Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I think one of the interesting emerging properties of LLMs like ChatGPT is that they can probably see in ASCII. But they require some guidance and context see examples.


It's not too different from how vision transformers work is it?


I didn’t think of that. Good analogy !




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: