undefined | Better HN

0 pointsbrrrrrm1y ago0 comments

LLMs can deal with more than text. Impressive today is nothing tomorrow

0 comments

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.

brrrrrmOP1y ago

not really. embeddings are embeddings. check out llava

j / k navigate · click thread line to collapse

0 pointsbrrrrrm1y ago0 comments

LLMs can deal with more than text. Impressive today is nothing tomorrow

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.

brrrrrmOP1y ago

not really. embeddings are embeddings. check out llava

j / k navigate · click thread line to collapse