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

221–230 of 695 posts

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

#221

Post by prmoustache »

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…

Looks like the enshittification simply started much quicker than other disruptive techs due to operating costs.

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

#222

Post by ImPostingOnHN »

athorax wrote: post #198
Rekindle8090 wrote: post #187

Earlier quoted context omitted.

The product was performing badly and you thought this would be solved by spending more money on it? When will people realize this is the same as vendor lock-in? "Maybe if I spend more money on the max plan it will be better" > no it will be the same "Maybe if I change my prompt it will work" > no it will be the same "Maybe if I try it via this API instead of that API it will improve" > no it will be the same. Claude,…

Do you realize Claude and Codex are different products by different companies?

You ask that as if there is some insight to the question, but the insight is hard to find. What the person you replied to is saying, applies to both Claude and Codex.

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

#223

Post by fps-hero »

bcherny wrote: post #210

Hey all, Boris from the Claude Code team here. We've been investigating these reports, and a few of the top issues we've found are: 1. Prompt cache misses when using 1M token context window are expensive. Since Claude Code uses a 1 hour prompt cache window for the main agent, if you leave your computer for over an hour then continue a stale session, it's often a full cache miss. To improve this, we have shipped a few…

Am I so out of touch?

No! It’s the children who are wrong!

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

#224

Post by jen20 »

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.…

> On UI/UX taste, I still think current Codex is behind the Jan/Feb era of Claude Code.

OpenCode is great though, and can (for now) use an OpenAI subscription.

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

#225

Post by nickstinemates »

brookst wrote: post #193
nickstinemates wrote: post #181

It feels so weird to me - people are exhausting their quotas while I am trying very hard to even reach mine with the $200 plan. We're generating all of the code for swamp[1] with AI. We review all of that generated code with AI (this is done with the anthropic API.) Every part of our SDLC is pure AI + compute. Many feature requests every day. Bug fixes, etc. Never hit the quota once. Something weird is definitely goi…

My hypothesis is that people who have continuous sessions that keep the cache valid see the behavior you’re describing: at 95% cache hits (or thereabouts), the max plan goes a long way. But people who go > 5 minutes between prompts and see no cache, usage is eaten up quickly. Especially passing in hundreds of thousands of tokens of conversation history. I know my quote goes a lot further when I sit down and keep sess…

I run dozens, hundreds? of new sessions every day. I don't have long lived sessions. 1 session = 1 task.

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

#226

Post by hirako2000 »

gruez wrote: post #169
hirako2000 wrote: post #22

Earlier quoted context omitted.

My take is that was the plan all along. Once people won't be able to think anymore and business expect the level of productivity witnessed before, will have no choice but cough up whatever providers bill us.

>and business expect the level of productivity witnessed before, will have no choice but cough up whatever providers bill us. Is that bad? After all, even if they hiked to price infinity, you wouldn't worse off than if AI didn't exist because you could still code by hand. Moreover if it's really in a "business" (employment?) context, the tools should be provided by your employer, not least for compliance/security rea…

This comment reads as trying on principle to defend the use of AI.

My argument was not about AI. Rather about the practice of Anthropic and the likes.

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

#227

Post by mvkel »

bcherny wrote: post #210

Hey all, Boris from the Claude Code team here. We've been investigating these reports, and a few of the top issues we've found are: 1. Prompt cache misses when using 1M token context window are expensive. Since Claude Code uses a 1 hour prompt cache window for the main agent, if you leave your computer for over an hour then continue a stale session, it's often a full cache miss. To improve this, we have shipped a few…

Why did this become an issue seemingly overnight when 1M context has been available for a while, and I assume prompt caching behavior hasn't changed?

EDIT: prompt caching behavior -did- change! 1hr -> 5min on March 6th. I'm not sure how starting a fresh session fixes it, as it's just rebuilding everything. Why even make this available?

It feels like the rules changed and the attitude from Anth is "aw I'm sorry you didn't know that you're supposed to do that." The whole point of CC is to let it run unattended; why would you build around the behavior of watching it like a hawk to prevent the cache from expiring?

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

#228

Post by mvkel »

losteric wrote: post #218
denysvitali wrote: post #214

Earlier quoted context omitted.

OpenAI (Codex) keeps on resetting the usage limits each time they fuck up... I have yet to see Anthropic doing the same. Sorry but this whole thing seems to be quite on purpose.

[flagged]

Why did it suddenly become an issue, despite prompt caching behavior being unchanged?

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

#229

Post by quikoa »

fooster wrote: post #91
1970-01-01 wrote: post #74

Earlier quoted context omitted.

Lights on = Ads in your output. EOY latest; they can't keep kicking the massive costs down the road.

Where is your evidence of this "massive cost"? Inference is massively profitable for both anthropic and openai. Training is not.

Inference for API or subscriptions? There is a massive price difference between the two.

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

#230

Post by peyton »

danbots wrote: post #204

Codex can feel standoffish at times. I can tell very quickly we wont become friends. The personality feels like an employee in another department that while gifted- is merely lending you a slice of their clearly precious time. I get the impression from codex that **gives me the feeling that I am wasting it’s time. That it will help me but deep down- it dos not want to, it does not care if we succeed toether. What I a…

I prompt it and check CI later. I couldn’t tell you how Codex feels. I’ve never had any conversation. You may want to try this sort of workflow if you’re affected personally in a negative way.
Post reply on HN