alt Hacker NewsIsn’t it at least equally likely that one would be more prone to confusion if one was a visual thinker?
I don’t think we can infer anythin about how LLMs think based on this.
Isn’t it at least equally likely that one would be more prone to confusion if one was a visual thinker?
I don’t think we can infer anythin about how LLMs think based on this.
Right. I'm not claiming the LLM has visual imagination - I suspect that OP has it, and that ChatGPT was trained on enough text from visual thinkers implicitly conveying their experience of the world, that it's now able to correctly interpret writing like that of OP's.