The 'stochastic parrot' debate reignites: mechanistic interpretability falsified its generalization claim

burny_tech · x · 2026-09-22

Rowan Cheung, responding to Jack Clark, defends Emily Bender's "stochastic parrot" argument: it never claimed LLMs would never become capable, only that statistical language generation isn't grounded understanding and that people would mistake fluency for comprehension — better capabilities make the warning more important, not refuted.

burnytech adds a technical angle: a general form of the stronger claim — that models learn no internal structure correlated with the ground-truth structure of the data — has been falsified, in a limited way, by mechanistic interpretability results. A substantive skirmish in the ongoing debate over whether LLMs "understand."

Related event: Jack Clark Calls "Stochastic Parrot" a Cognitive Virus, Sparking Fresh Debate(19 posts)→

Original post →

More from AGI Musings

AGI Musings channel →