Model can accept 1M tokens doesn't mean it can reason across those 1M tokens | Dark Hacker News

Dark Hacker News

new|best|ask|show|jobs

Built with the HackerNews API. Developed by LJT.AI

Note: The HackerNews API provides up to 500 stories per category

Model can accept 1M tokens doesn't mean it can reason across those 1M tokens | Dark Hacker News

Model can accept 1M tokens doesn't mean it can reason across those 1M tokens(twitter.com)

2 points by annjose 43 days ago | 1 comment

turtleyacht 43 days ago |

Looks like there is a memory hierarchy [1] even in LLMs.

[1] https://en.wikipedia.org/wiki/Memory_hierarchy