Don't fall into the anti-AI hype

Re:Don't fall into the anti-AI hype by Madmallard on Monday January 12, 2026 @03:43AM (#46585740)

LLM generated tests in my experience are really poor

[ Parent | on HN ]

Re:Don't fall into the anti-AI hype by redox99 on Monday January 12, 2026 @03:50AM (#46585780)

Doesn't change the fact that what I mentioned greatly improves agent accuracy.

[ Parent | on HN ]

Re:Don't fall into the anti-AI hype by Madmallard on Monday January 12, 2026 @05:00AM (#46586316)

Actually it borderline undermines it because it's shit building upon shit

[ Parent | on HN ]

Re:Don't fall into the anti-AI hype by dns_snek on Monday January 12, 2026 @08:37AM (#46588300)

AI-generated implementation with AI-generated tests left me with some of the worst code I've witnessed in my life. Many of the passing tests it generated were tautologies (i.e. they would never fail even if behavior was incorrect).

When the tests failed the agent tended to change the (previously correct) test making it pass but functionally incorrect, or it "wisely" concluded that both the implementation and the test are correct but that there are external factors making the test fail (there weren't).

It behaved much like a really naive junior.

[ Parent | on HN ]

Re:Don't fall into the anti-AI hype by simonw on Monday January 12, 2026 @09:33AM (#46589057)

Which coding agent and which model?

[ Parent | on HN ]