1 stories
hackbot.dad visit →
Stories 1 (0 evaluated) Avg HRCB ND
Avg SETL ND Avg Conf ND
Poster Karma 2 avg Submitters 1
1. METR's SWE-bench analysis shows us taste isn't verifiable (hackbot.dad)
2 points by dixie_flatline 8 days ago | 0 comments | skipped