Hacker News Reader

Comment by llmslave2 | Hacker News Reader

No but I don't use it to generate code usually.

I gave agents a solid go and I didn't feel more productive, just became more stupid.

A year or so ago I was seriously thinking of making a series of videos showing how coding agents were just plain bad at producing code. This was based on my experience trying to get them to do very simple things (e.g. a five-pointed star, or text flowing around the edge of circle, in HTML/CSS). They still tend to fail at things like this, but I've come to realize that there are whole classes of adjacent problems they're good at, and I'm starting to leverage their strengths rather than get hung up on their weaknesses.

Perhaps you're not playing to their strengths, or just haven't cracked the code for how to prompt them effectively? Prompt engineering is an art, and slight changes to prompts can make a big difference in the resulting code.

Perhaps it is a skill issue. But I don't really see the point of trying when it seems like the gains are marginal. If agent workflows really do start offering 2x+ level improvements then perhaps I'll switch over, in the meantime I won't have to suffer mental degradation from constant LLM usage.

and what are those strengths, if you don't mind me asking?

  - Providing boilerplate/template code for common use cases
  - Explaining what code is doing and how it works
  - Refactoring/updating code when given specific requirements
  - Providing alternative ways of doing things that you might not have thought of yourself

YMMV; every project is different so you might not have occasion to use all of these at the same time.

I appreciate your reply. A lot of people just say how wonderful and revolutionary LLMs are, but when asked for more concrete stuff they give vague answers or even worse, berate you for being skeptical/accuse you of being a luddite.

Your list gives me a starting point and I'm sure it can even be expanded. I do use LLMs the way you suggested and find them pretty useful most of the time - in chat mode. However, when using them in "agent mode" I find them far less useful.

"Agent mode" is vastly different in many ways. I suggest you read up on how people write things like CLAUDE.md files. But as I said earlier, every project is different, and one what one person was successful with won't necessarily make you successful, so you may find it more helpful to get somebody to coach you through prompting agents for your particular projects.

Here's a concrete example of what can be done with Opus 4.5, and how to do it: https://burkeholland.github.io/posts/opus-4-5-change-everyth...

Reply on news.ycombinator.com