Hacker News Reader

That's the part covered by the other model's review. That together with manually verifying the functionality results in output that works.

View on HN

If you don’t know the language you can’t evaluate if the models really found bugs.

That’s like translating a text to another language without knowing the language

This is wildly overblown. I've been working with agents for a good while, read tens of thousands of generated Python and the language factor is actually the part they get right that humans don't.

Do you know Python?

What do you think has more training data Python or Kotlin?

20+ years of using Python. I don't really think that lack of training data for Kotlin is a problem.

Reply on news.ycombinator.com