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

661–670 of 724 posts

Re: Claude Code weekly rate limits

#661

Post by ebiester »

Jcampuzano2 wrote: post #171
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.

My opinion is all of these tools should completely get rid of the "pay 20/month, 200/month", etc just to get access to some beholden rate limited amount that becomes hard to track. Mask off completely and just make it completely usage based for everyone. You could do something for trial users like first 20 (pick your number here) requests are free if you really need to in order to get people on board. Or you could do…

Then, however, they would be accountable for how many times AI fails.

If I'm paying a flat rate, the only economic cost I am worrying about is "will this be faster than me doing it myself if it fails once or twice?"

If I am paying per token, and it goes off for 20 minutes without solving the problem, I've just spent $$ for no result. Why would I even bother using it?

For something like Claude Code, that's an even more concerning issue - how many background tasks have to fail before I reach my monthly spending limit? How do I get granular control to say "only spend 7 dollars on this task - stop if you cannot succeed." - and I have to write my own accounting system for whether it succeeds or fails.

Re: Claude Code weekly rate limits

#662

Post by vonneumannstan »

lyu07282 wrote: post #655
vonneumannstan wrote: post #235

Apparently people are consistently getting thousands of dollars worth of tokens for their $200/mo sub so this was just obviously unsustainable for Anthropic.

The 95% of users are subsidizing the 5% power users, in theory they could adjust the usage cap dynamically depending on usage vs. total number of subscribers. But of course with a complete lack of transparency it doesn't matter, there is no reason to ever give the benefit of the doubt to a for-profit company.

>But of course with a complete lack of transparency it doesn't matter, there is no reason to ever give the benefit of the doubt to a for-profit company

We know inference is very expensive so it's not reasonable to expect unlimited usage in general...

Re: Claude Code weekly rate limits

#663

Post by zelphirkalt »

brookst wrote: post #469
umbra07 wrote: post #452

Earlier quoted context omitted.

If you don't use a skill, it atrophies. Now, maybe that is the future (no more/extremely little human-written code). Maybe that's a good thing in the same way that " x technological advancement means y skill is no longer necessary" - like how the advent of readily-accessible live maps means you don't need to memorize street intersections and directions or whatever. But it is true.

I am terrible at computing sine and cosine, for sure. It doesn’t bother me.

On the surface, this comparison might hold, but when you look at software development as a craft, and therefore containing aspects of creativity and art, the comparison no longer holds.

Re: Claude Code weekly rate limits

#664

Post by clbrmbr »

Anthropic has been incredibly generous. I use regularly ~750 USD worth of opus tokens per month, which is a great deal for 200 USD. I’ve never hit a limit on the Max 20x plan, but the Max 5x plan was laughably limited. The impression I got was that there was basically no limiting at all, and Anthropic was just watching the usage patterns.

It’s an all you can eat buffet, you’re just not allowed takeout!

Re: Claude Code weekly rate limits

#665

Post by muzani »

I hit the 5 hour limit almost every work day (pro, not max).

It has become a kind of goal to hit it twice a day. It means I've had a productive day and can go on and eat food, touch grass, troll HN, read books.

I'm on Claude Code after hitting Cursor Pro for the month. It makes more sense to subscribe to a bunch of different tools at $20/month than $100/month on one tool that throws overloaded errors. We'll probably get more uptime with the weekly restriction.

Re: Claude Code weekly rate limits

#666

Post by kanak8278 »

zamadatix wrote: post #478
xpe wrote: post #363

Earlier quoted context omitted.

> pressures users to hoard As a pedantic note, I would say 'ration'. Things you hoard don't magically go away after some period of time.

FWIW neither hoard nor ration imply anything about permanence of the thing to me. Whether you were rationed bread or you hoarded bread, the bread isn't going to be usable forever. At the same time whether you were rationed sugar or hoarded sugar, the sugar isn't going to expire (with good storage). Rationed/hoarded do imply, to me, something different about how the quantity came to be though. Rationed being given or…

It can only happens in HackerNews that people talking about Claude Code limit, can start discussing what is a better a word for explaining it. :-)

I just love this community for these silly things.

Re: Claude Code weekly rate limits

#667

Post by am17an »

matltc wrote: post #639
127 wrote: post #632

It's strange that everywhere I see people just believing everything they say and blaming the users. It's not as if a big corp has ever lied before...? People are just so gullible. Using the $20 Pro sub and for anything above Hello World project size, it's easy to hit the 5 hour window limit in just 2 hours. Most of the tokens are spent on Claude Code own stupidity and its mistakes quickly snowballing.

"You're just prompting it wrong. Did you: 1. set up your dozens of /\.?claude.*\.(json|md)/i dotfiles? 2. give insanely detailed prompts that took longer to write than the code itself? 3. Turn on auto-accept so that you can only review code in one giant chunk in diff, therefore disallowing you to halt any bad design/errors during the first shot?" > ...easy to hit the 5 hour window limit in just 2 hours I've had this…

Asymptotically, prompting is a programming language.

Re: Claude Code weekly rate limits

#668

Post by clownpenis_fart »

el_benhameen wrote: post #128
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”…

[dead]

Re: Claude Code weekly rate limits

#669

Post by Wowfunhappy »

kelnos wrote: post #649
Wowfunhappy wrote: post #509

Earlier quoted context omitted.

I feel like using Claude Code overnight while you sleep or sharing your account with someone else is equivalent to taking home leftovers from an all-you-can-eat buffet. I also find it hard to believe 5% of customers are doing that, though.

I think this is just a bad analogy. I've definitely set Claude Code on a task and then wandered off to do something else, and come back an hour or so later to see if it's done. If I'd chosen to take a nap, would you say I'm "gaming the system"? That's silly. I'm using an LLM agent to free up my own time; it's up to me to decide what I do with that time.

No, this doesn't sound like gaming the system to me. However, if you were using a script to automatically queue up tasks so they can run as soon as your 5-hour-session expires to ensure you're using Claude 24/7, that's a different story. A project like this was posted to HN relatively recently.

As I said, I have trouble believing this constitutes 5% of users, but it constitutes something and yeah, I feel Anthropic is justified in putting a cap on that.

Post reply on HN