How I use LLMs to learn complex topics

Re:How I use LLMs to learn complex topics by bumby on Sunday August 09, 2026 @10:55PM (#49238715)

I’m curious where you get the estimate that humans hold “like four” parameters in their mind at once?

[ Parent | on HN ]

Re:How I use LLMs to learn complex topics by btown on Sunday August 09, 2026 @11:33PM (#49238927)

Cowan (2001) is an oft-cited paper proposing three to five "chunks" of capacity in human attention: https://www.cambridge.org/core/journals/behavioral-and-brain...

The full PDF is worth a read (Figure 1 may be of interest to many here): https://www.cambridge.org/core/services/aop-cambridge-core/c...

If "attention is all you need" then it's something we do indeed lack, in comparison to LLMs! But it's an interesting question: might machine cognition benefit from similar bottlenecks in an attention algorithm? Advancements like Kimi Linear seem to indicate that we're far from the finish line: https://arxiv.org/abs/2510.26692

[ Parent | on HN ]

Re:How I use LLMs to learn complex topics by rDr4g0n on Sunday August 09, 2026 @10:58PM (#49238743)

updated the comment. i meant four "concepts". i dont reason about my own thinking in terms of parameters.

[ Parent | on HN ]