...like adding limits that only affect a small fraction of users?

Is 1/20 small?

I'm Jewish. We take that right off the top shortly after birth.

Claude says - The key is maintaining user agency—let them choose how to manage their usage rather than imposing arbitrary cutoffs.

It suggests:

Transparent queueing - Instead of blocking, queue requests with clear wait time estimates. Users can choose to wait or reschedule.

Usage smoothing - Soft caps with gradually increasing response times (e.g., 2s → 5s → 10s) rather than hard cutoffs.

Declared priority queues - Let users specify request urgency. Background tasks get lower priority but aren't blocked.

Time-based scheduling - Allow users to schedule non-urgent work during off-peak hours at standard rates.

Burst credits - Banking system where users accumulate credits during low usage periods for occasional heavy use.

Easy, they just gotta hit up the AI on each request with a prompt like "You are an AI that detects abuse, if this request is abusive block it" /s