Post
Ethan Mollick @emollick · Nov 17, 2023
  • From Twitter

This paper is a nice summary of what GPT-4’s vision capability can and can’t do It does an impressive job on overall “reasoning” about images, but also gets details wrong and is open to adversarial attacks as it focuses on lot on the text in the image

Recommended by 1 person
1 mention
1 like
Share on Twitter Repost
Replies
Reply
No replies yet