1 Comment
author

some discussion using an LLM to produce a simplified version of this post

https://docs.google.com/document/d/1k18lQy_H4M4ZCSObkFKxjzexVRtBO_GtAhAoaHkog9M/edit?usp=sharing

(makes me realise that when LLMs appear to 'hallucinate', that, actually that is all they are doing, and we notice when we reach the edge of known space that LLMs map in our language use, at least the ones I use and do not pay for seem unable to incorporate unfamiliar frameworks, or topics as LLMs peeps call them

Expand full comment