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

Claude Code users hitting usage limits 'way faster than expected'

theregister.com

Post reply on HN
Print view View original

11–20 of 245 posts

Re: Claude Code users hitting usage limits 'way faster than expected'

#11

Post by stavros »

Anthropic went about this in a really dishonest way. They had increased demand, fine, but their response was to ban third-party clients (clients they were fine with before), and to semi-quietly reduce limits while keeping the price the same.

Unilaterally changing the deal to give customers less for the same price should not be legal, but companies have slowly boiled the frog in such a way that now we just go "welp, it's corporations, what can you do", and forget that we actually used to have some semblance of justice in the olden days.

Re: Claude Code users hitting usage limits 'way faster than expected'

#12

Post by robviren »

I find Claude code to be a token hog. No matter how confidently the papers say context rot is not an issue I find curating context to be highly important to output quality. Manually managing this in the Claude Webui has helped with my use cases more than freely tossing Claude code at it. Likely I am using both "wrong" but the way I use it is easier for me to reason about and minimize context rot.

Re: Claude Code users hitting usage limits 'way faster than expected'

#13

Post by susupro1 »

lukewarm707 wrote: post #10

please tell me if i'm crazy. i just refuse to use openai/google/anthropic subscriptions, i only use open source models with ZDR tokens. - i like privacy in my work, and i share when i wish. somehow we accepted that our prompts and work may be read and moderated by employees. would you accept people moderating what you write in excel, google docs, apple pages? - i want a consistent tool, not something that is quantise…

You are not crazy, you are just waking up from the SaaS delusion. We somehow allowed the industry to convince us that paying $20/month to rent volatile compute, have our proprietary workflows surveilled, and get throttled mid-thought is an 'upgrade'. The pendulum is swinging violently back to local-native tools. Deterministic, privately owned, unmetered—buying your execution layer instead of renting it is the only way to build actual leverage.

Re: Claude Code users hitting usage limits 'way faster than expected'

#14

Post by jdefr89 »

Over reliance on LLMs is going to become such a disaster in a way no one would have thought possible. Not sure exactly what, who, when, or where.. Just that having your entire product or repo dependent on a single entity is going to lead to some bad times…

Re: Claude Code users hitting usage limits 'way faster than expected'

#16

Post by master_crab »

bensyverson wrote: post #5
master_crab wrote: post #3

Earlier quoted context omitted.

Tool calls (particularly fetching for context) eats the context window heavily. I explicitly send MCP calls to sub agents because they are so “wordy”.

Everyone who has not hit this bug thinks it’s user error… It’s not. It happened to me a few days ago, and the speed at which I tore through my 5 hour usage cap was easily 10x faster than normal. Also: sub agents do not get you free usage. They just protect your main context window.

Yes, sorry. I meant it more as a descriptor of how many tokens it consumes. You are still stuck burning money.

Re: Claude Code users hitting usage limits 'way faster than expected'

#18

Post by xnx »

jdefr89 wrote: post #14

Over reliance on LLMs is going to become such a disaster in a way no one would have thought possible. Not sure exactly what, who, when, or where.. Just that having your entire product or repo dependent on a single entity is going to lead to some bad times…

> on a single entity

Contrary to the popular opinion here, there are other services beyond Claude Code. These usage limits might even prompt (har har) people to notice that Gemini is cheaper and often better.

Post reply on HN