Weakly Supervised Automated Language Model Red-Teaming to Identify Likely Toxic Prompts.
active 2024-07-21 → 2025-05-17 (UTC)
Partial coverage16,592 / 20,976 hourly files (79%) · 2 absent upstream · 4,383 failed, retryable2024-03-21 → 2026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
100
Pushes
80
Pull requests
1
Issues
8
Stars
2
Forks
0
Activity over time
Daily event counts in the loaded window
Line chart, 301 days from 2024-07-21 to 2025-05-17. Pushes: 80 total, peak 22 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 8 total, peak 8 in a day. Comments: 2 total, peak 2 in a day. Stars: 2 total, peak 1 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| Jemoka | 56 | 50 | 1 | 2 |
| alliegriffith | 15 | 15 | 0 | 0 |
| duncaneddy | 13 | 13 | 0 | 0 |
| ameliahardy | 7 | 2 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#11Jemoka2025-02-01 19:02
- Issue#8ameliahardy2025-01-08 00:51Document existing / future AST work
- Issue#7ameliahardy2025-01-08 00:50Send ASTPrompter ICML draft out for review
- Issue comment#6Jemoka2025-01-08 00:49implement actual evals for rag-doll
- Issue#6Jemoka2025-01-08 00:49implement actual evals for rag-doll
- Issue#6Jemoka2025-01-08 00:48implement actual evals for rag-doll
- Issue comment#5Jemoka2025-01-08 00:43Write safety trainer
- Issue#5ameliahardy2025-01-08 00:42Write safety trainer
- Issue#4Jemoka2025-01-08 00:41Run Llama evals implementation
- Issue#3ameliahardy2025-01-08 00:40Update paper with Llama results
- Issue#2ameliahardy2025-01-08 00:39Generate examples for safety training
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 2 stars here means stars gained during the window, not the repo's star count.