Textbook on reinforcement learning from human feedback
active 2025-03-29 → 2026-08-07 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 497 days from 2025-03-29 to 2026-08-07. Pushes: 509 total, peak 12 in a day. Pull requests: 218 total, peak 9 in a day. Issues: 17 total, peak 2 in a day. Comments: 116 total, peak 7 in a day. Stars: 569 total, peak 64 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| natolambert | 720 | 504 | 163 | 35 |
| zafstojano | 46 | 0 | 19 | 16 |
| chatgpt-codex-connector[bot] | 44 | 0 | 0 | 26 |
| github-actions[bot] | 15 | 0 | 0 | 15 |
| Athe-kunal | 13 | 0 | 3 | 9 |
| yassersouri | 4 | 0 | 4 | 0 |
| zoranmedic | 4 | 0 | 1 | 1 |
| casinca | 3 | 0 | 2 | 1 |
| kiankyars | 3 | 0 | 3 | 0 |
| sagarhonnungar | 2 | 0 | 2 | 0 |
| galenballew | 2 | 0 | 2 | 0 |
| theoxo | 2 | 0 | 1 | 1 |
| afqueiruga | 2 | 0 | 2 | 0 |
| adsingh-64 | 2 | 0 | 1 | 1 |
| ShotaKaji5207 | 2 | 0 | 1 | 1 |
| vutrung96 | 2 | 0 | 1 | 1 |
| emmanuel-ferdman | 2 | 0 | 2 | 0 |
| kashif | 2 | 0 | 1 | 1 |
| lancerts | 2 | 0 | 1 | 1 |
| ofou | 2 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#469natolambert2026-06-30 23:42
- Pull request#460natolambert2026-06-28 20:39
- Pull request#439natolambert2026-06-20 02:18
- Pull request#452natolambert2026-06-15 22:41
- Pull request#442segyges2026-06-05 23:17
- Pull request#435natolambert2026-06-04 20:28
- Pull request#327natolambert2026-05-30 23:10
- Pull request#420natolambert2026-05-13 01:13
- Pull request#416zafstojano2026-05-10 15:42
- Issue comment#413natolambert2026-05-10 00:50[codex] Document and harden arXiv build
- Pull request#412natolambert2026-05-10 00:40
- Pull request#411natolambert2026-05-10 00:31
- Pull request#410natolambert2026-05-10 00:09
- Pull request#409natolambert2026-05-09 23:40
- Pull request#407natolambert2026-05-09 23:06
- Pull request#405natolambert2026-05-09 22:31
- Pull request#397Athe-kunal2026-05-05 20:40
- Issue comment#393zafstojano2026-05-04 07:21[CODE] fix(rejection sampling): updating for policy_gradients refactor
- Issue comment#393casinca2026-05-03 21:04[CODE] fix(rejection sampling): updating for policy_gradients refactor
- Issue comment#385Athe-kunal2026-04-29 02:09[WIP] Add DAPO to loss
- Pull request#390natolambert2026-04-29 01:43
- Pull request#389yassersouri2026-04-29 01:26
- Pull request#386yassersouri2026-04-29 01:24
- Issue comment#385Athe-kunal2026-04-27 01:00[WIP] Add DAPO to loss
- Issue comment#385zafstojano2026-04-26 09:20[WIP] Add DAPO to loss
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 569 stars here means stars gained during the window, not the repo's star count.