alt Hacker NewsLLMs are inherently text-based. For physical labor, some other deep-learning model will be used.
Replies
dyauspitr • yesterday at 8:43 PM
No, they are input and output based. They work with tokens/bits which could be anything. It can be a paragraph of text or it can be a bitstream for actuators. This isn’t science fiction. It’s happening right now.
Tokens don't need to represent text.
They are sequence to sequence models.