Ask HN: Where is the programming profession going?

Yes, this is the direction I am observing. Ironically, I don't think anybody is happy about it and we keep saying that it is a tool and you need to verify everything, etc, but this is not what is happening.

There are tons of people who produce questionable code at a rate which is not really compatible with a thoughtful review, we have people with little engineering background pushing their changes (although there is a large pushback against that as the results are really bad even short term), as you said, there is an explosion of LLM-generated tests.

As soon as someone writes a next-level harness which tightly iterates based on the spec/plan and/pr pioneers some sort of acceptance criteria format that works, I think at that point SWE job will completely change. We are not there yet but probably not that far off.

I’m not sure how you can say something general about the quality of tests unless you mean by simply prompting “make tests” or similar.

Yes, I’ve experienced that those tests succeed, and the app still breaks trivially on first run.

What I mean is: you design the tests. You analyse patterns. You insist on making testable code (average code by humans isn’t, so neither is average code by LLMs unless you specify testability as a design constraint.

One way to get testable code is to mock all interfaces. This is usually expensive, but not difficult for an AI, because you can set the success criterion to be interface exactness of your mock for a series of plausible and somewhat extensive interactions.

The tests you can make with AI are as good as you can make them otherwise, you just save time doing them, which should justify making more extensive testing.

I was trying to make a different statement. Everyone will need to become a manager, even ICs. But in the past, many engineers shied away from management, for various reasons. Now, it will need to change.

Managing people is hard because of all the things that make us human. Managing AI will be simpler as we won't need to deal with some of those things.

Separately,

> "By using AI we get all the benefits of workers but with none of the drawbacks of humans."

To be fair, I did not write that. You are projecting your thoughts on my post.

Programming models will continue to improve; in the foreseeable future, enterprises will rely less and less on human programmers to write code.

If you are still interested in programming, do not waste time delving deep into the code itself; instead, spend time understanding requirements and the market. The combination of an individual and Codex will be the optimal approach to programming.

I think of AI as an intelligent partner that took away the boring stuff and give me the real design decisions. The expectations of clients have changed but most of the code I have seen written by AI does the work but AI do ignore somethings that matter in scaling. In my company actually boss thinks he is a programmer now with claude but writes too much error prone code which I think mainly not because of claude because non technical person giving generic commands. For me in near future the need for proper engineers is still very high.