Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
Dive into FrontierHarness Eval: Claude Code cost 5.6× for the same pass rate (runta.com)
6 points by ADD-SP 1 day ago | past | 3 comments
FrontierHarness Eval benchmark. Pi is on the Pareto (runta.com)
3 points by redman25 8 days ago | past | discuss
Agents Aren't Software (runta.com)
3 points by jinqueeny 25 days ago | past
Runta SSH access for agent runtimes (runta.com)
6 points by shiqimei 28 days ago | past
When a long-running agent crashes, what does recovery mean? (runta.com)
5 points by guanlan 35 days ago | past

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

Search: