reporting up to 89% lower startup latency and a 70B model loading in 37 seconds.

Research Cloud Containers Performance Kubernetes

Read at InfoQ AI ↗

One letter a week, in your inbox.

Latest

GKE Pod Snapshots Cut Model Load Times, and Move the Work to Snapshot Lifecycle Management

Related

GitHubPresentation: Adaptive Recommenders in the Real World: Inference, Evals, and System Design InfoQ AI

GitHubFrom Agent Authorization to AI Production Evaluation: QCon AI New York 2026 InfoQ AI

GitHubPresentation: APIs for Agents: Rethinking API Programs in the MCP Era InfoQ AI

Japan続・LLMに"扁桃体"を埋め込んでみた記録 — Agentic Misalignment編 Zenn (AI)

GitHubClaude Opus 5.5 vs. Opus 5 on reasoning tasks: Cheaper, faster, but not better The New Stack

GitHubTuning a Server for Benchmarking Lobsters