Angelina YangFounder and Host, TwoSetAI · AI builder for visibility and discoverability

Hallucination is Just a Selection Error

19 Aug 2026 · 1 min

Watch on YouTube

0:34

Hallucinations in AI aren't mysterious failures but selection errors from an enormous output space. Constrain the outputs to a smaller, truly discrete set and the hallucinations vanish. The model isn't inventing information, it's just picking from too many options.

Chapters

Will hallucination be a problem here? Hallucination is an interesting word. Hallucination only matters on the output itself. So if you bound the output into discrete outputs, then hallucination is actually just a selection error. It's just such large discreteness that it doesn't feel discrete. And so if we reduce that dimensionality down to something that truly does feel discrete, then that's how determinism will work. Hallucinations only feel like a hallucination because the possible set of outputs is so large that it feels like it's just making things up.