Knitters teamed up with a neural-network creator to generate new shapes | Hacker News Reader

Knitters teamed up with a neural-network creator to generate new shapes

theatlantic.com

77 pointscardamomo10 comments

More pictures: https://www.ravelry.com/patterns/library/skyknit-the-collect...

Thanks for sharing that link. There are some really beautiful pieces in there! Natural, but with a strange edge. Regular enough to be pleasing, but unpredictable enough to be interesting.

This one in particular https://www.ravelry.com/patterns/library/skyknit-the-collect... reminds me of Wolfram's timeplot CA renderings.

It would be interesting to see this combined with simulation [1], which might itself need another neural network (or manually written "fixer") to interpret the ambiguous instructions.

[1] Kaldor et al - "Simulating Knitted Cloth at the Yarn Level" https://www.cs.cornell.edu/~srm/publications/SG08-knit.html

It seems like overly optimistic interpretations of crappy/noisy neural network output. I could be wrong though.

The comment about 19th century patterns resonated. I don’t knit well, but I do tatting, and original vintage patterns are often woefully incomplete, there seemed to be this expectation that you knew the basics and could work out what was missing yourself. As The article points out, knowing the intent of the pattern usually helps resolve ambiguity

Weirdly high rated though. Lots of pictures. Clearly someone likes this. Something is happening here. Any knitters that can explain?

Why do we like Conways game of life? Why are we interested in AI-generated art?

I found the outcomes delightful and hilarious (there are lots of photos in one of the other sites linked to from the article).

Perhaps more interesting is the collaboration between humans and AI to turn the AI's "imagination" into something that physically exists.

The naivety of these systems leads to output that we perceive as creative or playful. Personally, I've used simple Markov models to create texts or melodies that I then selectively recombine to write new music. The computer-created material is familiar but different enough from what I or a human might produce that it leads me to push my own creativity in new directions.

I am usually not a fan of puns, but skyknit is gold

In this piece, Alexis Madrigal gives one of the all time most straightforward descriptions of how neural nets work. Kudos.

Reply on news.ycombinator.com