Re:I made ChatGPT take an SAT Test
by Terretta on Saturday December 03, 2022 @01:45PM
(#33846096)
> What's missing from these models is everything related to visual or spatial information (that is not encoded in text). I assume that there will be eventually be something like ChatGPT/InstructGPT where part of the input data is images and or videos, with and without captions. So it would have a way of connecting the language to the spatial (and temporal).
Is that missing though? Dall-E is the next tab over. You can image to CLIP, and image to image is not just visual, it involves that language to spatial and visual step:
"CLIP (Contrastive Language-Image Pre-Training) is a neural network trained on a variety of (image, text) pairs. It can be instructed in natural language to predict the most relevant text snippet, given an image, without directly optimizing for the task, similarly to the zero-shot capabilities of GPT-2 and 3."
Is that missing though? Dall-E is the next tab over. You can image to CLIP, and image to image is not just visual, it involves that language to spatial and visual step:
"CLIP (Contrastive Language-Image Pre-Training) is a neural network trained on a variety of (image, text) pairs. It can be instructed in natural language to predict the most relevant text snippet, given an image, without directly optimizing for the task, similarly to the zero-shot capabilities of GPT-2 and 3."
https://github.com/openai/CLIP
Folks who've been playing with Dall-E and getting coherent images seem to be adept at prompting GPT-3 and getting coherent answers.