I'm guessing less than 5% of the users are just letting Claude Code run in an autonomous loop making slop. I tried this too: and Opus 4 isn't good enough to run autonomously yet. The Rube Goldberg machine needs to be carefully calibrated.
Claude Code weekly rate limits
111–120 of 724 posts
Re: Claude Code weekly rate limits
#112I'm well within the 95%. I might lack an imagination here, but... What are you guys doing that you hit or exceed limits so easily, and if you do... Why does it matter? Sometimes I'd like to continue exploring ideas with Claude, but once I hit the limit I make a mental note of the time it'll come back and carry on planning and speccing without it. That's fine. If anything, some time away from the slot machine often he…
I agree. I'm on the base plan, yet to hit any limits. The bottleneck is my ability to review the code it writes, and to write prompts detailed enough for the output to be useful to me. I assume that the people hitting limits are just letting it cycle, but doesn't that just create garbage if you don't keep it on a tight leash? It's very eager but not always intelligent.
I think this is it. They use it like a slot machine, and when something isn't quite what they wanted, they provide broad instructions to refine and do better. Progress is slow and questionable, but anticipation and (sometimes) reward is increased.
The issue could be, in part, that a lot of users don't care to be efficient with token usage and maintaining condensed, efficient, focused contexts to work with.
Re: Claude Code weekly rate limits
#113I'm well within the 95%. I might lack an imagination here, but... What are you guys doing that you hit or exceed limits so easily, and if you do... Why does it matter? Sometimes I'd like to continue exploring ideas with Claude, but once I hit the limit I make a mental note of the time it'll come back and carry on planning and speccing without it. That's fine. If anything, some time away from the slot machine often he…
Opus + extended thinking + deep research = 3-5 messages/reports per five hour limit. That’s the fastest way I’ve found to blow through the Pro plan. Some stuff I’ve used it for in the last day: figuring out what a family member needs for FAFSA as a nontraditional student, help identify and authenticate some rare first editions and incunabula for a museum collection I volunteer at, find a list of social events in my a…
"find a list of social events in my area"
Isn't this something you can do with a simple Google search? Or Perplexity?
No need to shove by far the most expensive LLM (Claude Opus 4) at it.
Re: Claude Code weekly rate limits
#114Confused on the Max 5x vs Max 20x. I'm on the latter, and in my email it says:
> "Most Max 20x users can expect 240-480 hours of Sonnet 4 and 24-40 hours of Opus 4 within their weekly rate limits."
In this post it says:
> "Most Max 5x users can expect 140-280 hours of Sonnet 4 and 15-35 hours of Opus 4 within their weekly rate limits."
How is the "Max 20x" only an additional 5-9 hours of Opus 4, and not 4x that of "Max 5x"? At least I'd expect a doubling, since I'm paying twice as much.
Re: Claude Code weekly rate limits
#115Earlier quoted context omitted.
Unlimited works well for everything that is “too cheap to meter”. Internet, text messages, etc are roughly that: the direct costs are so cheap. That’s not the case with LLM’s at this moment. There are significant direct costs to each long-running agent.
Internet and SMS used to be expensive and metered until they weren't thanks to technological advances and expanded use. I think LLMs will follow the same path, maybe on a shorter timespan.
They were not expensive to operate, they were only expensive for consumers
Re: Claude Code weekly rate limits
#116Hm. I run Claude Code in several containers, though generally only one is active at a time. I wonder if they’ll see that as account sharing?
This is a very common usage pattern, I don't think they will restrict that. The daily limits are probably there to fix the account sharing issue. For example I wanted to ask a friend who uses the most expensive subscription for work, if I could borrow the account at night and on weekends. I guess that's the kid of pattern they want to stop.
No. They're just desperately trying to limit the number of tokens burned per $200/mo account. It's trivial to burn 1-3x that dollar amount per DAY even before you're loaning your account out to friends in different timezones. And as ccusage will show, if you were paying API pricing rates your $200/mo plan would consume closer to $3-5k/mo in "credits".
Somehow you're "not allowed" to run your account 24/7. Why the hell not? Well because then they're losing money. So it's "against their ToS". Wtf? Basically this whole Claude Code "plan" nonsense is Anthropic lighting VC on fire to aggressively capture developer market share, but enough "power users" (and don't buy the bullshit that it's "less than 5%") are inverting that cost:revenue equation enough to make even the highly capitalized Anthropic take pause.
They could have just emailed the 4.8% of users doing the dirty, saying "hey, bad news". But instead EVERYONE gets an email saying "your access to Claude Code's heavily subsidized 'plans' has been nerfed".
It's the bait and switch that just sucks the most here, even if it was obviously and clearly coming a mile away. This won't be the last cost/fee balancing that happens. This game has only gotten started. 24/7 agents are coming.
Re: Claude Code weekly rate limits
#117"... and advanced usage patterns like running Claude 24/7 in the background" this is why we can't have nice things
All of these AI services tell everyone how amazing AI is, it can run things, solve things on its own, while the developers are drinking coffee or sleeping. Some developers could actually do that with the service they paid for, fully in agreement with the terms and now it is their fault?
"they paid for"
$100 doesn't even cover the electricity of running the servers every night, they were abusing a service and now everyone suffers because of them.
Re: Claude Code weekly rate limits
#118I'm not sure how this will play out long term, but I really am not a fan of having to feel like I'm using a limited resource whenever I use an LLM. People like unlimited plans, we are used to them for internet, text messaging, etc. The current pricing models just feel bad.
The Sonnet usage does not really look limited at 240-480 hours per week (a week has 168 hours in it). Opus at 24-40 looks pretty good too. A little hard to believe they aren't losing a bunch of money still if you're using those limits tbh.
Pretty sure they are still losing money on it, which is great for us. And these limits wouldn't even be happening if there weren't people bragging about having their CC running constantly for 30 hours writing 2 million lines of (doubtless bad) code. And sharing accounts to try to get even MORE usage. It's all that swarm guy tbh and he's proud of it.
Re: Claude Code weekly rate limits
#119Earlier quoted context omitted.
I'm ok using a limited resource _if_ I know how much of it I am using. The lack of visible progress towards limits is annoying.
npx ccusage@latest I'm assuming it'll get updated to include these windows as well. Pass in "blocks --live" to get a live dashboard!
Package page (with screenshot) https://www.npmjs.com/package/ccusage
Re: Claude Code weekly rate limits
#120I'm not sure how this will play out long term, but I really am not a fan of having to feel like I'm using a limited resource whenever I use an LLM. People like unlimited plans, we are used to them for internet, text messaging, etc. The current pricing models just feel bad.
I'm ok using a limited resource _if_ I know how much of it I am using. The lack of visible progress towards limits is annoying.
You can't really predict usage of output tokens, too, so this is especially concerning