Hacker News new | ask | show | jobs
by brrrrrm 701 days ago
LLMs can deal with more than text. Impressive today is nothing tomorrow
1 comments
ryanackley 700 days ago
The technology that allows an LLM to "see" images and video is completely different though. It's not what is being trained on common crawl.
link
brrrrrm 700 days ago
not really. embeddings are embeddings. check out llava
link