HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
1.
▲
Show HN: Terminal-Bench-RL: Training long-horizon terminal agents with RL
github.com/Danau5tin
12 comments
a year ago
Danau5tin
125 points
2.
▲
Show HN: Multi-Agent-Coder Is #12 on Stanford's TBench. Beats Claude Code
github.com/Danau5tin
1 comment
10 months ago
Danau5tin
5 points
3.
▲
My weekend project accidentally beat Claude Code – #12 on Stanford's TBench
github.com/Danau5tin
2 comments
10 months ago
Danau5tin
2 points
4.
▲
Scaling Coding-Agent RL to 32x H100s. 160% Improvement on Stanford's TBench
github.com/Danau5tin
1 comment
8 months ago
Danau5tin
2 points