Hacker Newsnew | past | comments | ask | show | jobs | submit | Danau5tin's submissions login

1. Scaling Coding-Agent RL to 32x H100s. 160% Improvement on Stanford's TBench (github.com/danau5tin) 2 points by Danau5tin 40 days ago | past | 1 comment 2. Show HN: Multi-Agent-Coder Is #12 on Stanford's TBench. Beats Claude Code (github.com/danau5tin) 5 points by Danau5tin 3 months ago | past | 1 comment 3. My weekend project accidentally beat Claude Code – #12 on Stanford's TBench (github.com/danau5tin) 2 points by Danau5tin 3 months ago | past | 2 comments 4. Show HN: Terminal-Bench-RL: Training long-horizon terminal agents with RL (github.com/danau5tin) 125 points by Danau5tin 4 months ago | past | 12 comments

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: