I don't agree. It may be true that most code is throwaway.

But you trust a C compiler, or a Python intepreter, to do their job in a deterministic way. You will never be able to trust Copilot telling you that "this should be the code you are using".

It may suggest you using AWS, or Google, or Microsoft, or Tencent infrastructure. An LLM can even push you a specific style, or political agenda, without even you realizing it.

I hate polarized discussion all-or-nothing thinking about LLMs. See how perfectly and reliably they can translate text in whatever language. See them fail at aligning a table with a monospace font.

I think you probably need a multimodal LLM to align a table with a monospace font. Blind human programmers using screenreaders will also have difficulty with that particular task. It doesn't mean they're bad at programming; it just means they can't see.

Human blind programmers may write programs to align their own tables like requested, in autonomy. Instead of me seeing them doing wrong, asking for a fix, and them doing it wrong again in an endless cycle. Also, when I tell them the solution and ask to add a feature - bam, the table is made wrong again.

True.

A c program is understandable even if it isn't efficient. It's also deterministic, or close enough that it shouldn't matter.

An llm project that can be generated from scratch every time is maybe understandable if you use very good prompts and a lot of grounding text. It is not deterministic unless you use zero temperature and stick with the same model forever. Something that's impossible now. Six months ago the state of the art model was deepseek r1.

This is exactly why we can't have nice things :(