12/12/2023 0 Comments Ai weirdness candy heartsFor most of its patterns, doing them exactly as written would result in the pattern immediately unraveling (due to many dropped stitches), or turning into long whiplike tentacles (due to lots of leftover stitches). The knitters didn’t follow SkyKnit’s directions exactly, as it turns out. This possibly marks one of the few times in history when a computer generated code to be executed by humans. SkyKnit also had trouble counting stitches, and would confidently declare at the end of certain lines that it contained 12 stitches when it was nothing of the sort.īut the knitters began knitting them. It could count rows fairly reliably up to about 22, but after that would start haphazardly guessing random largish numbers. It would sometimes repeat rows, or leave them out entirely. Here’s a later example.Įven at its best, SkyKnit had problems. MrsNoddyNoddy wrote, “it’s difficult to explain why 6395, 71, 70, 77 is so asthma-inducingly funny.” (It seems that a 6000-plus stitch count is, as GloriaHanlon put it, “optimism”).Īs training progressed, and as I tried some higher-performance models, SkyKnit improved. Then, not knowing if they had produced anything remotely knittable, I started posting the patterns. I gave the knitting patterns to a couple of neural networks that I collectively named “SkyKnit”. JC Briar exported another 4728 patterns from the site. The knitters helped me crowdsource a dataset of 500 knitting patterns, ranging from hats to squids to unmentionables. (When asked how I should describe them, one wrote “don’t forget the glitter and swearing!”)Īnd so, we embarked upon Operation Hilarious Knitting Disaster. She sent me to the Ravelry knitting site, and to its adults-only, often-indecorous LSG forum, who as you will see are amazing people. I knew almost nothing about knitting when sent me the suggestion one day. One of the toughest problems I’ve ever tried? Knitting patterns. When the problem is tough, the results are mixed (there was that one candy heart that just said HOLE). I’ve trained neural networks to generate new paint colors, new Halloween costumes, and new candy heart messages. I, however, like to give them silly datasets. They power corporate finances, recognize faces, translate text, and more. What’s fun about neural networks is they learn by example - give them a bunch of some sort of data, and they’ll try to figure out rules that let them imitate it. I use algorithms called neural networks to write humor.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |