Would human mathematicians only be cooked once AI comes up with the actual problems, and then solutions to them? Right now we're solving very old ideas (which is very cool, no doubt), but the universe doesn't end with solving the backlog, we need to find new problems that explains things we don't yet understand.
Once AI does that, then yes, math people are cooked, but I think most of us are by then.
We don’t have access to knowledge, we have access to information. Knowledge requires processing information and that just doesn’t happen any more.
A post-scarcity society is not possible without first wiping out society. If everyone has everything then everyone has nothing.
And of course, natural resources are actually limited, and those power LLMs.
Wouldn’t AI design a completely programmable base that can become any type of chip instead? It seems limiting that you’d need custom chips for different tasks, a chip could morph on demand, even include different architectures that change during runtime dynamically, or even reinvent itself as required.
If we use the very abstract term “the future” that is.
Indeed, this seems like a really low number for when to run into issues, unless they're running it on a shared VPS and/or it's just not very well built.
In five years everything will be bland and boring, people will start to ask about unique things and just get redirected to <ad paying company> instead.
It will speed up the death of content on the open internet, it didn’t start with AI, it’s just being massively accelerated by it.
Most people will be dumber and more easily tricked and controlled, others will start to distrust everything.
Everything will be worse, except for the stockholders of the gatekeepers (and their owners).
And before anyone asks, I’m using AI heavily every day.
I see something like ”const user = createMemo(() => fetchUser(props.id));” or “use server” and I’m instantly reminded of why I abandoned JS frameworks (not to mention anything touching JS on the server).
I much prefer Solid over React, but at least the idea of a compiler makes so much more sense instead of manually maintaining memoization.
BorisFX does this great. They don’t even call things AI just ML (which is correct) and the product I use, Optics, has this insane masking model that allows you to just paint with green and red colors very crudely (and I mean that) and get almost perfect masks immediately.
These kinds of tools are extremely valuable and worth paying for, compared to Photoshop who has gone all in on generative AI and it’s all terrible, slow and token based.
reply