This. For area where you can use tested and tried libraries (or tools in general) LLMs will generate better code when they use them.

In fact, LLMs will be better than humans in learning new frameworks. It could end up being the opposite that frameworks and libraries become more important with LLMs.

▲

nottorp an hour ago | parent | next [-]

> In fact, LLMs will be better than humans in learning new frameworks.

LLMs don't learn? The neural networks are trained just once before release and it's a -ing expensive process.

Have you tried using one on your existing code base, which is basically a framework for whatever business problem you're solving? Did it figure it out automagically?

They know react.js and nest.js and next.js and whatever.js because they had humans correct them and billions of lines of public code to train on.

▲

giancarlostoro 26 minutes ago | parent [-]

If its on github eventually it will cycle into the training data. I have also seen Claude pull down code to look at from github.

	▲	fauigerzigerk 2 minutes ago \| parent [-]
		Wouldn't there be a chicken and egg problem once humans stop writing new code directly? Who would write the code using this new framework? Are the examples written by the creators of the framework enough to train an AI?

▲

catlifeonmars an hour ago | parent | prev | next [-]

LLMs famously aren’t that good at using new frameworks/languages. Sure they can get by with the right context, but most people are pointing them at standard frameworks in common languages to maximize the quality of their output.

	▲	tappio 21 minutes ago \| parent [-]
		This is not my experience any longer. With properly set feedback loop and frameworks documentation it does not seem to matter much if they are working with completely novel stuff or not. Of course, when that is not available they hallucinate, but who anymore does that even? Anyone can see that LLMs are just glorified auto-complete machines, so you really have to put a lot of work in the enviroment they operate and quick feedback loops. (Just like with 90% of developers made of flesh...)

▲

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

> LLMs will be better than humans in learning new frameworks.

I don't see a base for that assumption. They're good at things like Django because there is a metric fuckton of existing open-source code out there that they can be trained on. They're already not great at less popular or even fringe frameworks and programming languages. What makes you think they'll be good at a new thing that there are almost no open resources for yet?

▲

lenkite an hour ago | parent | prev [-]

How will LLM's become better than humans in learning new frameworks when automated/vibe coders never manually code how to use those new frameworks ?