Hacker News new | ask | show | jobs
by otabdeveloper4 217 days ago
That's because when they say "long context window" they're lying and they actually mean that they support a long input prompt that is still compressed into a small context window. (Typically by throwing out tokens in the middle.)

An actually large context window is impossible due to how LLM attention works under the hood.

1 comments

Mamba-2 enters the chat.