logoalt Hacker News

bob1029 • last Monday at 7:50 PM • 2 replies • view on HN

I have my best successes by keeping things constrained to method-level generation. Most of the things I dump into ChatGPT look like this:

  public static double ScoreItem(Span<byte> candidate, Span<byte> target)
  {
     //TODO: Return the normalized Levenshtein distance between the 2 byte sequences.
     //... any additional edge cases here ...
  }
I think generating more than one method at a time is playing with fire. Individual methods can be generated by the LLM and tested in isolation. You can incrementally build up and trust your understanding of the problem space by going a little bit slower. If the LLM is operating over a whole set of methods at once, it is like starting over each time you have to iterate.

Replies

theshrike79 • last Tuesday at 11:50 AM

"Dumping into ChatGPT" is by far the worst way to work with LLMs, then it lacks the greater context of the project and will just give you the statistical average output.

Using an agentic system that can at least read the other bits of code is more efficient than copypasting snippets to a web page.

➕ show 2 replies
samdoesnothing • last Monday at 9:07 PM

I do this but with copilot. Write a comment and then spam opt-tab and 50% of the time it ends up doing what I want and I can read it line-by-line before tabbing the next one.

Genuine productivity boost but I don't feel like it's AI slop, sometimes it feels like its actually reading my mind and just preventing me from having to type...

➕ show 1 reply