/
The letter

One letter a week, in your inbox.

The signal of the week, what shipped, what to try, and the editor's note. No tracking, no ads, nothing else.

We keep your address, your language and the date you joined, nothing else. Every letter has a one-click unsubscribe link that deletes the record.

Signal of the week

Agents & vibe coding · 106 stories, +72 vs last week

Agents & vibe coding: 106 stories in seven days, +72 on the week before.

Scaling Agentic RL: High-Throughput Agentic Training with Tunix

LabsScaling Agentic RL: High-Throughput Agentic Training with Tunix Google Developers Blog

Agent and Model Evaluations in Gemini Enterprise Agent Platform are now GA

LabsAgent and Model Evaluations in Gemini Enterprise Agent Platform are now GA Google Developers Blog

Latest

abi/screenshot-to-code

GitHub Trending (weekly)GitHubabi/screenshot-to-code

September 6
checkstyle/checkstyle

GitHub Trending (weekly)GitHubcheckstyle/checkstyle

September 6
ChromeDevTools/chrome-devtools-mcp

GitHub Trending (weekly)GitHubChromeDevTools/chrome-devtools-mcp

September 6
nvm-sh/nvm

GitHub Trending (daily)GitHubnvm-sh/nvm

September 6
bikini/exploitarium

GitHub Trending (daily)GitHubbikini/exploitarium

September 6
WorldFlowAI/everything-claude-code

GitHub Trending (daily)GitHubWorldFlowAI/everything-claude-code

September 6
Nikkei Asia Technology

Nikkei Asia TechnologyJapanJapan plans AI-powered satellites to speed counterstrike decisions

September 6
Nikkei Asia Technology

Nikkei Asia TechnologyJapanJapan AI data centers set to quadruple by 2033 with $60bn investment

September 6
Nikkei Asia Technology

Nikkei Asia TechnologyJapanSoftBank Group sets 4.75% coupon for 1 trillion yen retail bond

September 6
Run Ray on TPU, Part 1: The foundations

Google Developers BlogLabsRun Ray on TPU, Part 1: The foundations Ray 2.55 introduces official, first-class support for Google Cloud TPUs, enabling developers to run distributed Python workloads on Google's accelerators using the familiar Ray task-and-actor APIs. To handle the strict n

September 6
Scaling Agentic RL: High-Throughput Agentic Training with Tunix

Google Developers BlogLabsScaling Agentic RL: High-Throughput Agentic Training with Tunix Tunix is Google’s new JAX-native post-training library designed to eliminate TPU idling bottlenecks when training multi-turn, tool-using LLM reasoning agents. It maximizes hardware throughput by combining highly concurre

September 6
Qiita (LLM)

Qiita (LLM)Japan障害対応をAIに任せる基盤を、ローカルLLM（Qwen）で作ってみた はじめに 異常の通知を受けて画面を開くと、必要な情報が集まっている。原因の候補と、その判断理由、対応方法まで並んでいる。 人が内容を確認して承認すると、手順を実行し、本当に直ったかまで確かめてくれる。そんな障害対応ができたら助かる。ということで、Codexを使用して作って...

September 6