<p>ChatGP can write knitting patterns</p>
<p>ChatGP can write knitting patterns</p>
Maybe I'm the only one who didn't know this, but it only just occurred to me to try - and it worked!
I gave it needle size, ply and the garment size I wanted - as well as asking for Australian sizing and instructions (so you'll need to change that for whatever you're used to) and from what I could see it was pretty good. Haven't actually tried it but I may for a small project and see how it goes.
Edit to say that I'm very aware of chatgpts limits (I work in a field where it's being abused) but thought it was an interesting idea. Simplicity would be key. I'd consider myself a beginner this might be a good way of creating small simple projects. Or nonsense! I have bags of cheap wool that I got through my local buy nothing group so I'm always up for a bit of experimentation.
ChatGPT has tokenized versions of knitting patterns scraped from the internet that it can attempt to reconfigure into something resembling a knitting pattern. I don’t think it has the ability to keep track of the number of stitches you have open or the knowledge of how different stitches will interact and build on each other. You will likely have to make corrections or modifications.
I saw someone generate a crochet pattern that they were able to actually create, and it was just a little sphere with nubs coming off of it. I think this it might be a fun experiment, but I would not expect anything impressive.
That actually sounds fun. Follow Ai nonsense and see what you end up with. Like those people who 3d designed their kid's drawings.
Yeah, for sure! I’ve done a couple of attempts with toy programs to randomly generate lace patterns, which is a little similar and was really fun. As long as you go into it not expecting it to be perfect or even match what your prompt was, I bet you could have a lot of fun!
Interesting! We had a post here a while back experimenting with this and getting terrible results, so I wouldn't be trusting it with any expensive yarn just yet! But at the rate these things are developing, maybe there's been significant progress since then.
Would definitely be interested to see how the pattern works up!
AI doesn't understand what it's doing. It's like a second grader savant that has read every book. If you ask it to write a story about or draw a man playing using a baguette as a baseball bat, you have a significant chance to get something with the animal "bat" in it and the baguette not being used to hit a ball.
One could almost say it's intelligence is artificial
You think so? https://chat.openai.com/share/3e9d7f52-1a7d-4f20-b707-6aa51ed1c7d6
Please provide your definition of "understanding" and explain how it is different in humans than in ML models. Please explain the functional differences in your mind that separate (for example) a human looking at and explaining the joke in a meme, and a Machine Learning model doing the same thing.
Of course they're not human-level yet in terms of adaptability, but the more I think about the above the more convinced I am that humans just have much, much larger "context windows" than current machine learning models, and that's an advantage that is already eroding quickly.
Edit: All I want is for someone to clearly show humans do it differently than these new machine learning models. That shouldn't be too hard, if it's so fundamental and obvious. Or, could it be that "understanding" is a nebulous term that's actually quite hard to define?
Specifically for knitting - can a machine be trained on the muscle movements involved in knitting? The feeling of tension in your yarn, how many stitches you feel comfortable crowding on that needles, how you need to move your yarn out of the way?
Knitting has some complicated stitches and movements that I don’t think have been replicated by machine. Crochet is not able to be produced by machine. I think that there is a kinesthetic understanding necessary for a sort of “AI” to really understand knitting which hasn’t been demonstrated by any models I’ve seen. Maybe someone will put sensors on someone’s muscles and try to “tokenize” the mechanics, but I don’t think that’s been done yet.
Writing patterns is a skill. Professional pattern writers test their patterns and modify them, calling heavily on their knowledge of that kinesthetic understanding. You could not just read a bunch of pattern books and write your own without having done the activity. You would need to be choosy in your pattern books too - anyone who does historical knitting/crochet/fiber work can tell you that there are lots of confusing, ambiguous, or wrong instructions! Can you consistently discriminate between different notation styles? Do you have opinions on magic loop versus ch6? These are things that I don’t think have been tokenized - and since most of that is ambiguity in human communication, where is “AI” supposed to pick this up from?
That’s awesome! But be careful, GPT4 might probably be able to make this. I’d suggest pasting the recipe back in and ask it to validate out loud and show its reasoning and math (if any). Then you could get one that works🙂