Generative AI’s crippling and widespread failure to induce robust models of the world Highlight

LLM are giant, opaque black boxes with no explicit models of at all. Part of what it means to say that an LLM is a black box is to say that you can’t point to a model of a particular set of facts etc inside. (Many people realize that LLMs are “black boxes”, but don’t quite understand this important implication.)
A whole field known as “mechanistic interpretability” has tried to derive (or infer) world models from LLMs, but with very limited success.