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

281–290 of 695 posts

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

#281

Post by hughw »

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…

Where can i learn about concepts like prompt cache misses? I don't have a mental model how that interacts with my context of 1M or 400k tokens... I can cargo cult follow instructions of course but help us understand if you can so we can intelligently adapt our behavior. Thanks.

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

#282

Post by hk__2 »

onlyrealcuzzo wrote: post #26
MeetingsBrowser wrote: post #11

I pay for the lowest plan. I used to struggle to hit my quota. Now a single question consistently uses around 15% of my quota

What plan are you using?

> What plan are you using?

OP wrote "I pay for the lowest plan", so that’s the $20/mo one.

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

#283

Post by hughw »

hughw wrote: post #281
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…

Where can i learn about concepts like prompt cache misses? I don't have a mental model how that interacts with my context of 1M or 400k tokens... I can cargo cult follow instructions of course but help us understand if you can so we can intelligently adapt our behavior. Thanks.

And why does /clear help things? Doesn't that wipe out the history of that session? Jeez.

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

#284

Post by yummytummy »

bcherny wrote: post #253
yummytummy wrote: post #249

Earlier quoted context omitted.

Ah, so cache usage impacts rate limits. There goes the ”other harnesses aren’t utilizing the cache as efficiently” argument.

Claude Code is the most prompt cache-efficient harness, I think. The issue is more that the larger the context window, the higher the cost of a cache miss.

That might be, but the argument was that poor cache utilization was costing Anthropic too much money in other harnesses. If cache is considered in rate limits, it doesn’t matter from a cost perspective, you’ll just hit your rate limits faster in other harnesses that don’t try to cache optimize.

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

#285

Post by muyuu »

rzkyif wrote: post #149
rzkyif wrote: post #87

My personal experience is way different: I struggle to burn through more than 50% of the 5 hour limit For context, with Google AI Pro, I can burn through the Antigravity weekly limit in 1-2 hours if I force it to use Gemini 3.1 Pro. Meanwhile Gemini 3 Flash is basically unlimited but frequently produces buggy code or fail to implement things how I personally would (felt like it doesn't "think" like a software dev) I…

Reading the other negative comments makes me wonder if this is only because I'm getting a hidden newcomer's limit bonus or something though hahah

it may also be local/timezone effects

it has been reported that it behaves very differently depending on those factors, presumably because people are placed in best-effort buckets, who knows

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

#286

Post by echelon »

rawicki wrote: post #247
bcherny wrote: post #241

Earlier quoted context omitted.

I don't think that's accurate. The malware prompt has been around since Sonnet 3.7. We carefully evaled it for each new model release and found no regression to intelligence, alongside improved scores for cyber risk. That said, we have removed the prompt for Opus 4.6 since it no longer needed it.

I started seeing "not a malware, continuing" in almost every reply since around 2 weeks ago. Maybe you just reintroduced it with some regression? Opus 4.6

1. I've never seen this. Is there a config option to unhide it if it's happening? Is this in Claude Code? Does it have to be set to verbose or something?

2. Can we pay more/do more rigorous KYC to disable it if it's active?

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

#287

Post by hk__2 »

stavros wrote: post #146
brunooliv wrote: post #97

[flagged]

> Anthropic CAN change their limits and rates as they see fit, there’s never been hard promises or SLOs on these plans. No they can't. When I buy an annual subscription and prepay for the year, they can't just go "ok now you get one token a month" a day in. I bought the plan as I bought it. They can't change anything until the next renewal.

> I bought the plan as I bought it. They can't change anything until the next renewal.

So no new models, no new features?

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

#288

Post by nickstinemates »

emptysongglass wrote: post #259
nickstinemates wrote: post #219

Earlier quoted context omitted.

I can't really speak to the sociotechnical proclamations, because I didn't make them. What it does for you is simple: if you want to automate something, it does. Load the AI harness of your choice, tell it what to automate, swamp builds extensions for whatever it needs to to accomplish your task. It keeps a perfect memory of everything that was done, manages secrets through vaults (which are themselves extensions it…

Ah, interesting, thanks! I think you might consider elevating some of that kind of copy. The sociotechnical stuff with System Initiative was made by your CEO? The guy who is really into music? And I don't even know how long that product was a thing before the pivot. Not long!

Does https://swamp.club do a better job?

System Initiative was a thing for ~6.5 years. I talked to every person who ever used it or was interested in using it in the last 2.5 years. Thousands of them.

Swamp is better by every metric; has a lot more promise, is a lot more interesting.

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

#289

Post by ImPostingOnHN »

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…

> if they hiked to price infinity, you wouldn't worse off than if AI didn't exist because you could still code by hand

This was addressed by the words that you perhaps mistakenly omitted from your quote:

> Once people won't be able to think anymore...

People who aren't able to think anymore, can't still code by hand. Think "Idiocracy".

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

#290

Post by reenorap »

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…

Boris, you're seeing a ton of anecdotes here and Claude has done something that has affected a bunch of their most fervent users.

Jeff Bezos famously said that if the anecdotes are contradicting the metrics, then the metrics are measuring the wrong things. I suggest you take the anecdotes here seriously and figure out where/why the metrics are wrong.

Post reply on HN