Review economics
ml-explore/mlx
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took 2.4× the reviews submitted of the rest.
≥5%
Attributed
a floor
7
Attributed PRs
93
Other PRs
100
Read
Attributed — the latest 5
#3894 docs: document the reduced-precision float32 default and MLX_ENABLE_TF32
4 reviews · 12.1d to merge
#3292 Fix vmap + floor_divide: preserve integer dtype
2 rounds · 8 reviews · 3.1d to merge
#3873 Fix JIT preamble header filter matching project paths containing "Xcode"
1 reviews · 38h to merge
#3875 Round MLX_SDPA_BLOCKS up to a multiple of 32
1 reviews · 36h to merge
#3647 Fix CPU gather transposing column-contiguous slices
2 reviews · 28.0d to merge
The rest — the latest 5
#3943 Support head dimension 96 in Metal full attention
1 reviews · 6.3d to merge
#3976 Fix mx.remainder floored-mod for float16/bfloat16 on CPU
1 round · 2 reviews · 2.8d to merge
#3904 Pad 2D conv input channels to reach the specialized Metal kernel
1 reviews · 12.3d to merge
#3970 Template Metal complex scalar lanes
3 reviews · 3.4d to merge
#3975 python: fix bfloat16 buffer format itemsize mismatch
7 reviews · 2.7d to merge
How this was measured
5% 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; reads 100 of 2016 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code.
“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 ml-explore/mlx 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 ml-explore/mlx — 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