This is a good point. I've seen people with really complex AI setups (multiple agents collaborating for hours). But what are they building? Are they building a react app with an express backend? A next js app? Which itself is a layer on top of an abstraction?

I haven't tried this myself but I'm curious if an LLM could build a scalable, maintainable app that doesn't use a framework or external libraries. Could be danger due to lack of training data but I think it's important to build stuff that people use, not stuff that people use to build stuff that people use to build stuff that....

Not that meta frameworks aren't valuable, but I think they're often solving the wrong problem.

▲

jimbokun 3 hours ago | parent [-]

When it comes time to debug would you rather ask questions about and dig through code in a popular open source library, or dig through code generated by an LLM specifically for your project?

▲

abustamam 3 hours ago | parent | next [-]

The copout answer is it depends. I've debugged sloppy code in React both before and after LLMs were commonly used. I've also debugged very well-written custom frameworks before and after LLMs.

I think with proper guardrails and verification/validation, a custom framework could be easier to maintain than sloppy React code (or insert popular framework here).

My point is that as long as we keep the status quo of how software is built (using popular tools that male it fast and easy to build software without LLMs that often were unperformant), we'll keep heading down this path of trying to solve the problems of frameworks instead of directly solving the problems with our app.

(BTW, it was your comment to my comment that inspired my comment, talk about meta! https://news.ycombinator.com/item?id=47512874 )

▲

apsurd 3 hours ago | parent | prev [-]

If the LLM doing it, it doesn't matter, isn't that the point?

Not saying I personally believe in this scenario, but everything I've heard supports the idea that code is no longer for humans to consume.

▲

jimbokun 3 hours ago | parent [-]

You are going to allow a product from a company you have no reason to trust write important software for you and put it into production without checking the code to see what it does?

▲

apsurd 3 hours ago | parent | next [-]

I agree with you, which makes me seem like the laggard at work. Devil's advocate is that AI-native development will use AI to ask these questions and such. So whether it's a framework or standard lib, def agree knowing your stuff is what matters, but the tools to demonstrate this knowledge is fast in flux.

Again, I am on the slow train. But this seems to be all I hear. "code optimized for humans" is marked for death.

▲

apsurd 2 hours ago | parent | prev | next [-]

had another thought on my drive just now. nextjs is really fantastic with LLM usage because there's so much body of work to source from. previously i found nextjs unbearable to work with with its bespoke isomorphic APIs. too dense, too many nuances, too much across the stack.

with LLMs it spit it out amazingly fast. but does that make nextjs the framework better or worse in design paradigms, that LLM is a requirement in order to navigate?

▲

servercobra 2 hours ago | parent | prev [-]

A lot of us use software written by other people we have no reason to trust and we haven't reviewed - most of open source libraries.

▲

sarchertech 2 hours ago | parent [-]

At least with any open source library I use, many other people have.

	▲	abustamam 9 minutes ago \| parent [-]
		Yeah a nice thing about OSS is that they usually come with a community and you can ask questions or even submit bug fixes.