- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Post-training with Tinker
01Result
thinking-machines-lab/tinker-cookbook ↗thinking-machines-lab/tinker-cookbook AI coding statistics: 73.8%
A small group is using agents. Adoption has spread beyond one person but is not project-wide.
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 |
|---|---|---|
| 2026-02 | 40% | 25 |
| 2026-03 | 85.5% | 124 |
| 2026-04 | 90.5% | 74 |
| 2026-05 | 57.1% | 28 |
| 2026-06 | 50% | 22 |
| 2026-07 | 50% | 16 |
| 2026-08 | 0% | 6 |
| 2026-09 | 66.7% | 6 |
Peak month: 90.5%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 219 | 72.8% |
| Cursor Agent | Anysphere | 4 | 1.3% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
8f33aaa1on GitHubAdd validation AUC to the forecasting results tables (#939)Claude Code1f962edaon GitHubAdd GLM-5.3 to the forecasting recipe and tune defaults / align with epochClaude Codeb739bed0on GitHubMake GLM-5.3 train the turn terminator on every assistant turn (#932)Claude Code4ce6b363on GitHubMigrate cookbook off the 2026-06-12 model lineup update (#718)Cursor Agent46e08026on GitHubClarify Tinker concurrency guidance for agents (#729)Cursor Agent5306f45bon GitHubAlign Kimi K2.6 revision pin (#697)Cursor Agent
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 | 322 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −21 |
| Considered | 301 |
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 thinking-machines-lab/tinker-cookbook