fwiw this problem already exists with my more junior co-workers. and also my own code that I write when exhausted!
if you have trusted processes for review and aren't always rushing out changes without triple checking your work (plus a review from another set of eyes), then I think you catch a lot of the subtler bugs that are emitted from an LLM.
there are a million million subcultures with pretty stark differences in taste/aesthetics that you can dig up on the internet. looking at what's grossing in mega-dense populations of millions of people then yeah, perhaps in aggregate at large N, things their individuality -- surprise?
there are parts of every major city that feel the same, but if you're willing to take a train out 45 minutes in any direction without google maps, i'm willing to bet you get into spaces that are incredibly local!
A new-ish field of "mechanistic interpretability" is trying to poke at weights and activations and find human-interpretable ideas w/in them. Making lots of progress lately, and there are some folks trying to apply ideas from the field to Alphafold 2. There are hopes of learning the ideas about biology/molecular interactions that the model has "discovered".
Perhaps we're in an early stage of Ted Chiang's story "The Evolution of Human Science", where AIs have largely taken over scientific research and a field of "meta-science" developed where humans translate AI research into more human-interpretable artifacts.
they have a blog hinting at some answers as to "why": https://turso.tech/blog/introducing-limbo-a-complete-rewrite...