this post was submitted on 15 Apr 2024
142 points (84.1% liked)

Showerthoughts

29679 readers
2366 users here now

A "Showerthought" is a simple term used to describe the thoughts that pop into your head while you're doing everyday things like taking a shower, driving, or just daydreaming. The best ones are thoughts that many people can relate to and they find something funny or interesting in regular stuff.

Rules

  1. All posts must be showerthoughts
  2. The entire showerthought must be in the title
  3. Avoid politics (NEW RULE as of 5 Nov 2024, trying it out)
  4. Posts must be original/unique
  5. Adhere to Lemmy's Code of Conduct

founded 1 year ago
MODERATORS
vatlark@lemmy.world
forkball@lemmy.world
quinten@lemmy.world
Thekingoflorda@lemmy.world
142
When historians are trying to credit the invention of generative AI, they may have to hunt down that one social media post that started the "use only auto-complete to finish this sentence" trend. (lemmy.sdf.org)
submitted 7 months ago by xia@lemmy.sdf.org to c/showerthoughts@lemmy.world
21 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] blazera@lemmy.world 13 points 7 months ago (1 children)

Im fascinated with the history of image AI as just some algorithms to help clean up noisy photos. Eventually they advanced enough that you just feed it complete noise, tell it what its an image of, and it just "gets rid of the noise"

[–] StitchIsABitch@lemmy.world 8 points 7 months ago (2 children)

Wait is that how image generation works? Denoising a random noise seed?

[–] JPAKx4@lemmy.blahaj.zone 10 points 7 months ago

Yes! It's called "stable diffusion", and it's how you get a unique image everytime.

[–] blazera@lemmy.world 7 points 7 months ago

Yeah thats the mechanism its generating with, and why every generation is different in some way. Theres a lot more cool components to the whole process and history tho. Tying language models into image recognition models, and then the image generation algorithm has an arms race with the image recognition, where the image generation is learning by trying to deceive image recognition, and image recognition is trying to distinguish between generated images and real images its also being fed.