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

71–80 of 695 posts

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

#71

Post by zozbot234 »

stingraycharles wrote: post #57
hrimfaxi wrote: post #10

Earlier quoted context omitted.

The response doesn't even make sense and appears to be written by AI. > The March 6 change makes Claude Code cheaper, not more expensive. 1h TTL for every request could cost more, not less Feels very AI. > Restore 1h as the default / expose as configurable? 1h everywhere would increase total cost given the request mix, so we're not planning a global toggle. They won't show a toggle because it will increase costs for…

Sounds like a decision I would make when memory is expensive and you want to get rid of the very long (in time) tail of waiting 1h to evict cache when a session has stopped. There must be a better way to do this. The consumer option is the pricing difference. If they’d make cache writes the same price as regular writes, that would solve the whole problem. If you really want to push it, use that pricing only for reque…

Memory is expensive? If reads are as rare as they claim you can just stash the KV-cache on spinning disk.

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

#73

Post by hirako2000 »

Cpoll wrote: post #46
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.

Didn't they move too soon then? People haven't forgotten how to tie their shoelaces (yet). And anyway, they'll just move to a different model; last holdout wins.

Too abruptly for sure.

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

#74

Post by 1970-01-01 »

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…

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

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

#75

Post by cedws »

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 had a weird experience at work last week where Claude was just thinking forever about tasks and not actually doing anything. It was unusable. The next day it was fine again.

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

#76

Post by peterpanhead »

10keane wrote: post #55

this same pattern seems to occur every time a new model is about to release. i didnt notice the usage problem - i am on 20x. but opus 4.6 feels siginificantly dumber for some reason. i cant qualitify it, but it failed on everyday tasks where it used to complete perfectly

Every time there is a new model coming I think they deteriorate the current. This happens every darn time. Opus 4.6 isn't as sharp, not even close to as it was few weeks ago.

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

#77

Post by sailingcode »

I had Max plan and never reached its limit despite constantly working. Now I use the Pro plan and regularly reach the 5h limit as well as the weekly limit, as expected. I found that it makes a huge difference if you provide clear context when developing code. If you leave open room for interpretation, Claude Code uses tokens up much faster than in a defined context. The same is true for his time to answer getting longer if there isn't much documentation about the project.

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

#78

Post by freedomben »

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…

What does it look like when you get rate limited? Does the instance just kind of sit and spin?

I suspect I was getting rate limited very aggressively on Thursday last week. It honestly infuriated me, because I'm paying $200 a month for this thing. If it's going to rate limit me, at least tell me what it's doing instead of just making it seem like it's taking 12 hours to run through something that I would expect to be 15 minutes. The worst part is that it never even finished it.

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

#79

Post by zozbot234 »

imglorp wrote: post #69
zozbot234 wrote: post #54

Earlier quoted context omitted.

> 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?

Because the "explicit instruction" you give AI is not deterministic as in a normal computer program. It's a complete black box and the context is also most likely polluted by all sorts of weird stuff. Putting it on as tight of a leash as possible should be seen as normal.

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

#80

Post by hdndjsbbs »

hirako2000 wrote: post #22
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

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.

"enshittification" gets thrown around a lot, but this is the exact playbook. Look at the previous bubble's cash cow: advertising.

Online advertising is now ubiquitous, terrible, and mandatory for anyone who wants to do e-commerce. You can't run a mass-market online business without buying Adwords, Instagram Ads, etc.

AI will be ubiquitous, and then it will get worse and more expensive. But we will be unable to return to the prior status quo.

Post reply on HN