top | item 47158221 (no title) thellimist | 4 days ago What do you mean? discuss order hn newest hiccuphippo|4 days ago The article says the LLM has to load 15540 tokens every time, I wonder if that can be reduced while retaining the context maybe with deduplications, removing superfluous words, using shorter expressions with the same meaning or things like that.
hiccuphippo|4 days ago The article says the LLM has to load 15540 tokens every time, I wonder if that can be reduced while retaining the context maybe with deduplications, removing superfluous words, using shorter expressions with the same meaning or things like that.
hiccuphippo|4 days ago