causal
Context window as scratchpad for staged problem-solving
LLMs use the context window as a scratchpad, generating internal tokens that break complex tasks into subtasks and sub-agents, so next-word generation can support substantial staged problem-solving.
causalpending
Speaker
Chandra SripadaEvidence Quote
“these models can use the context window as a kind of scratchpad and generate internal tokens as part of what they call thinking”
Created: 11/17/2026, 6:53:48 AM
Your notes
Loading notes...