News for hackers. Stuff that matters.
Re:Every model learned by gradient descent is approximately ... by qarl on Sunday February 25, 2024 @05:23PM (#39505527)
As the others have said, your criticism is silly.
Re:Every model learned by gradient descent is approximately ... by jiggawatts on Monday February 26, 2024 @01:52AM (#39508281)
Granted, they said it silly, so it must be so.
Re:Every model learned by gradient descent is approximately ... by qarl on Monday February 26, 2024 @07:03AM (#39510313)
Ok - here let me explain.

It's a ridiculous situation - a horse in outer space in a space suit. But you want the image to be hyper physically accurate. That's fine, but it's a little incongruous. I wouldn't expect a human artist to be able to guess your requirements, let alone an AI.

So no, I do not believe any amount of computer resources will let the AI guess your requirements. You'll have to spell them out, as I did with the bubble for you once already. If you want the tail to be enclosed as well, you'll have to spell it out.

The whole point of this discussion is to determine whether the AI is simply copy/pasting images it's seen before. We've determined that it does not - it is able to synthesis new images by understanding what it's seen.

Whether it can read your mind is a silly digression.

Re:Every model learned by gradient descent is approximately ... by jiggawatts on Monday February 26, 2024 @04:14PM (#39516829)
“Have the protective clothing actually cover the body” is something you think a human couldn’t figure out on their own?
Re:Every model learned by gradient descent is approximately ... by qarl on Monday February 26, 2024 @09:36PM (#39519483)
Yes. I think an actual artist, if you simply requested "a horse in a space suit" would not think that you were worried about literally protecting a horse in space.

Because, as I have repeatedly tried to explain to you, the idea of a horse in space is ridiculous and tends toward ridiculous renditions.

I'm going to stop replying to you now. Have a nice day.