dioscuri: post-training for truth debunks the 'LLMs just imitate human text' canard

dioscuri · x · 2026-11-19

A favourite canard of AI sceptics is that LLMs merely imitate human text, but dioscuri argues that post-training for truth debunks this: even when most humans get a question wrong, models are trained to get it right. Studying for exams teaches you real facts, not just what examiners expect to hear.

Original post →

More from AGI Musings

AGI Musings channel →