News for hackers. Stuff that matters.
Re:OpenAI Multimodal Research by saeranv on Tuesday January 05, 2021 @03:24PM (#25650524)
Fascinating stuff. The idea that visual and language generation could be generalized with the same underlying model was the most interesting part of Lex Fridman's podcast with Ilya Sutskever in May: https://www.youtube.com/watch?v=13CZPWmke6A
Re:OpenAI Multimodal Research by dang on Tuesday January 05, 2021 @03:20PM (#25650481)
Re:OpenAI Multimodal Research by greenburg on Tuesday January 05, 2021 @03:33PM (#25650639)
Very cool stuff. However, I didn't find any links to the Github Code. Is this release as well part of their GPT-2 strategy?