causal
Models need external notes, like Deep Research
Long-horizon work requires models to write notes outside their context window and compress information into language, as OpenAI's Deep Research does over 45 minute runs producing millions of tokens, and models must learn this from environments rather than pretraining.
causalpending
Speaker
Dylan PatelEvidence Quote
“How they did that was they enabled it to be able to write something down elsewhere and have this recall, and effectively use language to compress information that it looked at, put that off to the side”
Created: 11/16/2026, 4:01:45 AM
Your notes
Loading notes...