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

Apple Machine Learning ResearchResearch

SCLATE: A Substrate for Continual-Learning Agent Training and Evaluation

September 30

Continual-learning agents are systems of models, harnesses, and memory operating over long multi-session horizons.

Agents & vibe coding Research Funding & deals

Read at Apple Machine Learning Research ↗

One letter a week, in your inbox.

Latest

SCLATE: A Substrate for Continual-Learning Agent Training and Evaluation

Related

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

LabsOpen TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning Hugging Face Blog

JapanClaude Code、同梱のclaude-apiスキルに新コマンド「build-eval」と「hillclimb」を追加 ——評価の作成からプロンプト・モデル設定の調整まで gihyo.jp

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

VoicesChroma and Agentic Retrieval Software Engineering Daily

SiliconHow SWE-Serve Exposes the Gap Between Local Tests and Live Serving NVIDIA Technical Blog