Review economics
karpathy/nanoGPT
Read from the 45 most recently merged pull requests ·
Not enough merged pull requests on both sides yet to compare how they land in review.
≥2%
Attributed
a floor
1
Attributed PRs
44
Other PRs
45
Read
Attributed — the latest 1
The rest — the latest 5
#420 Move enc to gloabal namespace to fix #371
0 reviews · 45.9d to merge
#487 Update README.md
0 reviews · 6.4d to merge
#116 Minor change to allow using ddp with exclusive process mode
0 reviews · 11h to merge
#463 Fixing eval path in README
0 reviews · 71.4d to merge
#429 Open "shakespeare" data in UTF-8 in "prepare.py"
0 reviews · 32.8d to merge
How this was measured
2% of merged commits carry agent attribution — a floor, not the share; tools that only complete code inline leave no commit trail, so the unattributed side includes AI-assisted work.
Detected: Devin.
“Attributed” means a commit carried an agent’s signature — a co-author trailer, an agent commit identity, or an agent bot account. Tools that only complete code inline leave no such mark, so the other column is “rest”, not “human-written”. Full method and its limits
The badge reads this repo’s current report, so it follows the number.
Tell me when this moves
We re-read karpathy/nanoGPT weekly and email only when the number changes materially.
Read your own repos
This one is public. For a private repo, run the same read locally through your own GitHub credentials — nothing is installed and nothing is sent to us.
npx @ambera/review-taxWant this continuously on karpathy/nanoGPT — each pull request paired to the task it came from, and the work graded from its review loop rather than its diff size? Claim this repo in Forge
Browse every repo people have read · Read a different repository