Hacker News Reader

This exactly matches my experience. I also suspected that it was my higher threshold for code quality but Ai generated code is just not worth adding to a project without very strict reviews, unless it's non production and I want to fully give the project over to Ai

View on HN

You can keep burning tokens until it complies. Thats what I do and I get good results. I do often have to spend a day just thinking through the prompt, but then again coding rarely was the bottleneck. But AI is very good at doing a refactor as well, tedious stuff like constructor juggling. Thing is code is to be written for humans first, no matter if the author is human or AI.

> You can keep burning tokens until it complies. Thats what I do and I get good results.

Like "it compiles" is literally the lowest bar, not "good results."

Depends on the language and the way code is written. Actually if you can run the code locally, getting things to compile is a bottleneck in Java especially for constructor juggling. Once code compiles, iterations do the rest. Iterations are better done by hand I think, we can get feedback on the code while keeping things fresh in our heads. For critical stuff where coding = thinking, its just faster to code.

Reply on news.ycombinator.com