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

Google EnvHarness Enables Self-Evolving Agents to Learn in Dynamics Environments

10.16

Google researchers open sourced EnvHarness, a framework that dynamically adapts agent-training environments to an agent's weaknesses without modifying the agent, environment, or evaluation system.

Agents & vibe coding Open weights Open Source Large language models Agents Google

Read at InfoQ AI ↗

One letter a week, starting soon.

Latest

Google EnvHarness Enables Self-Evolving Agents to Learn in Dynamics Environments

Related

LabsIntroducing Reflection Beam: an open-weight model for agentic coding on AWS AWS Machine Learning

GitHubEmployees are vibe-coding their own apps. Cloudflare open-sources Void to give IT a handle on them The New Stack

ToolsOpen SWE: An Open-Source Framework for Internal Coding Agents LangChain

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

ToolsImprove TTFT for Multi-Turn Agentic Workloads with Bi-Directional KV Transfer in vLLM vLLM Blog

ToolsDeepSeek-V4.1-Flash on vLLM: 5x Agentic Throughput Since Day 0 vLLM Blog