Re:Imagen, a text-to-image diffusion model
by satokausi on Tuesday May 24, 2022 @01:26AM
(#31488322)
I doubt 99% of humans can draw a ”chess game with a puzzle where white mates in 4 moves”
Maybe not draw, but we can do an image search for "chess puzzle mate in 4" which gives plenty of results:
https://www.google.com/search?q=chess+puzzle+mate+in+4&tbm=i...
It would be surprising if AI couldn't do the same search and produce a realistic drawing out of any one of the result puzzles.
They can with computer assistance, and this AI sort of has that in that it’s both some “intelligence” and a whole lot of memorized internet, with the issue that we don’t know how to separate those things.
It's surprisingly easy to construct such a thing.
If you want to be trivial about it, you can just have white back-rank mate with a rook, and black has 4 pieces to block with.
AI was expected to grow like a child. Somehow blurting out things that would show some increasing understanding on a deep level but poor syntax.
In fact we get the exact opposite. AI is creating texts that are syntaxically correct and very decently articulated and pictures that are insanely good.
And these texts and images are created from a text prompt?! There is no way to interface with the model other than by freeform text. That is so weird to me.
Yet it doesn’t feel intelligent at all at first. You can’t ask it to draw “a chess game with a puzzle where white mates in 4 moves”.
Yet sometimes GPT makes very surprising inferences. And it starts to feel like there is something going on a deeper level.
DeepMind’s AlphaXxx models are more in line with how I expected things to go. Software that gets good at expert tasks that we as humans are too limited to handle.
Where it’s headed, we don’t know. But I bet it’s going to be difficult to tell the “intelligence” from the “varnish”