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
55 posts on engineering, 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.
Microsoft 365 was still degraded 21 hours in. Some coverage tied it to the exit offer. Nobody has left under it yet, but the advisory shows what recovery takes.
Plug sets cache-control on every response, so a check for a missing header never matches. How I fixed it on this site and what each page sends now.
Exit code 137 means SIGKILL, and memory is only one sender. On one Phoenix project I hit it twice: a compile that ran out of RAM, and a binary that never ran.
Claude Code's scratchpad lives in /tmp, which is RAM on my Omarchy box. 7.1 GB of worktrees froze it. The fix, what it still misses, and a checklist.
Seven weeks after my first install, I'm keeping Omarchy. What worked on an RTX 3070 desktop, what broke, and what 4.5 RC changes.
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.
Anthropic built Scion and moved its monorepo off git in five months. Here is why a small team shouldn't copy it, and where to spend the attention instead.
This site has no database. Here's how a future-dated post stays invisible until its timestamp, and the three places the gate gave the wrong answer anyway.
Teams built real review gates around agent-written code. The PR descriptions, design docs, and incident summaries the same agent writes pass through nothing.
Posting every week is a tool, not the goal. What predicts a public body of work is never fully stopping, one deep topic, and the right things to measure early.
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.