Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-03-20 · source-backed
A large-scale empirical study of 278,790 code review conversations across 300 open-source GitHub projects found human reviewers require 11.8% more back-and-forth rounds when reviewing AI-generated code versus human-written code. First quantification of how agentic coding changes review dynamics at scale. AI-generated code generates more scrutiny, not less — with implications for team velocity calculations and PR tooling design.
Each link below shares sources, entities, or timing with this story.
Simon Willison has been writing software for over 25 years. He's one of the most disciplined, transparent engineers in the Python ecosystem. And yesterday he published an essay admitting he no longer reviews every line of code that Claude Code generates for his production proj...
Every team's answer to "how do we control agent output quality" is human review. A study submitted September 5 says that gate loosens on its own. Researchers analyzed 11,429 code reviews and found approval rates for AI-authored changes climb with repeated exposure: 30.5% early...
The Claude Code source leak was the biggest story in developer tools this week. But the most important analysis didn't come from the people picking through feature flags and Easter eggs. It came from Sebastian Raschka, who read the 512,000 lines of leaked TypeScript and reache...
Opsera found that AI-assisted workflows produce pull requests 48-58% faster, but those PRs wait 4.6x as long to be reviewed compared to human-written code. Speed gains from AI coding are being negated by human review capacity constraints — creating demand for AI-assisted revie...
Repo-To-Skill (arXiv 2609.02749, submitted September 2) makes the argument I've been circling for months and then supplies the controlled experiment. The claim is that what research agents lack is operational know-how, not reasoning capability, and that this know-how already e...
This is the paper of the week. arXiv 2607.28871 introduces BSG-VA, which replays every validation command an agent runs across three code states: the original buggy code (B), the candidate patch (S), and the gold developer fix (G). If a test passes in all three states, it neve...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.