factual

Marie Curie prompt reveals implicit task inference

When a prompt supplies Einstein is German and Gandhi is Indian before asking Marie Curie is..., the model infers the task pattern and answers French, and studies using mixtures of hidden Markov models show this resembles implicit Bayesian inference over candidate tasks.

factualpending

Speaker

Chandra Sripada

Evidence Quote

“They use hidden Markov models, mixtures of them, and they show the model is doing something like implicit Bayesian inference. It's got a hypothesis about what task is being asked.”

Source

363 | Chandra Sripada on How LLMs and Humans are Cognitive Cousins— Sean Carroll's Mindscape
Created: 11/17/2026, 6:53:48 AM

Your notes

Loading notes...