Hacker News Reader

Another way to think about it: every single user of Claude is paying an extra tax in every single request

Well the system prompt is probably permanently cached.

Takes up a portion of the context window, though

And the beginning of the context window gets more attention, right?

On API pricing you still pay 10% of the input token price on cache reads. Not sure if the subscription limits count this though.

And of course all conversations now have to compact 80 tokens earlier, and are marginally worse (since results get worse the more stuff is in the context)

Isn't it basically the same as paying dust to crypto exchanges when making a transaction - it's so miniscule that it's not worth caring about?

Reply on news.ycombinator.com