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

Claude Code weekly rate limits

news.ycombinator.com

Post reply on HN
Print view View original

161–170 of 724 posts

Re: Claude Code weekly rate limits

#161

Post by beepbooptheory »

jimbo808 wrote: post #22

I'm not sure how this will play out long term, but I really am not a fan of having to feel like I'm using a limited resource whenever I use an LLM. People like unlimited plans, we are used to them for internet, text messaging, etc. The current pricing models just feel bad.

I'm sure people hate this mindset here, but any time I use an LLM I just picture the thousands of fans spinning, the heat of the datacenter... I treat each prompt like a painful interval where I am leaving my door open on a hot day.

I know nobody else really cares.. In some ways I wish I didn't think like this.. But its at this point not even an ethical thing, its just a weird fixation. Like I can't help but feel we are all using ovens when we would be fine with a toasters.

Re: Claude Code weekly rate limits

#162

Post by dotancohen »

belter wrote: post #87
jimbo808 wrote: post #22

I'm not sure how this will play out long term, but I really am not a fan of having to feel like I'm using a limited resource whenever I use an LLM. People like unlimited plans, we are used to them for internet, text messaging, etc. The current pricing models just feel bad.

The real bottleneck isn’t Jevons paradox, it’s the Theory of Constraints. A human brain runs on under 20 W, yet every major LLM vendor is burning cash and running up against power supply limits. If anything pops this bubble, it won’t be ethics panels or model tweaks but subscription prices finally reflecting those electricity bills. At that point, companies might rediscover the ROI of good old meat based AI.

  > good old meat based AI.
NI, or really just I.

Though some of us might fall into the NS category instead.

Re: Claude Code weekly rate limits

#163

Post by littlestymaar »

el_benhameen wrote: post #128
Wowfunhappy wrote: post #88

I'm probably not going to hit the weekly limit, but it makes me nervous that the limit is weekly as opposed to every 36 hours or something. If I do hit the limit, that's it for the entire week —a long time to be without a tool I've grown accustomed to! I feel like someone is going to reply that I'm too reliant on Claude or something. Maybe that's true, but I'd feel the same about the prospect of loosing ripgrep for a…

This is how I feel about the 100 msg/wk limit on o3 for the ChatGPT plus plan. There’s no way to see how much I’ve used, and it’s an important enough resource that my lizard brain wants to hoard it. The result is that I way underutilize my plan and go for one of the o4-mini models instead. I would much prefer a lower daily limit, but maybe the underutilization is the point of the weekly limit. *edited to change “pro”…

> This is how I feel about the 100 msg/wk limit on o3 for the ChatGPT

Do I read this correctly? Only 100 messages per week, on the pro plan worth a few hundred buck a month?!

Re: Claude Code weekly rate limits

#165

Post by TeMPOraL »

belter wrote: post #87
jimbo808 wrote: post #22

I'm not sure how this will play out long term, but I really am not a fan of having to feel like I'm using a limited resource whenever I use an LLM. People like unlimited plans, we are used to them for internet, text messaging, etc. The current pricing models just feel bad.

The real bottleneck isn’t Jevons paradox, it’s the Theory of Constraints. A human brain runs on under 20 W, yet every major LLM vendor is burning cash and running up against power supply limits. If anything pops this bubble, it won’t be ethics panels or model tweaks but subscription prices finally reflecting those electricity bills. At that point, companies might rediscover the ROI of good old meat based AI.

Where is this oft-repeated idea coming from? Inference isn't that expensive.

Re: Claude Code weekly rate limits

#166

Post by lossolo »

flashgordon wrote: post #142
paxys wrote: post #107

Earlier quoted context omitted.

You can build a decent rig for yourself with: - 2x 4070 Ti (32 GB total VRAM) - $2200 - 64 GB RAM - $200-250 - Core i9/Ryzen 9 CPU - $450 - 2 TB SSD - $150 - Motherboard, cooler, case, PSU - $500-600 Total - ~$3500-3700, say $4000 with extras.

wow - do you mind sharing any links to a specific setup? Also whats the biggest model anybody has run on this?

Unfortunately, you will not be able to run any model on this that is comparable to the Claude models.

Re: Claude Code weekly rate limits

#167

Post by garciasn »

anonzzzies wrote: post #159

We will see but I hit the limit multiple times a day so I am a bit scared that this would mean looking for alternatives.

Using Claude Code or the web UI? If when using Claude Code, you may need to break your codebase up into smaller chunks to help.

That said, there's no fucking way I am getting what they claim w/Opus in hours. I may get two to three queries answered w/Opus before it switches to Sonnet in CC.

Re: Claude Code weekly rate limits

#168

Post by sitkack »

el_benhameen wrote: post #128
Wowfunhappy wrote: post #88

I'm probably not going to hit the weekly limit, but it makes me nervous that the limit is weekly as opposed to every 36 hours or something. If I do hit the limit, that's it for the entire week —a long time to be without a tool I've grown accustomed to! I feel like someone is going to reply that I'm too reliant on Claude or something. Maybe that's true, but I'd feel the same about the prospect of loosing ripgrep for a…

This is how I feel about the 100 msg/wk limit on o3 for the ChatGPT plus plan. There’s no way to see how much I’ve used, and it’s an important enough resource that my lizard brain wants to hoard it. The result is that I way underutilize my plan and go for one of the o4-mini models instead. I would much prefer a lower daily limit, but maybe the underutilization is the point of the weekly limit. *edited to change “pro”…

Working as Intended.

Re: Claude Code weekly rate limits

#169

Post by ankit219 »

serf wrote: post #11

200 bucks a month isn't enough. Fine. Make a plan that is enough so that I will be left alone about time limits and enforced breaks. NOTHING breaks flow better than "Woops! Times up!"; it's worse than credit quotas -- at least then I can make a conscious decision to spend more money or not towards the project. This whole 'twiddle your thumbs for 5 hours while the gpus cool off' concept isn't productive for me. '35 ho…

API has fewer limits, and practically limitless. Claude is also on Aws and gcp, where you get more quotas (probably credits as well) and different rate limits.

Re: Claude Code weekly rate limits

#170

Post by alwillis »

rmujica wrote: post #108
andruby wrote: post #36

Earlier quoted context omitted.

Unlimited works well for everything that is “too cheap to meter”. Internet, text messages, etc are roughly that: the direct costs are so cheap. That’s not the case with LLM’s at this moment. There are significant direct costs to each long-running agent.

Internet and SMS used to be expensive and metered until they weren't thanks to technological advances and expanded use. I think LLMs will follow the same path, maybe on a shorter timespan.

Yes and no.

It’s very expensive to create these models and serve them at scale.

Eventually the processing power required to create them will come down, but that’s going to be a while.

Even if there was a breakthrough GPU technology announced tomorrow, it would take several years before it could be put into production.

And pretty much only TSMC can produce cutting edge chips at scale and they have their hands full.

Between Anthropic, xAI and OpenAI, these companies have raised about $84 billion dollars in venture capital… VCs are going to want a return on their investment.

So it’s going to be a while…

Post reply on HN