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

491–500 of 724 posts

Re: Claude Code weekly rate limits

#491

Post by canada_dry »

landl0rd wrote: post #357
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”…

You can tell how it’s intentional with both OpenAI and Anthropic by how they’re intentionally made opaque. I cant see a nice little bar with how much I’ve used versus have left on the given rate limits so it’s pressuring users to hoard. Because it prevents them from budgeting it out and saying “okay I’ve used 1/3 of my quota and it’s Wednesday, I can use more faster.”

OpenAI's "PRO" subscription is really a waste of money IMHO for this and other reasons.

Decided to give PRO a try when I kept getting terrible results from the $20 option.

So far it's perhaps 20% improved in complex code generation.

It still has the extremely annoying ~350 line limit in its output.

It still IGNORES EXPLICIT CONTINUOUS INSTRUCTIONS eg: do not remove existing comments.

The opaque overriding rules that - despite it begging forgiveness when it ignores instructions - are extremely frustrating!!

Re: Claude Code weekly rate limits

#492

Post by Tokumei-no-hito »

const_cast wrote: post #490
Tokumei-no-hito wrote: post #489

Earlier quoted context omitted.

we differ on the opinion that you can be abusive without breaking ToS. perhaps a charitable view is that this type of [abuse || acceptable use] helps lawyers stay employed so they can [eliminate exploitation of || more adequately describe] their ToS.

IMO abuse requires an exercise of power. End-users have no power - they hold zero leverage over the contract, and they have zero room to negotiate. It's a fully take-it-or-leave-it deal, and pray they do not alter the deal further. Because of that, IMO end-users can't abuse the contract, no matter how hard they try. It's not on them to do that, because they have zero control over the contract. It's a have-your-cake-a…

it's not a court of law.

end users did have power. the power to use the service legitimately, even as a power user. two choices were possible, with the users given the power to decide:

1. use it for an entire 8 hour workday with 1-2 agents at most - limited by a what a human could possibly entertain in terms of review and guidance.

2. use for 24 hours a day, 7 days a week with recursive agents on full opus blast. no human review could even be possible with this much production. its the functional equivalent of one person managing a team of 10-20 cracked engineers on adderall that pump out code 24 hours a day.

the former was the extreme of a power user with a practical deliverable. the latter is a circus whose sole purpose is to push the bounds and tweet about it.

now the lawyers get some fresh work to do and everyone gets throttled. oh and that 2nd group? they'll be, and are, the loudest about how they've been "rug pulled just like cursor".

Re: Claude Code weekly rate limits

#493

Post by 48terry »

jedberg wrote: post #486
48terry wrote: post #484

Earlier quoted context omitted.

Just in case everybody in this comment tree forgot: Claude is not some common, public good. It barely even qualifies as a digital commons, if it does. It is a private tool owned by a private, for-profit company. Nobody has a common obligation to make Anthropic profitable or to reduce its expenses.

I never said anything about a public good. See my sibling comment.

The "finite, valuable resource" in this case being "something a private company is actively trying to produce and pocket wealth with".

Again, there is no moral obligation to ensure Anthropic's business goes well and conveniently.

Re: Claude Code weekly rate limits

#494

Post by Tokumei-no-hito »

const_cast wrote: post #490
Tokumei-no-hito wrote: post #489

Earlier quoted context omitted.

we differ on the opinion that you can be abusive without breaking ToS. perhaps a charitable view is that this type of [abuse || acceptable use] helps lawyers stay employed so they can [eliminate exploitation of || more adequately describe] their ToS.

IMO abuse requires an exercise of power. End-users have no power - they hold zero leverage over the contract, and they have zero room to negotiate. It's a fully take-it-or-leave-it deal, and pray they do not alter the deal further. Because of that, IMO end-users can't abuse the contract, no matter how hard they try. It's not on them to do that, because they have zero control over the contract. It's a have-your-cake-a…

there's a famous quote that i think captures the spirit of what i'm trying to express

"you're not wrong, you're just an asshole" - the dude to walter.

(no particular offense directed, the you here is of course the "royal you").

Re: Claude Code weekly rate limits

#495

Post by slimebot80 »

Overall I think this is as positive - protecting the system from being hit heavily 24/7 and with multiple agents from some users might make the system more sustainable for a wider population of users.

This one thing that bugs me is the visibility of how far through your usage you are. Being told when you're close to the end means I cannot plan. I'm not expecting an exact %, but a few notices at intervals (eg: halfway through) would help a lot. Not providing this kinda makes me worry they don't want us to measure. (I don't want to closely measure, but I do want to have a sense of where I am at)

Re: Claude Code weekly rate limits

#496

Post by AstroBen »

serf wrote: post #11

200 bucks a month isn't enough. Fine. Make a plan that is enough so that I will be left alone about time limits and enforced breaks. NOTHING breaks flow better than "Woops! Times up!"; it's worse than credit quotas -- at least then I can make a conscious decision to spend more money or not towards the project. This whole 'twiddle your thumbs for 5 hours while the gpus cool off' concept isn't productive for me. '35 ho…

It's quite possible changing plans to something that's enough to make them profitable would push everyone to a competitor

Slowly bringing up prices as people get dependent sounds like a pretty decent strategy if they have the money to burn

Re: Claude Code weekly rate limits

#497

Post by Tokumei-no-hito »

Aurornis wrote: post #233
Tokumei-no-hito wrote: post #219

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. clearly that's abusive and should be targeted. but in general idk how else any inference provider can handle this situation. cursor is fucked because they are a whole layer of premium above the at-cost of anthropic / openai etc. so everyone…

> 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 bragging about their spend. maybe you can find their handles and ask them what MRR they hit spending $500k (not a typo) in credits.

https://www.viberank.app/

Re: Claude Code weekly rate limits

#498

Post by Tokumei-no-hito »

jjmarr wrote: post #318
Tokumei-no-hito wrote: post #219

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. clearly that's abusive and should be targeted. but in general idk how else any inference provider can handle this situation. cursor is fucked because they are a whole layer of premium above the at-cost of anthropic / openai etc. so everyone…

If VCs want to give me free money in exchange for using their product, do you expect me to say no?

of course not. the buffet said all you can eat, didn't it? i don't expect you to do anything less but engorge your body to the point of hospitalization while 95% of the remaining customers look in horror.

Re: Claude Code weekly rate limits

#499

Post by aprdm »

pythonguython wrote: post #472
forty wrote: post #362

Earlier quoted context omitted.

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.

Do you mind sharing what industry you’re in where you can fully rely on FOSS? In my industry we’re dependent on MATLAB, Xilinx tools, closed source embedded software and more. To name a few industries: game devs might be stuck with unity, finance quant devs might be stuck with Bloomberg terminals, iOS app devs are stuck with apple’s tooling etc… this isn’t just an LLM problem IMO.

backend web services devops frontend javascript

just three possible examples

Re: Claude Code weekly rate limits

#500

Post by jjani »

mattkrause wrote: post #488
zamadatix wrote: post #478

Earlier quoted context omitted.

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…

For me, the difference between ration and hoard is the uhh…rationality of the plan. Rationing suggests a deliberate, calculated plan: we’ll eat this much at these particular times so our food lasts that long. Hoard seems more ad hoc and fear-driven: better keep yet another beat-up VGA cable, just in case.

> Hoard seems more ad hoc and fear-driven: better keep yet another beat-up VGA cable, just in case.

Counterexample: animals hoarding food for winter time, etc.

Post reply on HN