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

101–110 of 724 posts

Re: Claude Code weekly rate limits

#101

Post by steve_adams_86 »

bad_haircut72 wrote: post #52
steve_adams_86 wrote: post #31

I'm well within the 95%. I might lack an imagination here, but... What are you guys doing that you hit or exceed limits so easily, and if you do... Why does it matter? Sometimes I'd like to continue exploring ideas with Claude, but once I hit the limit I make a mental note of the time it'll come back and carry on planning and speccing without it. That's fine. If anything, some time away from the slot machine often he…

Im not a formula 1 driver but why do they have those big padel things on the back? looks dumbo IMHO I just dont get it

I respectfully consider this analogy void, but welcome an explanation of why I'm wrong.

I haven't yet seen anyone doing anything remarkable with their extensive use of Claude. Without frequent human intervention, all of it looks like rapid regression to the mean, or worse.

Re: Claude Code weekly rate limits

#103

Post by kmac_ »

aliljet wrote: post #60

Maybe this is an unpopular opinion, but it seems like Anthropic has quietly 4x'd the real cost of the Pro plan. There are 168 hours in a week, and if I'm able to (safely) bet on 40 hours of use, realistically, I just lost 75% of the value of the plan. What are the reasonable local alternatives? 128 GB of ram, reasonably-newish-proc, 12 GB of vram? I'm okay waitign for my machine to burn away on LLM experiments I'm ru…

Pro is just a paid demo. I hit the limit all the time on a small project, and I'm not even doing anything weird. The product is still great, though. At work, we checked out a bunch of options, and almost everyone chose something different, so the competition is though.

Re: Claude Code weekly rate limits

#105

Post by steve_adams_86 »

mendor wrote: post #62
steve_adams_86 wrote: post #31

I'm well within the 95%. I might lack an imagination here, but... What are you guys doing that you hit or exceed limits so easily, and if you do... Why does it matter? Sometimes I'd like to continue exploring ideas with Claude, but once I hit the limit I make a mental note of the time it'll come back and carry on planning and speccing without it. That's fine. If anything, some time away from the slot machine often he…

I've found that asking for deep research consumes my quota quite fast, so If I run 2 or 3 and normal use I hit the limit and have to wait to reset

Me too. I've also found that even when trying to restrict models meant for these tasks, they tend to go on tangents and waste tremendous amounts of tokens without providing meaningfully better outputs. I'm not yet sold on these models for anything outside of fuzzy tasks like "does this logic seem sound?". They tend to be good at that (though they often want to elaborate excessively or propose solutions excessively).

Re: Claude Code weekly rate limits

#106

Post by steveklabnik »

blalezarian wrote: post #90

Can we PLEASE fix the bug in VS Code where the terminal occasionally scrolls out of control and VS Code crashes? It is very painful and we have to start the context all over again. This happens at least 1x per day.

> we have to start the context all over again.

Use /resume

Re: Claude Code weekly rate limits

#107

Post by paxys »

flashgordon wrote: post #64

Ok I really really have to figure out how to have a local setup of the open-source LLMs. I know i know - the "fixed costs" are high. But I have a strong feeling being able to setup local LLMs (and the rig for it) is the next build-your-own-PC phase. All I want is a coding agent and the grunt power to run it locally. Everything else Il build (generate) with it. I see so many folks claiming crazy hardware rigs and perf…

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.

Re: Claude Code weekly rate limits

#108

Post by rmujica »

andruby wrote: post #36
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.

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.

Re: Claude Code weekly rate limits

#109

Post by andix »

thoughtfulappco wrote: post #79
serial_dev wrote: post #56

Earlier quoted context omitted.

Affecting 5% of users to me sounds like it affects pretty much everyone who got some value out of the tool and is not a casual coder.

I dont know if running an agent 24/7 means you are "better" than casual coder. Code quality is still a thing, HITL i believe in still (not buying complete agent/mcp hype), I don't know if using more resources = extracting more value atm

I don't really get how those 24/7 agents should work. Claude code is the first tool that gives me really good LLM code, but it needs A LOT of guidance. I even interrupt it often, to stop it following through on bad ideas.

Re: Claude Code weekly rate limits

#110

Post by gnator »

richwater wrote: post #75
flashgordon wrote: post #64

Ok I really really have to figure out how to have a local setup of the open-source LLMs. I know i know - the "fixed costs" are high. But I have a strong feeling being able to setup local LLMs (and the rig for it) is the next build-your-own-PC phase. All I want is a coding agent and the grunt power to run it locally. Everything else Il build (generate) with it. I see so many folks claiming crazy hardware rigs and perf…

If you're okay with lower quality output, a $10k Mac Studio will get you there. But you _will_ have to accept lower quality outputs compared to todays' frontier models.

Has anyone tried running with a tenstorrent card? Wanted to see how they fare
Post reply on HN