how do you measure "surpass"?
Re:Visual ChatGPT
by dragonwriter on Friday March 10, 2023 @10:41AM
(#35095778)
I think no one has bothered with using as many images as documents used to train GPT-3.5, to create as big of a model, and then RLHF as done to produce ChatGPT from GPT-3.5 is why image models haven’t surpassed language models.
At any level of scale of model and scale of training set, images models do surpass language models.
Re:Visual ChatGPT
by ipunchghosts on Saturday March 11, 2023 @12:05PM
(#35110262)
No way this is true. I have yet to see it. Image permutations are so easy to come by where as they are eventually infinite.
This is utterly wrong. There is a huge amount of redundancy in images compared to language. This redundancy is why image models have yet to surpass language models. In some sense, language is much easier than the vision problem.