Hacker News Reader

Comment by tikkun | Hacker News Reader

Possible - here's a counterpoint: ChatGPT will make it easier to make new programming languages because all you'd need to do is give an AI your docs, and it'll be able to figure out how to re-write things in the new language.

I'm not sure what I agree with, but I think it's interesting to think about.

My off the top of my head guess is it makes it easier to make new programming languages and have them be usable by people, but it reduces the value of new programming languages. So both things happen. We end up with more new programming languages because they're easier to make and use, but more of the usage concentrates on the existing languages and the ones that ChatGPT is best at. So both a bigger long tail, but more concentrated 'big winners'

View on HN

But ChatGPT didn't get good simply from reading docs.python.org. While I'll be the first to argue that it does things that resemble reasoning, it's limited context window means it doesn't sit there and stew on things during inference. It got good at Python during training because of the reams and reams of Python code out there.

The reason I say this is because with something with fewer examples but still with docs available online, specifically, AutoHotKey; ChatGPT's not nearly as good.

We'll get to where you're going, but we're not there quite just yet.

We're not far off. I'll often copy and paste docs examples in and it will work its magic pretty well

You’re copying and pasting the docs of the things for which it has seen millions of lines of code already. It’s not making the inferences off the docs.

OP is saying that without this initial bootstrap corpus, this won’t work well and hence people accustomed to this won’t adopt the language.

No. I'm pasting docs of stuff not used in the training data. Otherwise why would I paste the docs in?

This is my guess too. Programming languages currently have to make tradeoffs around cognitive load and the ability to fully reason about effects of statements. An AI assistant with stronger reasoning ability might allow the creation of more powerful languages than we're capable of using by ourselves.

(If this sounds dangerous to you -- to use a technology that humans aren't smart enough to understand ourselves -- I guess I'd agree.)

Yep. The next big programming language will be a variant of English, or other human language of choice.

You can give it a BNF grammar for the target language of choice, if you like. Not only is C/C++ the "new assembly," but every other high-level programming language can be thought of that way as well.

I asked the free version to make a basic grammar for SQL SELECT statements that is compatible with Oracle and DB2.

It replied chirpily that it could do that, in so many words, and output a grammar (which I didn't test) that solely parsed MySQL identifiers rather than the double-quoted kind. It wasn't precisely an invalid response, but it was clearly inappropriate for a human-like reply and showed what I consider a qualitative absence of consciousness.

I don't know why, but this seems to be a pattern with SQL - I have never asked it about MySQL, and indeed MySQL results tend to pollute my Google searches, but there may just not be enough other training material.

It's starting to aggravate me every time someone concedes it only is useful sometimes, and you have to check it, because it is starting to seem like unwarranted "praising with faint damns".

Reply on news.ycombinator.com