🔗 Source evidence
- Publisher
- anthropics
- Repository license
- MIT
- Last upstream push / UTC
- 2025-06-17 15:43:37
- Observed / UTC
- 2026-10-25 15:48:25
- Forks
- 166
📦 GITHUB PROJECTS / RECORDED SOURCE METADATA
hh-rlhf
Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"
anthropics/hh-rlhf⭐ 1,858 repository starsarchived
🏷️ Upstream topics
No topics supplied by the upstream repository.
🧩 Skill discovery
Repository file discovery is pending or in progress.
Repository metadata and stars describe the whole project. They do not certify quality, compatibility or safety.