News for hackers. Stuff that matters.
Re:Show HN: I AI-coded a tower defense game and documented t... by cainxinth on Saturday July 05, 2025 @08:55AM (#44472489)
> No security holes. No bugs.

A friend called me for advice on trouble he was having with an LLM and I asked “What exactly do you want the LLM to do?” He said “I want it to knock this project out of the park.” And I had to explain to him it doesn’t work that way. You can’t just ask for perfection.

I mean, you can, but you won’t get it.

Re:Show HN: I AI-coded a tower defense game and documented t... by exographicskip on Sunday July 06, 2025 @12:13AM (#44477781)
Writing tests and/or PRDs helps. Gives llms tangible direction that can be quantified.