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

521–530 of 724 posts

Re: Claude Code weekly rate limits

#521

Post by hinkley »

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”…

> it’s an important enough resource that my lizard brain wants to hoard it.

I have zero doubt that this is working exactly as intended. We will keep all our users at 80% of what we sold them by keeping them anxious about how close they are to the limit.

Re: Claude Code weekly rate limits

#522

Post by arvinsim »

forty wrote: post #362
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…

It makes me sad that devs start relying on proprietary online services to be able to work. We have been lucky enough to have FOSS tools to do everything and not to have to rely on any specific service or company to work and some of us are deciding to become like Monsanto-addicted farmers who forgot how to do their jobs without something they have to pay every month.

I think it's less about reliance and more about competition.

Sure, devs can still work without AI.

But if the developer who uses AI has more output than the one that doesn't, it naturally incentives everyone to leverage AI more and more.

Re: Claude Code weekly rate limits

#523

Post by debian3 »

ehnto wrote: post #513

I am pretty interested in what the person letting it run 24/7 is achieving. Is it a continuously processing workload of some kind that pipes into the model? Maybe a 24/7 chat support with high throughput? Very curious.

Share your account with people on different timezone

Re: Claude Code weekly rate limits

#524

Post by dawnerd »

strictnein wrote: post #114

Confused 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 "M…

They really need to to just a limit so you can see how much you've used, not some vague hours per week or whatever. Github copilot will tell you, you have 300 requests with sonnet a month, makes it really easy to know when you're blowing past without having to worry about how long something has run.

Re: Claude Code weekly rate limits

#525

Post by valenterry »

xtracto wrote: post #411
rmujica wrote: post #108

Earlier quoted context omitted.

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.

I think LLMs follow more of an Energy analogy: Gas or Electricity, or even water. How much has any if these decreased over the last 5 decades? The problem is that as of right now, LLM cost is linearly (if not exponentially) related to the output. It's basically "transferring energy" converted into bytes. So unless we see some breakthrough in energy generation, or better use it, it will be difficult to scale. This mak…

I don't think so. Yes, LLMs use electricity. But they use electricity in the data-center, not in your home. That's very different, because it's cheap to transfer tokens from the data-center to your home, but it's not cheap to transfer electricity from the data-center to your home. And that matters, because we can build a data-center in a place where there's lots of renewable and hence cheap energy (e.g. from solar or from water/wind).

If you think about it, LLMs are used mostly when people are awake, at least right now. And when is the sun shining? Right. So, build a data-center somewhere where land is cheap and lots of solar panels can be build right next to it. Sure, some other energy source will be used for stability etc., but it won't be as expensive as the energy price for your home.

> This makes me wonder, would it be possible to pre-compue some kind of "rainbow tables" equivalent for LLMs?

Already happening. Read up on how those companies do caching prompt-prefixes etc.

Re: Claude Code weekly rate limits

#526

Post by ImaCake »

strictnein wrote: post #114

Confused 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 "M…

The ambiguity here is awful marketing practice. This bitter pill would be much easier to swallow if it was a hard number instead of these vague ranges. It would serve Anthropic better too - telling people they only get 300hrs vs between 240-480 (which they will naturally evaluate as 240hrs) will mean less users leaving the platform.

Re: Claude Code weekly rate limits

#527

Post by milankragujevic »

milankragujevic wrote: post #418
el_benhameen wrote: post #128

Earlier quoted context omitted.

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”…

Where did you find this info? I am unable to find in on OpenAI's website. https://help.openai.com/en/articles/6950777-what-is-chatgpt-... I haven't yet run into this limit...

Found it: https://help.openai.com/en/articles/9824962-openai-o3-and-o4...

Re: Claude Code weekly rate limits

#528

Post by stingraycharles »

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…

Yeah, if this happens, I’m probably going to do the inevitable: get two accounts. If I could pay $500 a month for Claude 100x I would probably do it at this point.

Given that I rarely hit the session limits I’m hopeful I won’t be affected, but the complete and utter lack of transparency is really frustrating.

Re: Claude Code weekly rate limits

#529

Post by stingraycharles »

forty wrote: post #362
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…

It makes me sad that devs start relying on proprietary online services to be able to work. We have been lucky enough to have FOSS tools to do everything and not to have to rely on any specific service or company to work and some of us are deciding to become like Monsanto-addicted farmers who forgot how to do their jobs without something they have to pay every month.

Devs have been doing this for years. If Github goes down, it has a huge impact on dev productivity.

Re: Claude Code weekly rate limits

#530

Post by what »

Tokumei-no-hito wrote: post #497
Aurornis wrote: post #233

Earlier quoted context omitted.

> guy was bragging about it on twitter yesterday. $13,200 of spend for his $200 account. he said he had like 4-5 opus only agents running nonstop and calling each other recursively. Do you have a link? I'm always curious to see these users after working at a startup that was the target of some creative use from some outlier customers.

sorry i went looking but couldn't find it. asked grok to search too. it wasn't creative use imo, it was extremism for the sake of attention since as far as i could tell they weren't producing anything (i'm sure they would have told everyone). although to be fair, the recursive opus chaining could be considered creative but only if it had a practical application. not the tweet but here's a leaderboard of claude clowns…

There’s zero chance the top rankings are real. 13B tokens in two days?
Post reply on HN