Hacker News: haukebrihttps://news.ycombinator.com/user?id=haukebriHacker News RSShttps://hnrss.org/hnrss v2.1.1Wed, 09 Sep 2026 15:54:49 +0000<![CDATA[New comment by haukebri in "AI in Test Automation: Real Limitations vs. User Error"]]>I love AI, but understanding errors and "bad" things is so tough.

I have built systems from Skills to full SaaS solutions for testing with AI. Sometimes it's great, sometimes it's just full on weirdness.

]]>Wed, 09 Sep 2026 07:42:26 +0000https://news.ycombinator.com/item?id=49622758haukebrihttps://news.ycombinator.com/item?id=49622758https://news.ycombinator.com/item?id=49622758<![CDATA[New comment by haukebri in "The Problem with Your AI Tests"]]>Reading AI written tests feels like reading AI written stories from a few years ago. The text is there, things are happening but they are contradicting themself and make no sense. Sometimes you have a gem that is great.

I've been building agent skills against exactly this, cutting worthless tests and pushing the agent to write fewer but sharper ones. It's kind of the same approach as yours, just as a skill. --> github.com/haukebri/mira-test-engineer

]]>Wed, 09 Sep 2026 07:38:40 +0000https://news.ycombinator.com/item?id=49622725haukebrihttps://news.ycombinator.com/item?id=49622725https://news.ycombinator.com/item?id=49622725<![CDATA[New comment by haukebri in "Ask HN: Why don't LLM APIs have a first-class test mode?"]]>It happens and I hate it. What happens: the tests are green and all looks falsely good. I have a bunch of mechanisms that try to prevent this.

I have a skill that acts as a guide to test writing. I have a CLI command that can test end to end in a browser, and I have a prod monitoring / testing SaaS.

]]>Sun, 06 Sep 2026 08:07:06 +0000https://news.ycombinator.com/item?id=49584318haukebrihttps://news.ycombinator.com/item?id=49584318https://news.ycombinator.com/item?id=49584318<![CDATA[New comment by haukebri in "What happens when your AI agent edits its own tests to pass?"]]>It happens and I hate it. What happens: the tests are green and all looks falsly good. I have a bunch of mechanisms that try to prevent this.

I have a skill that acts as a guide to test writing.

I have a cli CMD that can test end to end in a browser and I have a prod monitoring / testing SaaS

]]>Sun, 06 Sep 2026 08:03:13 +0000https://news.ycombinator.com/item?id=49584302haukebrihttps://news.ycombinator.com/item?id=49584302https://news.ycombinator.com/item?id=49584302<![CDATA[Coding-agent skills that cut your worthless tests and write fewer, better ones]]>Article URL: https://github.com/haukebri/mira-test-engineer

Comments URL: https://news.ycombinator.com/item?id=49578579

Points: 3

# Comments: 0

]]>Sat, 05 Sep 2026 17:17:51 +0000https://github.com/haukebri/mira-test-engineerhaukebrihttps://news.ycombinator.com/item?id=49578579https://news.ycombinator.com/item?id=49578579