“Current language models fall short in understanding aspects of the world not easily described in words, and struggle with complex, long-form tasks.”

“Current language models fall short in understanding aspects of the world not easily described in words, and struggle with complex, long-form tasks.”

https://largeworldmodel.github.io/

I like the final sentence of their abstract “This work paves the way for training on massive datasets of long video and language to develop understanding of both human knowledge and the multimodal world, and broader capabilities.” 
If they succeed training data scarcity is a thing of the past. 
Hal reads lips now

Writer. Building @pinatacloud. Tinkering with a Farcaster native alternative to GoodReads: https://readcast.xyz \ https://polluterofminds.com