Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code weekly rate limits

news.ycombinator.com

Post reply on HN
Print view View original

121–130 of 724 posts

Re: Claude Code weekly rate limits

#121

Post by data-ottawa »

steveklabnik wrote: post #100
qiller wrote: post #67

Earlier 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!

Oh wow, this showed me the usage stats for the period before ccusage was installed, that’s very helpful especially considering this change.

ETA: You don’t need to authenticate or share your login with this utility, basically zero setup.

Re: Claude Code weekly rate limits

#122

Post by furyofantares »

serial_dev wrote: post #33
rstupek wrote: post #8

"... 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?

Many such people have been in HN threads bragging about having servers running 24/7 and how they're getting $10,000 worth of compute (based on API pricing) for $200 per month. If anyone doing that is surprised that it wasn't going to last, then lmfao.

Re: Claude Code weekly rate limits

#124

Post by serial_dev »

thoughtfulappco wrote: post #79
serial_dev wrote: post #56

Earlier quoted context omitted.

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.

Re: Claude Code weekly rate limits

#125

Post by SaucyWrong »

steve_adams_86 wrote: post #31

I'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…

One way I've seen personally is that folks are using tools that drive many Claude Code sessions at once via something like git-worktree as a way of multitasking in a single codebase. Even with garden-variety model use, these folks are hitting the existing 5-hourly rate limits routinely.

Re: Claude Code weekly rate limits

#126

Post by swalsh »

bachittle wrote: post #111

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.

This happens when you prompt it poorly. If you want to avoid slop, the first step is to write an extensive BRD. Read it, understand it, make sure it has everything needed. Then write a solutions architecture document. Read it, understand it, make sure it is fully specified including how things are structured, architecture, principles etc. You can use AI to write these documents. Just make sure to read them, and edit them as needed.

When you have your functional spec, and your tech spec, ask it to implement it. Additionally add some basic rules, say stuff like "don't add any fallback mechanisms or placeholders unlessed asked. Keep a todo of where you're at, ask any questions if unsure.

The key is to communicate well, ALWAYS READ what you input. Reivew, and provide feedback. Also i'd reccomend doing smaller chunks at a time once things get more complicated.

Re: Claude Code weekly rate limits

#127

Post by steve_adams_86 »

throwup238 wrote: post #65
steve_adams_86 wrote: post #31

I'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…

I hadn't considered that. I'm using it almost exclusively to validate logic, kind of like a fuzzer in nature ("What if we need to do this with this logic/someone tries to do that/what am I missing/etc"), or to fill in specifications ("what feature would compliment this/what could be trimmed to achieve MVP more easily/does this spec appear to be missing anything according to this set of requirements"), which requires a lot of review, and using more expensive models like Opus doesn't appear to provide meaningfully better results. After prompting it, I typically have a lot to think about and the terminal goes quiet, or I prompt it on a related matter that will similarly require my eyes and brain for long enough that I won't be able to limit out.

I can see how work involving larger contexts and deeper consideration would lead to exhausting limits a lot faster though, even if you aren't using it like a slot machine.

Re: Claude Code weekly rate limits

#128

Post by el_benhameen »

Wowfunhappy wrote: post #88

I'm probably not going to hit the weekly limit, but it makes me nervous that the limit is weekly as opposed to every 36 hours or something. If I do hit the limit, that's it for the entire week —a long time to be without a tool I've grown accustomed to! I feel like someone is going to reply that I'm too reliant on Claude or something. Maybe that's true, but I'd feel the same about the prospect of loosing ripgrep for a…

This is how I feel about the 100 msg/wk limit on o3 for the ChatGPT plus plan. There’s no way to see how much I’ve used, and it’s an important enough resource that my lizard brain wants to hoard it. The result is that I way underutilize my plan and go for one of the o4-mini models instead. I would much prefer a lower daily limit, but maybe the underutilization is the point of the weekly limit.

*edited to change “pro” to “plus”

Re: Claude Code weekly rate limits

#129

Post by bugglebeetle »

KronisLV wrote: post #81
jimbo808 wrote: post #22

I'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 personally take an issue with them expecting that your usage would be more or less consistent throughout the month. Instead, I might have low usage throughout most of the month and then an 11 hour binge a few days, which in most cases would involve running into rate limits (either that, or just token limitations for inputs). That's why using the API directly and paying for tokens anything past that basic usage feel…

Gemini 2.5 Pro is a better coding model, but Gemini CLI is way behind Claude Code, perhaps because the model itself isn’t well-tuned for agentic work. If you’re just doing targeted refactoring and exploration, you can copy and paste back and forth from the web app for $20 a month.

Re: Claude Code weekly rate limits

#130

Post by swalsh »

Wowfunhappy wrote: post #88

I'm probably not going to hit the weekly limit, but it makes me nervous that the limit is weekly as opposed to every 36 hours or something. If I do hit the limit, that's it for the entire week —a long time to be without a tool I've grown accustomed to! I feel like someone is going to reply that I'm too reliant on Claude or something. Maybe that's true, but I'd feel the same about the prospect of loosing ripgrep for a…

I used about $300 worth of credits based on ccusage ($20 pro plan). It's pretty easy to hit the limit once you get going.
Post reply on HN