Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Can Language Models Serve as Text-Based World Simulators?. Parent comment
Don’t restrict LLMs to text. If you train one with images and text you’ll get one that understands position.
There are no comments on this comment yet.
Don’t restrict LLMs to text. If you train one with images and text you’ll get one that understands position.