Re:The Limits of GPT-3 and Similar Large Language Models
by boredemployee on Saturday January 07, 2023 @03:50PM
(#34292626)
>> Human babies learn by watching the world around them.
While I understood what you meant, I'd just add that babies learn by a combination of multisensory triggers (so not only _watching_)
Re:The Limits of GPT-3 and Similar Large Language Models
by tintor on Saturday January 07, 2023 @04:28PM
(#34293032)
There is VideoGPT paper. It uses small frame sizes, but that will improve with time.
Re:The Limits of GPT-3 and Similar Large Language Models
by TomSwirly on Sunday January 08, 2023 @06:58AM
(#34298358)
> a significant percentage of YouTube content [...] a world model far richer and more robust than ChatGPT’s
There are three objections to this.
The first is the astonishingly large amount of CPU power that this would take, given how high bandwidth video is. The second is that it is hard to believe that some thing really coherent could emerge from this, and certainly, it has never been shown. The third is that the world might be "richer" in terms of information-rich but seeing the world through YouTube's eyes would likely be a degrading and incoherent experience.
It would probably be insanely expensive. But I feel like it would be almost guaranteed to acquire a world model far richer and more robust than ChatGPT’s.
Human babies learn by watching the world around them. Video frame prediction feels much closer to that than text prediction, and given the wildly impressive results we are seeing with large text prediction models alone, it seems like an obvious next step.