Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How Good Is DALL-E Mini at Origami?

origami.kosmulski.org

Post reply on HN
Print view View original

11–20 of 31 posts

Re: How Good Is DALL-E Mini at Origami?

#11

Post by blagie »

One related property of GPT-3: It's very bad at traditional computational tasks.

* "Make a list of 20 items" results in a list. The number of items is as accurate as if you asked a toddler the same question.

* If you ask GPT-3 a simple combinatorics question, it will be 100% confident in the wrong answer.

Origami is sort of the same. It takes a conceptual understanding of how paper folds, which DALL-E Mini doesn't have. It has a feel for the general origaminess of a picture.

If I showed a human being a few pieces of origami, including a paper crane, and they had never seen origami before, they'd likely result in similar pictures.

Re: How Good Is DALL-E Mini at Origami?

#12

Post by blagie »

bambax wrote: post #8
greyface- wrote: post #4

Earlier quoted context omitted.

GPT-3 already seems capable of generating SVG. I prompted it with: and it completed it to the following: which looks like this: https://i.imgur.com/sHpv4Ii.png

Yes, but that's just random SVG (xml); it would be amazing to be able to ask for specific shapes or silhouettes.

Try it! codex model.

It's pretty random. It will do a fine smiley face, for example. Most other things, it won't do.

Re: How Good Is DALL-E Mini at Origami?

#15

Post by anon_123g987 »

blagie wrote: post #11

One related property of GPT-3: It's very bad at traditional computational tasks. * "Make a list of 20 items" results in a list. The number of items is as accurate as if you asked a toddler the same question. * If you ask GPT-3 a simple combinatorics question, it will be 100% confident in the wrong answer. Origami is sort of the same. It takes a conceptual understanding of how paper folds, which DALL-E Mini doesn't ha…

Don't overestimate humans. Most people (adults, not toddlers) can't even draw a bicycle, even if they used one for most of their lives, so presumably they have a conceptual understanding of how it looks and works.

https://www.fastcompany.com/3059089/it-turns-out-its-almost-...

Re: How Good Is DALL-E Mini at Origami?

#16

Post by l33tman »

desro wrote: post #9

Some of the issues seemingly stem from the model's either poor or mis-understanding of the input language... I wonder what a fusion of DALL-E + GPT3 or LaMBDA, where the text-based models perform prompt interpretations, would look like. This may be a naïve thought as my understanding of all models mentioned is superficial at best.

The text input comprehension is (supposedly) much better in Google's "DALL-E 2", https://imagen.research.google/

Re: How Good Is DALL-E Mini at Origami?

#18

Post by thom »

I don't mean this to sound overly negative, because I absolutely think DALL-E is a killer app amongst recent AI advances. But the thing that made DALL-E astonishing is that it was... good. While DALL-E Mini mimics a lot of the technical advances and you can kind of see what it's getting at with its outputs, they're still mostly garbage. Very clever garbage! But they lack the emotional impact that - woah! - this is doing something superhuman.

Obviously the hope is that somehow this and future advances can be democratised. It was funny that Asimov's The Last Question has been posted here a couple of times recently because it makes such a big thing about world-sized computers and how advanced minicomputers would be. It's easy to read and scoff at the naivety... before realising we could easily be heading back in that direction for many impactful future technologies.

Re: How Good Is DALL-E Mini at Origami?

#19

Post by ossopite »

anon_123g987 wrote: post #15
blagie wrote: post #11

One related property of GPT-3: It's very bad at traditional computational tasks. * "Make a list of 20 items" results in a list. The number of items is as accurate as if you asked a toddler the same question. * If you ask GPT-3 a simple combinatorics question, it will be 100% confident in the wrong answer. Origami is sort of the same. It takes a conceptual understanding of how paper folds, which DALL-E Mini doesn't ha…

Don't overestimate humans. Most people (adults, not toddlers) can't even draw a bicycle, even if they used one for most of their lives, so presumably they have a conceptual understanding of how it looks and works. https://www.fastcompany.com/3059089/it-turns-out-its-almost-...

This example gets trotted out a lot but I don't really understand it. Why do we assume cyclists have a conceptual mechanical understanding of a bicycle and can remember its exact appearance? If they build or repair bicycles, sure, but the majority of people don't do that. They just have learnt how to operate one by instinct.

Re: How Good Is DALL-E Mini at Origami?

#20

Post by dr_zoidberg »

thom wrote: post #18

I don't mean this to sound overly negative, because I absolutely think DALL-E is a killer app amongst recent AI advances. But the thing that made DALL-E astonishing is that it was... good. While DALL-E Mini mimics a lot of the technical advances and you can kind of see what it's getting at with its outputs, they're still mostly garbage. Very clever garbage! But they lack the emotional impact that - woah! - this is do…

What makes DALLE Mini great is that we can all sit down and play with it, with no "oh this thing might destroy humanity" warning. A warning that most people who have worked seriously on different areas of AI find annoying for different reasons, but mainly it feels like a marketing gimmick to draw attention.

I have lots of friends who aren't related to the tech field having lots of fun playing with DALLE Mini, even though the results are terribly looking -- if they sort of resemble the prompt (and many times they do), they are ecstatic that the machine made a weird doodle about something ridiculous.

Post reply on HN