vivendi

joined 1 week ago
[–] vivendi@programming.dev 81 points 1 week ago (16 children)

Oh yeah, even higher chance of cancer, what's not to love

[–] vivendi@programming.dev 3 points 1 week ago

Simply, Diffusion models somewhat (and this is extremely hand wavy) work as the "reverse" of an image recognizer.

It is taught the concepts of images through image learning (build neural circuits) to detect image features. Then, you do the reverse, iterate on noise to generate features.

[–] vivendi@programming.dev 4 points 1 week ago

Any good OCR model also uses "AI"

And LLMs are usually really good at detecting text

Source: Had to OCR a quite a few ancient university papers

view more: ‹ prev next ›