Built RL for long-horizon agents – tested on 32x H100s but too poor to train from Hacker News on 2025-07-29 11:12 (#6YZ1J) Comments
Show HN: Terminal-Bench-RL: Training Long-Horizon Terminal Agents with RL from Hacker News on 2025-07-29 11:12 (#6YZ3R) Comments
