Show HN: I AI-coded a tower defense game and documented the whole process

Re:Show HN: I AI-coded a tower defense game and documented t... by stavros on Friday July 04, 2025 @11:37AM (#44465454)

I wrote a whole PRD for this very simple idea, but still the bug persisted, even though I started from scratch four times. Granted, some had different bugs.

[ Parent | on HN ]

Re:Show HN: I AI-coded a tower defense game and documented t... by gametorch on Friday July 04, 2025 @11:55AM (#44465607)

I guess sometimes I have to do some minor debugging myself. But I really haven't encountered what you're experiencing.

Early on, I realized that you have to start a new "chat" after so many messages or the LLM will become incoherent. I've found that gpt-4.1 has a much lower threshold for this than o3. Maybe that's affecting your workflow and you're not realizing it?

[ Parent | on HN ]

Re:Show HN: I AI-coded a tower defense game and documented t... by stavros on Friday July 04, 2025 @11:57AM (#44465626)

No, that's why I started again, because it's a fairly simple problem and I was worried that the context would get saturated. A sibling commenter said that browser rendering bugs on mobile are just too hard, which seems to be the case here.

[ Parent | on HN ]

Re:Show HN: I AI-coded a tower defense game and documented t... by cootsnuck on Friday July 04, 2025 @01:36PM (#44466408)

Have you tried with both Claude opus 4 and Gemini 2.5 pro?

[ Parent | on HN ]

Re:Show HN: I AI-coded a tower defense game and documented t... by stavros on Friday July 04, 2025 @01:39PM (#44466421)

Opus 4, Sonnet 4, o3, o4-mini-high.

[ Parent | on HN ]