Hacker News Reader

Comment by mvvl | Hacker News Reader

This is only going to get worse with LLMs. Now people can "contribute" garbage code at 10x the speed. We're entering the era of the "read only" maintainer focused on self-defense.

View on HN

I’ve seen it already where someone has set some fully automated agent at the GitHub issues and machine gunned PRs every minute for every reported issue. Likely never looked at or tested by the submitter.

Even if they worked, it would be easier for the maintainer to just do that themselves rather than review and communicate with someone else to resolve issues.

...that assumes LLMs will contribute garbage code in the first place. Will they, though?

The problem isn't that it can't write good code. It's that the guy prompting it often doesn't know enough to tell the difference. Way too many vibe coders these days who can generate a PR in 5 seconds, but can’t explain a single line of it.

That’s 100% the trick to it all. I don’t always write code using LLMs. Sometimes I do. The thing that LLMs have unlocked for me is the motivation to put together really solid design documentation for features before implementing them. I’ve been doing this long enough that I’ve usually got a pretty good idea of how I want it to work and where the gotchas are, and pre-LLMs would “vibe code” in the sense that I would write code based on my own gut feeling of how it should be structured and work. Sometimes with some sketches on paper first.

Now… especially for critical functionality/shared plumbing, I’m going to be writing a Markdown spec for it and I’m going to be getting Claude or Codex to do review it with me before I pass it around to the team. I’m going to miss details that the LLM is going to catch. The LLM is going to miss details that I’m going to catch. Together, after a few iterations, we end up with a rock solid plan, complete with incremental implementation phases that either I or an LLM can execute on in bite-sized chunks and review.

The LLM isn’t contributing garbage, the user is by (likely) not testing/verifying it meets all requirements. I haven’t yet used an LLM which didn’t require some handholding to get to a good code contribution on projects with any complexity.

I heard a quote recently that I really like.

"AI sucks at most peoples' jobs. If you think AI is good at something, chances are you suck at it too."

Reply on news.ycombinator.com