I know when you're vibe coding

I think this should be renamed "I know when you're vibe coding with a last generation LLM".

Claude 4 Opus would not make any of the mistakes mentioned, because it knows and understands everything in your codebase. It would know when there's an existing utility function for that particular task, or that you prefer a functional rather than OOP approach. You say you want developers to care about the code they write, well, this is the next best thing; I believe it's as close as we'll see to a machine being able to "care" in my lifetime.

This is all true. The best way to treat LLM's as they are now is one step above the abstraction offered by compiled languages over assembly. You can describe something in plain english, note its explicit requirements, inputs and outputs, and an LLM can effectively write the code as a translation of the logic you are specifying. Using LLM's, you are best served minimizing the entropy they have to deal with. The transformer is essentially a translation engine, so use it as a translator, not as a generator.

That being said, every few months a new model comes out that is a little less encumbered by the typical flaws of LLM's, a little more "intuitively" smart and less needing of hand-holding, a little more reliable. I feel that this is simply a natural course of evolution, as more money is put into LLM's they get better because they're essentially a giant association machine, and those associations give rise to larger abstractions, more robust conceptions of how to wield the tools of understanding the world, etc. Over time it seems inevitable that providing an LLM any task it will be able to perform that task better than any human programmer given it, and the same will go for the rest of what humans do.

In the context of react codebases, people typically use either functional components everywhere or class components. Mixing the two approaches is frustrating and painful, eg you can’t use any of the hooks in your codebase in a class component. Perhaps the OP was talking about this, but just being really vague.

No, LLMs are not an "abstraction" like a compiler is. This is bullshit. LLMs are stochastic token generators. I have NEVER met someone in real life that has produced something I wouldn't throw in the trash using LLMs, and I have had the displeasure of eating cookies baked from an LLM recipe.

No, LLMs will not get better. The singularity bullshit has been active since 2010s. LLMs have consumed the entire fucking Internet and are still useless. Where the fuck is the rest of the data going to come from? All these emails from people wanting high quality data from PhDs only for them to be scammy. People only want to train these things on easily stolen garbage, not quality input, because quality is expensive. Go figure!

This optimistic horeshit hype is embarrassing.

LLMs would also need to use historic commits as context, rather than just the current state of the codebase in isolation. Most codebases I've worked with go through migrations from a legacy pattern A to a newer and better pattern B, used across different parts of the codebase. Rarely can these migrations be done in a single go, so both patterns tend to stick around for a while as old code is revisited. Like the HTTP example, even if LLMs pick up a pattern to follow (which they often don't), it's a coin flip whether they pick the right one or not.