- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
不玩晦涩不搞少数派的 AI 入门圣经,从学生到工程师都能轻松掌握。涵盖神经网络到大模型、顶层设计到微观原理、工程实现到算法基础。 学完后,大家能彻底看懂为什么下一 token 预测这个看似不起眼的能力可以改变世界,也能发现原来 AI 并没有想象中那么神秘、那么高不可攀。 Let's just beat it !
01Result
origin-brain/beat-ai ↗origin-brain/beat-ai AI coding statistics: 72.4%
One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.
Agent share by month
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-03 | 68.8% | 170 |
| 2026-05 | 83% | 153 |
| 2026-06 | 56.5% | 23 |
| 2026-07 | 0% | 4 |
| 2026-08 | 0% | 5 |
Peak month: 83%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 257 | 72.4% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
4ddc427eon GitHubchore: stop tracking .claude directoryClaude Code148ebed7on GitHubai-insights: re-translate 4 articles (2026-06-04) via hybrid flowClaude Code8073c918on GitHubdocs(plans): evaluate Chrome built-in Translator API for material-pipelineClaude Code
04Method
What entered the denominator
The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.
Exclusion ledger
| Commits in window | 355 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −0 |
| Considered | 355 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
Run the same detector locally.
Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.
npx qmmit-cli origin-brain/beat-ai