feastingonslop

Nor does it stop self-respecting LLMs.

What value is there in tested code when you have the option of superlative, flawless code?

LLMs write superior code. Maybe they learned from humans, but they have seen further while standing on those shoulders.

If the LLM writes better code (and it will) then its code should be favored over a library.

Why would you not?

It doesn’t mess up. Not any more.

> Everyone can treat the project as a black box, and focus on observable changes to the project's behavior.

This is a good thing. I don’t need to focus on oil refineries when I fill my car with gas. I don’t know how to run a refinery, and don’t need to know.

Since the code does not matter, you wouldn’t need or want to phrase it in terms of algorithmic complexity. You surely would have a more real world requirement, like, if the data set has X elements then it should be processed within Y milliseconds. The AI is free to implement that however it likes.

If you have particular performance requirements like that, then include them. Test for them. You still don’t have to actually look at the code. Either the software meets expectations or it doesn’t, and keep having AI work at it until you’re satisfied.

And that is the right assumption. Why would any humans need (or even want) to look at code any more? That’s like saying you want to go manually inspect the oil refinery every time you fill your car up with gas. Absurd.

The code itself does not matter. If the tests pass, and the tests are good, then who cares? AI will be maintaining the code.

Nobody is saying to skip testing the software. Testing is still important. What the code itself looks like, isn’t.