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

251–260 of 695 posts

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

#251

Post by bcherny »

denysvitali wrote: post #237
losteric wrote: post #218

Earlier quoted context omitted.

[flagged]

Me and my colleagues faced, over the last ~1 month or so, the same issues. With a new version of Claude Code pretty much each day, constant changes to their usage rules (2x outside of peak hours, temporarily 2x for a few weeks, ...), hidden usage decisions (past 256k it looks like your usage consumes your limits faster) and model degradation (Opus 4.6 is now worse than Opus 4.5 as many reported), I kind of miss how i…

> past 256k it looks like your usage consumes your limits faster

This is false. My guess is what is happening is #1 above, where restarting a stale session causes a 256k cache miss.

That said, I hear the frustration. We are actively working on improving rate limit predictability and visibility into token usage.

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

#252

Post by martinp »

coderbants wrote: post #140
SkyPuncher wrote: post #125

I skimmed the issue. No wonder Anthropic closes these tickets out without much action. That’s just a wall of AI garbage. Here’s what I’ve done to mostly fix my usage issues: * Turn on max thinking on every session. It save tokens overall because I’m not correcting it of having it waste energy on dead paths. * keep active sessions active. It seems like caches are expiring after ~5 minutes (especially during peak usage…

Can’t you turn the 1M off with a /model opus (or /model sonnet)? At least up until recently the 1M model was separated into /model opus[1M]

[dead]

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

#253

Post by bcherny »

yummytummy wrote: post #249
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…

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.

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

#254

Post by zamalek »

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.…

I am also on Codex while Claude seems to be blatantly ignoring instructions (as recently as Thursday: when I made the switch). The huge Claude context helps with planning, so that's all it does now.

Codex consumes way fewer resources and is much snappier.

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

#255

Post by maerF0x0 »

losvedir wrote: post #245
SkyPuncher wrote: post #125

I skimmed the issue. No wonder Anthropic closes these tickets out without much action. That’s just a wall of AI garbage. Here’s what I’ve done to mostly fix my usage issues: * Turn on max thinking on every session. It save tokens overall because I’m not correcting it of having it waste energy on dead paths. * keep active sessions active. It seems like caches are expiring after ~5 minutes (especially during peak usage…

Haha. yeah my eyes glazed over immediately on the issue. Absolutely this was someone telling their Claude Code to investigate why they ran out of tokens and open the issue. Good chance it's not real or misdiagnosed. But it gives me some degree of schadenfreude to see it happening to the Claude Code repo.

And you think companies aren't doing the same back to us? Are you sure you're speaking to a human?

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

#256

Post by docheinestages »

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 are you all of a sudden running into so many issues like this? Could it be that all of the Anthropics employees have completely unlimited and unbounded accounts, which means you don't get a feeling of how changes will affect the customers?

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

#257

Post by bcherny »

mvkel wrote: post #227
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 di…

> 1hr -> 5min on March 6th

This is not accurate. The main agent typically uses a 1h cache (except for API customers, which can enable 1h but it is not on by default because it costs more). Sub-agents typically use a 5m cache.

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

#258

Post by kirby88 »

I've been building an AI coding agent that using the exact same prompt than claude code, but uses a virtual filesystem to minify source code + the concept of stem agents (general agents that specializes during the conversation for maximum cache hit). The results on my modest benchmark is 50% of claude code cost and 40% of the time. https://github.com/kirby88/vix-releases

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

#259

Post by emptysongglass »

nickstinemates wrote: post #219
emptysongglass wrote: post #207

Earlier quoted context omitted.

Man what the hell happened to System Initiative. It was a super weird pivot from sociotechnical proclamations to a tool I honestly have no idea what it does for me? Is it n8n for agents? Is it needed when I have a bunch of skills that approximate whatever swamp is trying to do? Who knows!

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!

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

#260

Post by elephanlemon »

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…

IMO we are currently in the ENIAC era of LLMs. Perhaps there will be a brief moment where things get worse, but long term the cost of these things will go way down.
Post reply on HN