They began leveraging large language models against... any data set as I understand it. There were a few papers that set the world on fire with their implementations. Academia was raided for questionably sourced corpus for commercial use veiled in community gain.
I've been wrenching on stable diffusion API for a few weeks, as a former professional photographer it is shocking to me the quality you can get from very little input and common COTS GPUs. Haven't touched any of the SaaS cloud inferencing services that have come out in this gold rush but they can do quite a lot more with the datacenter class GPU grunt.  Text to video (so-called "T2V") is here and getting scary.~

Bless,
soup

On Tue, Feb 13, 2024 at 4:19 PM Keith Wright via WLUG <wlug@lists.wlug.org> wrote:
John Stoffel via WLUG <wlug@lists.wlug.org> writes:

> And does anyone have pointers to the Image generating stuff we talked
> about?  It wiould be fun to try it out myself and for $10 I could get
> alot of fun.

That wasn't a motion, but I second it anyway.

>From the viewpoint of a jit.si watcher, that was one of the most
fun demos of a program I have seen at a WLUG over the decades.

But eye-candy aside, I was most interested that the demonstrator
claimed to understand how it works and to have some links.

The meaning of words changes over time.  More change in less time now.

A cartoon generating program is called "artificial intelligence".
I can't draw cartoons, so I must not be intelligent.

The words "machine learning" were used.  As I said Thursday, I did
my dissertation on machine learning.  At that time, it meant a computer
(with appropriate programming) would input a sequence of examples,
each marked as in or not in a certain class.  The computer would then
(we hoped) be able to correctly classify examples that had not been
explicitly shown before.

I didn't see anything like that in the demo.

It was said to be based on a "neural net", but neural nets have been
around since Minsky started inventing words back in the fifties.
What changed to make neural networks suddenly start working?

   -- Keith
_______________________________________________
WLUG mailing list -- wlug@lists.wlug.org
To unsubscribe send an email to wlug-leave@lists.wlug.org
Create Account: https://wlug.mailman3.com/accounts/signup/
Change Settings: https://wlug.mailman3.com/postorius/lists/wlug.lists.wlug.org/
Web Forum/Archive: https://wlug.mailman3.com/hyperkitty/list/wlug@lists.wlug.org/message/7OFTTGWG2NBFBCWYYNO37IALPQ3DIDHU/