In recent months I've heard of several teams with an interesting policy: each pull request should be no more than a few files, and no more than a certain number of lines (say 500). And do just one thing and do it well. And be easy for a human to review. And be fully tested by the test suite.
Agent pull requests are everywhere. Here's how to review them.
A practical guide to reviewing agent-generated pull requests: what to look for, where issues hide, and how to catch technical debt before it ships.
Project 2025 Tracker
A comprehensive, community-driven initiative to track the implementation of Project 2025's policy proposals
GitHub Stacked PRs
Break large changes into small, reviewable, stacked pull requests with first-class GitHub support.
February 2026 Global Dialogues Survey | Windfall Trust
Windfall Trust is bringing together tech pioneers, economists, and policymakers to plan for a future where no one is left behind.
100R — permacomputing 101
This is a blog post based on a transcript of a talk by Devine that took place on August 11th for Critical Signals 2025. Watch the video version on (YouTube). The slideshow presentation was made using Adelie.
100R — permacomputing 101
This is a blog post based on a transcript of a talk by Devine that took place on August 11th for Critical Signals 2025. Watch the video version on (YouTube). The slideshow presentation was made using Adelie.
The AI Engineering Report 2026: The AI Acceleration Whiplash - Ten Takeaways
What two years of telemetry data from 22,000 developers reveals about AI's real impact on developer productivity, code quality, and business risk in 2026.
2026 Idea Dump
AF just went on its annual summer break in June, and I spent the most glorious two weeks up north for some much needed, off-the-grid time.
sunil pai on Twitter / X
suspect we're a few months (if not weeks!) away from a model that's good enough for tool calling / small enough to be shipped on devices/OSes by default these already exist in research space, but hitting mainstream /consumer space is when it'll really take off. apps will be…— sunil pai (@threepointone) September 8, 2025
State of AI 2025: 100T Token LLM Usage Study | OpenRouter
Read OpenRouter's 2025 State of AI report — an empirical 100 trillion token study of real LLM usage, model trends, and developer insights.
Coldtea: ship at agent speed. Break nothing.
Coldtea runs the full SDLC. Agents test every pull request on a real device, watch production, and file what breaks before your users find it.
FOSDEM 2026 - FOSDEM 2026 Call for Participation
Proposals for developer rooms and main track talks for FOSDEM 2026 can now be submitted!
AI vs human code gen report: AI code creates 1.7x more issues
We analyzed 470 open-source GitHub pull requests, using CodeRabbit’s structured issue taxonomy and found that AI generated code creates 1.7x more issues.
Agents Done Right: A Framework Vision for 2026
Agents choke on context, loop on failures, and dump walls of code for review. It's time to rethink the architecture.
State of AI Report 2025
The State of AI Report analyses the most interesting developments in AI. Read and download here.
A recap of #atmosphereconf 2026 as well as an overview of why I'm spending my very limited free time in my life betting on ATProto (and why I think you should, too!) This isn't just for developers. This is for everyone. brittanyellich.com/atproto/
Why I'm betting on ATProto (and why you should, too)
brittanyellich.com