bisonbear | Dark Hacker News

user:	bisonbear
created:	September 17, 2025
karma:	63
about:	Building evals for AI coding agents, on your repo. Tests pass. Nobody's measuring the rest. http://stet.sh email ben@stet.sh

1.	I compared Opus 4.8 vs. Opus 5 on 25 of my tasks to see what the difference was(stet.sh) 18 points by bisonbear 22 hours ago \| 0 comments
2.	I compared 5 popular token saving methods in Codex and found that none delivered(stet.sh) 2 points by bisonbear 28 days ago \| 0 comments
3.	I ran Sonnet 5 vs. Opus 4.8 head to head on 24 tasks to see what's different(stet.sh) 1 points by bisonbear 42 days ago \| 0 comments
4.	I evaluated GLM 5.2 against the frontier on tasks from real repos(stet.sh) 2 points by bisonbear 67 days ago \| 2 comments
5.	I benchmarked Opus 4.8 vs. GPT 5.5 on 2 open source repos(stet.sh) 3 points by bisonbear 84 days ago \| 0 comments
6.	I used autoresearch to improve my AGENTS.md, measured against real tasks(stet.sh) 8 points by bisonbear 91 days ago \| 7 comments
7.	A brief investigation into the GPT-5.5 regression claims(stet.sh) 1 points by bisonbear 99 days ago \| 0 comments