Re:The LLama Effect: Leak Sparked a Series of Open Source Al...
by blatant303 on Sunday April 09, 2023 @08:26PM
(#35507820)
I asked GPT4 to draw a dog or a skull in openscad and even though the end result was buggy, commenting things in the code here and there and making some volumes transparent I figured out he got it okay. For instance the dog had two eyes two ears one long nose (potatoids). It understood the symmetry of both pairs but was unable to place them at the right place. It's not like it was just misaligned, things were in the wrong planes, but they where there. As if he hadn't understood a face is like one face of a cube.
[ Parent
| on HN ]
Re:The LLama Effect: Leak Sparked a Series of Open Source Al...
by j5155 on Sunday April 09, 2023 @11:40PM
(#35508963)
I think things like this (or simpler things like asking ChatGPT for ascii art of a circle) really show the difference between LLMs and humans. The issue is that it’s a language model rather then an image one, so it doesn’t understand the concept of ‘looks like a dog’.
Re:The LLama Effect: Leak Sparked a Series of Open Source Al...
by alpaca128 on Monday April 10, 2023 @03:58AM
(#35510126)
Image models don't understand it either, they only know the typical "look" of something but not the correct proportions or number of parts. If you have the word "wheel" in the prompt they might turn every circle-like shape in the image into a car wheel because it cannot selectively apply parts of the prompt to parts of the image.
At least the few models I tinkered with all had this issue, and without some additional guidance that understands scene composition and anatomy/proportions in three dimensions this probably won't fundamentally improve.
Re:The LLama Effect: Leak Sparked a Series of Open Source Al...
by blatant303 on Monday April 10, 2023 @06:56AM
(#35510971)
I got it to extrude a cylinder into a sinusoidal, guiding it by feeding it back screenshots of the scene converted to ascii.