I measured epistemic quality in 11 LLMs. Baseline was terrible. One context injection made it 10x better. Then things got weird.
I've been obsessing over one question for 20 years: how do you know what you actually know vs what you think you know? Not philosophically - practically. I tracked how theories break across domains (medicine, law, physics, finance, statistics, biology, engineering) and noticed the same patterns at every breaking point....
Mar 171