When coding agents first came out, the overwhelming narrative was how bad they were, they don't know what they're doing, the code they write just sucks and they hallucinate APIs.

While these criticisms were technically true, they were stated mostly out of a sense of insecurity from people whose jobs were basically spending years and years just glueing code together and mixing APIs to display some CRUD apps rather than out of a genuine concern for whether LLMs were actually producing poor products.

Nowadays those concrete criticisms don't really work anymore, LLMs are pretty good now and surpass most developers when it comes to writing the majority of shovelware that people have been employed, and so the narrative is changing from concrete criticisms about how LLMs were genuinely not capable of writing software... to these kinds of abstract and philosophical arguments that are really hard to argue against because they make no concrete claims.

If you say an LLM can't implement a feature, we'll we can test that claim concretely and LLMs are getting much better with every new release. If you say its code is slower, buggier, or less maintainable, those claims too can be measured and once again they're getting really good at these. If you say it takes longer to complete a task or requires more human intervention, we can compare it and measure etc...

But now the objection has shifted not to LLMs are incapable, but people are now incapable and LLMs represent a degradation of the "craft". And here there is nothing left to test or falsify. The argument has stopped being about whether the LLMs work, because that's verifiable and they are now at a point where it's hard to argue against their ability to actually produce functioning software, so now the argument is about whether people are morally, culturally, or intellectually permitted to use it.

I'm with you here. If we skate to the puck, LLMs will continue to write tighter and tighter code, comments, unit tests, integration tests, etc. I would also assume that it will become increasingly good at code organization, architecture, and understanding intent. i feel like I am a series of monthly shifting of the goal posts...."LLMs can't autocomplete code", "LLMs can't write a high quality function", "LLM's can't understand small repos". "LLM's can't understand legacy code bases".....

If it's this easy for you it's just as easy for anyone else. What do you think will happen to your salary when no particular skills are required to do your job?

Next year you may be unemployed (because your boss will cut by half the engineering department), or perhaps your salary will be cut by half (because your boss will route your other half of your salary to openai/anthropic), or perhaps you will get half insane (because your boss will ask you 10X the output you used to have but within the same timeframe)

Whatever the path is, regular engineers (90% of the people around here) will get screwed up one way or another. But hey, playing with LLM agents is cool!

You may not be at a company where people are dropping AI slop into the codebase faster than it can be cleaned up. I've thought about my options for going "single operator", so I don't end up with a mismatch between people who use AI thoughtfully and those those who don't.