←back to thread

165 points gdudeman | 2 comments | | HN request time: 0.633s | source
1. epohs ◴[] No.44482491[source]
A year or two ago I had a pretty simple thought. The idea was that LLMs make a great assistant for a skilled developer, a bad replacement for a skilled developer, and a dangerous assistant for an unskilled developer. That idea has mostly seemed to hold true as I have gotten more experience with LLMs.

I think I would revise it now to allow that LLMs can be really useful teachers for unskilled developers, however I don’t get the sense that that’s how they’re being used in many cases. It seems that it’s more common that unskilled developers using LLMs just vibe code their way through issues that they run into, never really gaining insight into why the thing they’re working on failed, and just push through until it seems like it isn’t failing anymore.

And that more or less reinforces my idea that they’re dangerous assistants in those cases where the developer is unskilled. It’s pretty much inevitable that this will introduce problems that make it through the process of creation not only unnoticed, but problems that the developer is incapable of understanding even if they are noticed.

replies(1): >>44487280 #
2. aryehof ◴[] No.44487280[source]
> It seems that it’s more common that unskilled developers using LLMs just vibe code …

This is my conclusion to date also, however, I believe the reason behind that is the increasing adoption of agentic tools like Claude Code and Gemini CLI etc, that encourage users to disregard the actual code generated.