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

Pro Max 5x quota exhausted in 1.5 hours despite moderate usage

github.com

Post reply on HN
Print view View original

61–70 of 695 posts

Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage

#61

Post by dgellow »

geeky4qwerty wrote: post #39

I'm afraid the music may be slowly fading at this party, and the lights will soon be turned on. We may very well look back on the last couple years as the golden era of subsidized GenAI compute. For those not in the Google Gemini/Antigravity sphere, over the last month or so that community has been experiencing nothing short of contempt from Google when attempting to address an apparent bait and switch on quota expec…

For what it’s worth, that was pretty obvious from the get go it wasn’t a realistic long term deal. I’ve been building all the libraries I hoped existed over the past 1-2y to have something neat to work with whenever the free compute era ends. I feel that’s the approach that makes sense. Take the free tokens, build everything you would want to exist if you don’t have access to the service anymore. If it goes away you’re back to enjoying writing code by hand but with all the building blocks you dreamt of. If it never goes away, nothing wasted, you still have cool libs

Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage

#62

Post by jandrese »

I mean this is expected is it not? These companies burned unimaginable amounts of investor cash to get set up and now they have to start turning a profit. They can't make up for the difference with volume because the costs are high, so the only option is to raise prices.

Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage

#63

Post by egeozcan »

zozbot234 wrote: post #54
chandureddyvari wrote: post #40

Claude has gotten noticeably worse for me too. It goes into long exploration loops for 5+ minutes even when I point it to the exact files to inspect. Then 30 minutes later I hit session limits. Three sessions like that in a day, and suddenly 25% of the weekly limit is gone. I ended up buying the $100 Codex plan. So far it has been much more generous with usage and more accurate than Claude for the kind of work I do.…

> It goes into long exploration loops for 5+ minutes even when I point it to the exact files to inspect. Give it a custom sandbox and context for the work, so it has no opportunity to roam around when not required. AI agentic coding is hugely wasteful of context and tokens in general (compared to generic chat, which is how most people use AI), there's a whole lot of scope for improvement there.

But the problem is it used to not need that before. These days, you have to think twice before you summon a subagent.

Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage

#64

Post by pxc »

holoduke wrote: post #29

I spend full 20x the week quota in less than 10 hours. How is that possible? Well try to mass translate texts in 30 languages and you will hit limits extremely quick.

Translation generally works well with very small models compared to the frontier LLMs. You can definitely run a model on your own hardware for this.

Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage

#65

Post by GorbachevyChase »

TacticalCoder wrote: post #13
cmaster11 wrote: post #2

For whoever else is having the same problems, worth voting these kind of issues. There needs to be more transparency over what goes on with our subscriptions.

We vote here on HN and it's much more effective. Anyone from Anthropic reading conversations on HN like this one can be scared. We'll jump ship if they don't address such glaring issues.

The nice iOS app is a big convenience for me, but I’m starting to think I should just put my $20 in Open Router. It seems like minimax is a pretty solid competitor. I’m curious if the US-centric “frontier” is just marketing.

Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage

#66

Post by comandillos »

sdevonoes wrote: post #32
comandillos wrote: post #5

Quite scared by the fact that the original issue pointing out the actual root cause of the issue has been 'Closed as not planned' by Anthropic. https://github.com/anthropics/claude-code/issues/46829

Why scared? Like, if theit software gets bad, we stop using it.

Maybe scared wasn't the best word... but we cannot deny Opus is a great - if not greatest - model at coding and Anthropic is the only one serving it a reasonable prices when going through their subscription model.

Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage

#67

Post by dgellow »

meetingthrower wrote: post #56

I don't get it. Last week on the 100 bucks plan I generated probably 50k LOC (not a quality measure for sure!) and just barely kissed the weekly limit. I did get rate limited on some sessions for sure, but that's to be expected. I'm curious what are people doing that is consuming your limits? I can't imagine filling the $200 a month plan unless I was essentially using Claude code itself as the api to mass process stu…

I have the same experience as you. I’m wondering if it is regional? I’m in Europe so don’t overlap much with US usage, which is likely to be way higher

Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage

#69

Post by imglorp »

zozbot234 wrote: post #54
chandureddyvari wrote: post #40

Claude has gotten noticeably worse for me too. It goes into long exploration loops for 5+ minutes even when I point it to the exact files to inspect. Then 30 minutes later I hit session limits. Three sessions like that in a day, and suddenly 25% of the weekly limit is gone. I ended up buying the $100 Codex plan. So far it has been much more generous with usage and more accurate than Claude for the kind of work I do.…

> It goes into long exploration loops for 5+ minutes even when I point it to the exact files to inspect. Give it a custom sandbox and context for the work, so it has no opportunity to roam around when not required. AI agentic coding is hugely wasteful of context and tokens in general (compared to generic chat, which is how most people use AI), there's a whole lot of scope for improvement there.

The sandbox is fine, but if the parent has given explicit instruction of files to inspect, why is it not centering there? Is the recent breakage that the base prompt makes it always try to explore for more context even if you try to focus it?

Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage

#70

Post by sdevonoes »

comandillos wrote: post #66
sdevonoes wrote: post #32

Earlier quoted context omitted.

Why scared? Like, if theit software gets bad, we stop using it.

Maybe scared wasn't the best word... but we cannot deny Opus is a great - if not greatest - model at coding and Anthropic is the only one serving it a reasonable prices when going through their subscription model.

Sounds like an addiction to me
Post reply on HN