Hacker Newsnew | past | comments | ask | show | jobs | submit | JoshPurtell's submissionslogin
1.
Engine-Bench: Benchmarking Coding Agents on TCG Game Engine Tasks (github.com/joshuapurtell)
2 points by JoshPurtell 3 days ago | past | discuss
2.
Verify long-horizon tasks with GEPA on the judge (usesynth.ai)
4 points by JoshPurtell 31 days ago | past

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

Search: