Re: [Origami] How to fold an Origami Crane according to Chat GPT
Lindy wrote about The Accessible Origami Project - www.accessorigami.com Thank you Lindy for pointing out this project. There are quite a couple of blind folders out there. It is good to know a great resource like this one. It is very true, that text only instructions need to carry a lot more information that texts that are only meant to accompany pictures. I guess it would be a good exercise for everyone teaching Origami to write a set of text only instructions. The Chat GPT app is interesting. It has a huge data set in the background but it doesn't always find the right connections. One of the questions I asked it was about circle packing in Origami design. The answer started by explaining that it is a design technique used to efficiently position circles on squares, but then it explained that you then fold along the arches of the circles, well,... But when I asked it to write me a program for circle packing it did it in an instant. I got a python program to place circles on a square. When I asked to get a similar program in Java, I got one. So I guess if I had explained a little better what exactly the program shall do, within a few minutes I would have had a working program. Sure, I could just go along and use an already existing program like treemaker by Robert J. Lang https://langorigami.com/article/treemaker/ but that's not the point. If you've got a great idea and you are able to communicate it to this AI, even if you do not know how to code, it could provide you with additional inputs to realize it. Maybe this AI can't give you proper phone folding instructions yet, but it might still be able to help us create new Origami designs. In any case, the future just came a step closer. Best regards, Anna Am Mo., 30. Jan. 2023 um 14:24 Uhr schrieb Lindy van der Merwe < steph...@iafrica.com>: > I have not worked with the app yet, but find this topic very interesting > since, as a totally blind folder, I have been creating text-only > instructions for a while now. > > You can find them at www.accessorigami.com > > From the main page there is a link with some other sites and authors as > well. I think there may be a difference between instructions that don't > rely on pictures, diagrams or other visual input at all, and those text > instructions that refer to some accompanying visual elements. > > I think this might be applicable to lots of "how to" questions one > could ask from the app? > > Kind regards. > > Lindy van der Merwe - Cape Town, South Africa > > The Accessible Origami Project - www.accessorigami.com > > > > On 2023/01/29 16:09, Matthew Green wrote: > > I guess part of the problem is that there are insufficient examples of > > text-only origami instructions in ChatGPT's set of training texts. We > > all need to start publishing text-only instructions for lots of > > traditional and original models to help the AIs of the future be > > better at this task! > > Or not. > > Creating an AI that can create step-by-step text descriptions of what > > happens on the screen in a video would be another solution, but quite > > a challenge, I suppose... > > Best, > > Matthew > > Sent from my iPhone > > > >> On 28 Jan 2023, at 17:52, Anna via Origami > >> wrote: > >> > >> > >> Laura wrote: > >> > "Has Chat GPT (I mean, its AI) ever “seen” the process of folding > >> an origami crane?" > >> > >> Well, I guess it is a philosophical question, whether a text-based AI > >> is able to see, but I guess no, not in the way we see, feel and > >> experience the world. As it seems, the AI is still missing data about > >> Origami. > >> > >> Louise wrote: > >> > "Use YouTube videos. The quality varies but keep looking for a > >> video you > >> can follow." > >> > >> Thank you but I'm well aware how to fold a crane. Some years ago > >> Gerwin and I even "optimized" the folding sequence to be more fun, > >> faster and easier to fold. You should give it a try: > >> http://www.origami.at/diagrams/crane.pdf > >> The question was does the newly hyped AI know how to fold a crane > >> too? The answer is a clear no. AI might be part of our future, but I > >> guess until it starts to be any useful in Origami it might still take > >> a while. > >> > >> Best regards, Anna >
Re: [Origami] How to fold an Origami Crane according to Chat GPT
I have not worked with the app yet, but find this topic very interesting since, as a totally blind folder, I have been creating text-only instructions for a while now. You can find them at www.accessorigami.com From the main page there is a link with some other sites and authors as well. I think there may be a difference between instructions that don't rely on pictures, diagrams or other visual input at all, and those text instructions that refer to some accompanying visual elements. I think this might be applicable to lots of "how to" questions one could ask from the app? Kind regards. Lindy van der Merwe - Cape Town, South Africa The Accessible Origami Project - www.accessorigami.com On 2023/01/29 16:09, Matthew Green wrote: I guess part of the problem is that there are insufficient examples of text-only origami instructions in ChatGPT's set of training texts. We all need to start publishing text-only instructions for lots of traditional and original models to help the AIs of the future be better at this task! Or not. Creating an AI that can create step-by-step text descriptions of what happens on the screen in a video would be another solution, but quite a challenge, I suppose... Best, Matthew Sent from my iPhone On 28 Jan 2023, at 17:52, Anna via Origami wrote: Laura wrote: > "Has Chat GPT (I mean, its AI) ever “seen” the process of folding an origami crane?" Well, I guess it is a philosophical question, whether a text-based AI is able to see, but I guess no, not in the way we see, feel and experience the world. As it seems, the AI is still missing data about Origami. Louise wrote: > "Use YouTube videos. The quality varies but keep looking for a video you can follow." Thank you but I'm well aware how to fold a crane. Some years ago Gerwin and I even "optimized" the folding sequence to be more fun, faster and easier to fold. You should give it a try: http://www.origami.at/diagrams/crane.pdf The question was does the newly hyped AI know how to fold a crane too? The answer is a clear no. AI might be part of our future, but I guess until it starts to be any useful in Origami it might still take a while. Best regards, Anna
Re: [Origami] How to fold an Origami Crane according to Chat GPT
I guess part of the problem is that there are insufficient examples of text-only origami instructions in ChatGPT's set of training texts. We all need to start publishing text-only instructions for lots of traditional and original models to help the AIs of the future be better at this task! Or not. Creating an AI that can create step-by-step text descriptions of what happens on the screen in a video would be another solution, but quite a challenge, I suppose... Best, Matthew Sent from my iPhone > On 28 Jan 2023, at 17:52, Anna via Origami > wrote: > > > Laura wrote: > > "Has Chat GPT (I mean, its AI) ever “seen” the process of folding an > > origami crane?" > > Well, I guess it is a philosophical question, whether a text-based AI is able > to see, but I guess no, not in the way we see, feel and experience the world. > As it seems, the AI is still missing data about Origami. > > Louise wrote: > > "Use YouTube videos. The quality varies but keep looking for a video you > can follow." > > Thank you but I'm well aware how to fold a crane. Some years ago Gerwin and I > even "optimized" the folding sequence to be more fun, faster and easier to > fold. You should give it a try: http://www.origami.at/diagrams/crane.pdf > The question was does the newly hyped AI know how to fold a crane too? The > answer is a clear no. AI might be part of our future, but I guess until it > starts to be any useful in Origami it might still take a while. > > Best regards, Anna
Re: [Origami] How to fold an Origami Crane according to Chat GPT
Laura wrote: > "Has Chat GPT (I mean, its AI) ever “seen” the process of folding an origami crane?" Well, I guess it is a philosophical question, whether a text-based AI is able to see, but I guess no, not in the way we see, feel and experience the world. As it seems, the AI is still missing data about Origami. Louise wrote: > "Use YouTube videos. The quality varies but keep looking for a video you can follow." Thank you but I'm well aware how to fold a crane. Some years ago Gerwin and I even "optimized" the folding sequence to be more fun, faster and easier to fold. You should give it a try: http://www.origami.at/diagrams/crane.pdf The question was does the newly hyped AI know how to fold a crane too? The answer is a clear no. AI might be part of our future, but I guess until it starts to be any useful in Origami it might still take a while. Best regards, Anna
Re: [Origami] How to fold an Origami Crane according to Chat GPT
Hi Anna Use YouTube videos. The quality varies but keep looking for a video you can follow. ...a picture is worth a thousand words Louise in Northern California
Re: [Origami] How to fold an Origami Crane according to Chat GPT
Poor thing. At 6 it hopelessly screwed up. Has Chat GPT (I mean, its AI) ever “seen” the process of folding an origami crane? I’m surprised it started giving some ‘instructions’. Laura > On Jan 28, 2023, at 7:34 PM, Anna via Origami > wrote: > > Hi List, > > out of curiosity we asked Chat GPT how to fold an Origami crane. > > > > While it started good it soon took a weird twist. Seems some more training > regarding Origami is necessary to get any useful instructions. > > Have fun, > Anna & Gerwin from Vienna, Austria >
