Hacker News new | ask | show | jobs
by mlhpdx 1188 days ago
Most people don’t understand the technology and maths at play in these systems. That’s normal, as is using familiar words that make that feel less awful. If you have a genuine interest in understanding how and why errant generated content emerges, it will take some study. There isn’t (in my opinion) a quick helpful answer.
1 comments

I genuinely want to understand whether there’s a meaningful difference between non-hallucinatory and hallucinatory content generation other than “real world correctness”.
I’m far from an expert but as I understand it the reference point isn’t so much the “real world” as it is the training data. If the model generates a strongly weighted association that isn’t in the data, and shouldn’t exist perhaps at all. I’d prefer a word like “superstition”, it seems more relatable.