alt Hacker NewsThe usage metering is just so incredibly inconsistent, sometimes 4 parallel Opus sessions for 3 hours straight on max effort only uses up 70% of a session, other times 20 mins / 3 prompts in one session completely maxes it out. (Max x20 plan) Is this just a bug on anthropic side or is the usage metering just completely opaque and arbitrary?
It's something strange because i never have these issues. I often run two in parallel (though not all day), and generally have something running anytime i look at my laptop to advance the steps/tasks/etc. Usually i struggle to hit 50% on my Max20.
Heck two weeks ago i tried my hardest to hit my limit just to make use of my subscription (i sometimes feel like i'm wasting it), and i still only managed to get to 80% for the week.
I generally prune my context frequently though, each new plan is a prune for example, because i don't trust large context windows and degradation. My CLAUDE.md's are also somewhat trim for this same fear and i don't use any plugins, and only a couple MCPs (LSP).
No idea why everyone seems to be having such wildly different experiences on token usage.