This seems like a worthwhile listen. As it stands I think that LLMs sort of suck at this. Either that or I don't understand what analogous thinking is or people who use LLMs to facilitate this kind of thinking are bad at it too.
But I think that LLMs are bad at something that has to do with taking seemingly disparate concepts and assimilating one into the other to convey a novel idea.
Like these articles...
<https://spectrum.ieee.org/jimi-hendrix-systems-engineer>
<https://zed.dev/blog/agentic-xanadu>
...are anything but convincing once you read past the gravitas that the LLM lends the prose.
> As it stands I think that LLMs sort of suck at this.
Metaphors are at the core of LLM cognition too via vector embeddings. The distance between embeddings is an inverse measure of their metaphorical attachment. That lets AIs scrape meaning from natural language, which demonstrates that natural language is an encoded sequence of metaphors.
I'm going to need a weekend or two to figure out what this means.
Have you played with a vector databases and have them explained yet? The grandparent comment is only explaining that concept.
Nope! But I'm soaking all of this in and I appreciate these nudges.
And after some thought I'm curious whether this means that LLMs ought to be adept at forming new metaphors as opposed to handling pre-existing ones.