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 SripadaEvidence Quote
“this amplifies the inferential power of the model”
Created: 11/17/2026, 6:53:48 AM
Your notes
Loading notes...