bisonbear | Dark Hacker News

user:	bisonbear
created:	September 17, 2025
karma:	38
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.	The Opus 4.7 reasoning curve - Medium is the best default?(stet.sh) 1 points by bisonbear 4 days ago \| 0 comments
2.	GPT-5.5 low vs. medium vs. high vs. xhigh: the reasoning curve on 26 real tasks(stet.sh) 2 points by bisonbear 9 days ago \| 0 comments
3.	GPT-5.5 vs. GPT-5.4 vs. Opus 4.7 on 56 real coding tasks from 2 open source repo(stet.sh) 4 points by bisonbear 16 days ago \| 0 comments
4.	I ran Opus 4.7 vs. Old Opus 4.6 vs. New Opus 4.6 on 28 Zod tasks(stet.sh) 2 points by bisonbear 30 days ago \| 0 comments
5.	Coding evals are broken. CI is green while AI code quality goes unmeasured(stet.sh) 1 points by bisonbear 32 days ago \| 0 comments
6.	Agents.md is the highest-leverage code you're not testing(stet.sh) 1 points by bisonbear 37 days ago \| 0 comments
7.	Your AI coding benchmark is hiding a 2x quality gap(stet.sh) 3 points by bisonbear 65 days ago \| 0 comments