logoalt Hacker News

s0ck_r4wtoday at 9:22 PM2 repliesview on HN

How do a few extra requests with the same prefix make it more expensive for everyone else?


Replies

SwellJoetoday at 9:33 PM

Keeping a conversation with a very large model active requires hundreds of GB of memory. If my conversation can never be swapped out, like when I go to lunch or take an afternoon walk, that's several hundred GB not available for other users. If everybody does that, Anthropic needs even more infrastructure than the quarter trillion dollars in infra they're already using.

show 1 reply
szniotoday at 9:28 PM

you use more memory?