> affecting less than 5% of users based on current usage patterns.

Affecting 5% of users to me sounds like it affects pretty much everyone who got some value out of the tool and is not a casual coder.

I dont know if running an agent 24/7 means you are "better" than casual coder. Code quality is still a thing, HITL i believe in still (not buying complete agent/mcp hype), I don't know if using more resources = extracting more value atm

Emphasis on “and”.

> it affects pretty much everyone who got some value out of the tool AND is not a casual coder.

I didn’t mean casual in the negative sense, so there is no “better”, there is only casual and not casual.

My theory is that 5% sounds like a small number until you realize that many people just tried it and and didn’t like it, forgot to cancel, have it paid by their employer wishing for 100x improvements, or most people have found AI useful only in certain scenarios that they face every once in a while etc.

I don't really get how those 24/7 agents should work. Claude code is the first tool that gives me really good LLM code, but it needs A LOT of guidance. I even interrupt it often, to stop it following through on bad ideas.

3 hours of Opus usage per work day will be exhausted fast.

I don't think it's that simple. We'll see though, I am very curious if I'm in that 5% or not.

We do not know if that is less than 5% of users or less than 5% of paid users?

We do know that PR teams enjoy framing things in the most favorable light possible.

We do, they're paid users. These limits are regarding the usage of the paid plans.

It's talking about subscriptions, which implies paid users.

Let's hope that's true, and not some statistics trick.

I certainly am!

This seems to be the exact opposite?

The writing is on the wall, we just need to read it. Fixed price offerings will be either gone or neutered.

Why? There are a lot of products where fixed price offerings can exist, like internet access in many parts of the world. The way that Anthropic implemented this change and how they explain it, hints that this could work very much the same: There is be a level of borderline abusers that need to be reigned in. The rest are a few power users that are subsidized by a lot of normal users.

I am not saying this is what must happen here, but I see no effort to substantiate why it could not.