News for hackers. Stuff that matters.

A comment on Imagen, a text-to-image diffusion model. Parent comment

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”
[ Parent | on HN ]
Re:Imagen, a text-to-image diffusion model by bambax on Tuesday May 24, 2022 @01:35AM (#31488368)
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.

[ Parent | on HN ]
Re:Imagen, a text-to-image diffusion model by astrange on Tuesday May 24, 2022 @02:00AM (#31488510)
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.
[ Parent | on HN ]
Re:Imagen, a text-to-image diffusion model by stevage on Tuesday May 24, 2022 @04:38AM (#31489524)
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.

[ Parent | on HN ]