causal
Models Lack Memory Scaffolding for Salient Facts
Current models are not good at knowing which memories to store because their training only optimizes next-word prediction; unlike humans who actively construct memorable summaries, models lack the opportunity to do so, and memory scaffolding remains very primitive.
causalpending
Speaker
Trenton BrickenEvidence Quote
“Memory scaffolding in general is just very primitive right now.”
Created: 6/13/2026, 3:36:46 AM
Your notes
Loading notes...