Burkov: In-distribution vs out-of-distribution should be taught in school

burkov · x · 2026-11-22

ML author Burkov argues in a short post that the difference between in-distribution and out-of-distribution should be taught in school — pointing at the core LLM-era problem that models only reliably handle data similar to their training distribution, while users rarely realize when they've stepped outside it.

Original post →

More from AGI Musings

AGI Musings channel →