GitHub · Python
BrandeisPatrick/openbench
Reverse-engineer the RL reward an LLM was trained on — from black-box agentic coding behavior alone. Tested on Opus 4.8, Fable 5, GPT-5.5.
- Stars
- 9
- Forks
- 0
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: agentic-ai, ai-agents, ai-alignment, benchmark, claude, coding-agents, fable5, gpt, interpretability, inverse-reinforcement-learning
Latest data point: Nov 21, 2026 · 9 stars · 0 forks