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

Hugging Face BlogLabs

ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model

10.20

A Blog post by IBM Research on Hugging Face

Models & releases

Read at Hugging Face Blog ↗

One letter a week, starting soon.

Latest

ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model

Related

LabsWelcome Beam: a 501B open model you can own, customize, and scale Hugging Face Blog

LabsWelcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta Hugging Face Blog

LabsRun fast, private agents on-device with LFM2.5-24B-A2B Hugging Face Blog

LabsTransformers now runs llama.cpp quants Hugging Face Blog

JapanCodexでGPT-6 Astraを選ぶ判断軸とAPI移行チェック Zenn (AI)

GitHubDeepSeek open-sources the inference engine behind its API. And Huawei gets equal billing with Nvidia. The New Stack