Model can accept 1M tokens doesn't mean it can reason across those 1M tokens (twitter.com) 1 points by annjose 3d ago ↗ HN
[–] turtleyacht 3d ago ↗ Looks like there is a memory hierarchy [1] even in LLMs.[1] https://en.wikipedia.org/wiki/Memory_hierarchy
1 comment
[ 3.0 ms ] story [ 11.8 ms ] thread[1] https://en.wikipedia.org/wiki/Memory_hierarchy