How Much Code Is Written by AI? Depends What You Count
Anthropic, Google, GitHub and Microsoft each give a number for AI-written code. Each counts something different. Here are the claims, units, and a repo test.
We can't find the internet
Attempting to reconnect
Something went wrong!
Attempting to reconnect
Writing · Tag
56 posts on agents, page 1 of 5. Or browse the full writing index →
Anthropic, Google, GitHub and Microsoft each give a number for AI-written code. Each counts something different. Here are the claims, units, and a repo test.
I think agents will do the CRUD in your app and the screen will shrink to charts, previews and approvals. What GitHub and Stripe ship, and where MCP fits.
Six copyable artifacts for rolling out coding agents to a dev team: review rule, AGENTS.md, handoff, controls, pilot log, and gh baselines. Vendor-neutral.
Anthropic's AI code review works because flags and fast rollback sit under it. A small team should first add checks an agent can't talk into a pass.
A fractional Chief AI Officer for a 5-20 engineer team owns the daily agent workflow, not a governance board. The four jobs and the first 30 days, week by week.
Teams built real review gates around agent-written code. The PR descriptions, design docs, and incident summaries the same agent writes pass through nothing.
DHH's Campfire benchmark has Rust far ahead of Elixir and Go. The repos show Rust got 398 commits and 16 merged performance PRs. The others got three.
The agent pipeline that runs this blog, stage by stage: where AI is safe because its output is checkable, and where a human has to stay in the loop.
Linux setup used to cost me hours per problem. Six things broke across my two machines, most fixed in minutes with an agent, and two that took longer.
Ten skills my coding agent runs to fact-check drafts and find where my posts stop reaching people, tested on my own site before I sold them.
Omarchy's new Agentic QA swarm tests every release. I run Omarchy on two machines and update within days. Here's what the design catches, and what it can't.
DHH told Rails World 2026 that hand-writing code no longer pays. What he gets right, what Basecamp 5 proves, and who owns the code nobody reads.