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 · 98 stories, +75 vs last week

Agents & vibe coding: 98 stories in seven days, +75 on the week before.

Latest

bilawalsidhu/gods-eye-view

GitHub Trending (daily)GitHubbilawalsidhu/gods-eye-view

September 14
melgarafael/DeskcommCRM

GitHub Trending (daily)GitHubmelgarafael/DeskcommCRM

September 14
asgeirtj/system_prompts_leaks

GitHub Trending (daily)GitHubasgeirtj/system_prompts_leaks

September 14
ayghri/i-have-adhd

GitHub Trending (weekly)GitHubayghri/i-have-adhd

September 14
affaan-m/ECC

GitHub Trending (weekly)GitHubaffaan-m/ECC

September 14
openai/plugins

GitHub Trending (weekly)GitHubopenai/plugins

September 14
Release v0.61.0-nightly.20260914.g9c1b0a610

Gemini CLI releasesToolsRelease v0.61.0-nightly.20260914.g9c1b0a610 <p><strong>Full Changelog</strong>: <a class="commit-link" href="https://github.com/google-gemini/gemini-cli/compare/v0.61.0-nightly.20260913.g9c1b0a610...v0.61.0-nightly.20260914.g9c1b0a610"><tt>v0.61.0-nightly.20260913

September 14
Nikkei Asia Technology

Nikkei Asia TechnologyJapanApplied Materials using AI to speed chip materials discovery, Japan chief says

September 14
Nikkei Asia Technology

Nikkei Asia TechnologyJapanFujitsu to export AI chips built on supercomputer tech to US, Asia

September 14
Nikkei Asia Technology

Nikkei Asia TechnologyJapanHuawei rolls out AI-based tourism promotion service for Xi'an region

September 14
Autonomous LLM post-training with Tunix on TPUs

Google Developers BlogLabsAutonomous LLM post-training with Tunix on TPUs Imagine going to sleep after writing a single Markdown specification and waking up to find that an A...

September 14
The Anatomy of Harness Engineering: How to Evaluate, Iterate, and Guard AI Coding Agents

Google Developers BlogLabsThe Anatomy of Harness Engineering: How to Evaluate, Iterate, and Guard AI Coding Agents While end-to-end benchmarks like SWE-bench provide broad performance scores for AI agents, they are often expensive, slow, and lack the root-cause diagnostics needed to explain exactly where an agent's logic broke down.

September 14