A repository for collecting LLM agent challenges, hypotheses / methods, and experimental results. For science!
active 2025-07-05 → 2025-07-18 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 16 days from 2025-07-05 to 2025-07-22. Pushes: 4 total, peak 2 in a day. Pull requests: 4 total, peak 2 in a day. Issues: 7 total, peak 1 in a day. Comments: 15 total, peak 5 in a day. Stars: 1 total, peak 1 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 |
|---|---|---|---|---|
| shcv | 7 | 1 | 1 | 4 |
| Brads3290 | 5 | 0 | 0 | 2 |
| OtterEngineer | 3 | 0 | 0 | 1 |
| maker95 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#9shcv2025-07-22 21:42
- Issue comment#9shcv2025-07-19 04:04Experiment: TodoMVC Race
- Issue comment#9Brads32902025-07-19 03:26Experiment: TodoMVC Race
- Pull request#9shcv2025-07-19 01:37
- Issue comment#7OtterEngineer2025-07-19 00:59General Problem: Claude is terrible at design and should never be allowed to make a design decision.
- Pull request#8shcv2025-07-19 00:48
- Issue comment#8jbmiller102025-07-18 22:20Add TodoMVC specs
- Issue comment#8Brads32902025-07-18 22:11Add TodoMVC specs
- Issue comment#8shcv2025-07-18 22:07Add TodoMVC specs
- Issue comment#8Brads32902025-07-18 21:50Add TodoMVC specs
- Issue comment#8jbmiller102025-07-18 21:50Add TodoMVC specs
- Pull request#8shcv2025-07-18 03:58
- Issue comment#1shcv2025-07-16 02:33Clauding...
- Issue#1shcv2025-07-16 02:33Clauding...
- Issue comment#7shcv2025-07-16 02:32General Problem: Claude is terrible at design and should never be allowed to make a design decision.
- Issue comment#5shcv2025-07-15 21:25General problem: agents making up silly requirements
- Issue comment#4shcv2025-07-15 21:20Hypothesis: Claude performs worse if you're mean to it
- Issue#7OtterEngineer2025-07-11 18:47General Problem: Claude is terrible at design and should never be allowed to make a design decision.
- Issue comment#5OtterEngineer2025-07-11 18:46General problem: agents making up silly requirements
- Issue#5Brads32902025-07-09 07:21General problem: agents making up silly requirements
- Issue comment#4Brads32902025-07-08 00:57Hypothesis: Claude performs worse if you're mean to it
- Issue#4Brads32902025-07-08 00:55Hypothesis: Claude performs worse if you're mean to it
- Issue#3OtterEngineer2025-07-07 04:31Troubleshooting Methods
- Issue comment#2Brads32902025-07-06 10:09Measuring outcomes
- Issue#2Brads32902025-07-06 09:53Measuring outcomes
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1 stars here means stars gained during the window, not the repo's star count.