causal
Verbatim Memory Inhibits Abstraction and Questions
Because transformers can rely on a very large verbatim working memory, they are not pushed to summarize and abstract key ideas the way humans must, and they only mimic human patterns rather than asking sharp questions or contributing genuinely new points on novel topics.
causalpending
Speaker
Yejin ChoiEvidence Quote
“it's not really pushed or challenge it to think about how to summarize the key idea... it's not going to be able to ask sharp questions”
Created: 6/13/2026, 12:23:11 AM
Your notes
Loading notes...