causal

Chain-of-thought scratchpad amplifies inferential power

When a model is allowed to generate hidden reasoning tokens that feed back into its context, it can solve problems like the Julia's-sisters puzzle that it gets wrong without chain of thought, and this scratchpad substantially amplifies inferential power.

causalpending

Speaker

Chandra Sripada

Evidence Quote

“this amplifies the inferential power of the model”

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...