[0xpgm]

Hypothetically if LLMs were possible in the early 90s, what would the software ecosystem look like today?

Would it be 80s technology everywhere but widely deployed? Or would things have advanced further - better compilers, more ergonomic languages, better platforms etc? I don't know. But I suspect we'd still have needed people studying computer science to advance the state of the art.

Now looking forward 30-40 years from now, will everything still run on 2020s technologies?

[lucianbr]

> better compilers, more ergonomic languages

If anything it seems wide deployment of LLMs would go against this. When nobody writes code by hand anymore, who will care about the ergonomics of programming languages? And even if a few do care, how would you get adoption? I expect everyone will just use whatever is already used most.

[camdenreslink]

I agree, it seems like the current most popular languages and frameworks will become ossified, because they have the highest amount of training data. It's hard to see a future where Python and JavaScript aren't the most popular languages to use (assuming LLM-assisted development is the norm moving forward).

[omcnoe]

LLMs can be pretty conmpetent at languages that have zero training data, at least to the extent that those languages use features/ideas that are familiar. I wrote a toy language/compiler and AI can write code for it competently.

[__float]

Do you not review the code that LLMs output?

It seems that now more than ever, testing is important. But LLMs love to cheat the tests and make them superficially pass. If you're never reading the code, how do you know changes are reasonable?

[lucianbr]

I do review, if only whatever I do was the norm for everyone :)

Do you see lots of posts about new compilers and languages and language features on HN in the last year? Maybe I just missed them. I'd love to read more posts like that and fewer about agent frameworks.

[strangegecko]

Product does what it should and doesn't what it shouldn't?