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

1. Show HN: Randomly switching between LMs at every step boosts SWE-bench score (swebench.com) 5 points by lieret 63 days ago | past | 1 comment 2. GPT-5 on SWE-bench: Cost and performance deep-dive (mini-swe-agent.com) 4 points by lieret 75 days ago | past | 3 comments 3. Show HN: New SWE-bench leaderboard compares LMs without fancy agent scaffolds (swebench.com) 2 points by lieret 83 days ago | past 4. Show HN: Mini-swe-agent achieves 65% on SWE-bench in 100 lines of python (github.com/swe-agent) 7 points by lieret 89 days ago | past | 4 comments

Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10 Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: