News for hackers. Stuff that matters.

A comment on Vision language models are blind. Parent comment

Re:Vision language models are blind by empiricus on Thursday July 11, 2024 @03:51AM (#40934526)
I hope you are aware of the fact that LLMs does not have direct access to the stream of words/characters. It is one of the most basic things to know about their implementation.
[ Parent | on HN ]
Re:Vision language models are blind by jordan_bonecut on Thursday July 11, 2024 @10:32AM (#40937250)
Yes, but it could learn to associate tokens with word counts as it could with meanings.

Even still, if you ask it for token count it would still fail. My point is that it can’t count, the circuitry required to do so seems absent in these models

[ Parent | on HN ]