| ▲ | blitzar 5 days ago |
| > Anthropic is saying that one out of every 20 users will hit the new limit. I regularly hit the the Pro limits 3 times a day using sonnet. If I use claude code & claude its over in about 30 minutes. No multi 24/7 agent whatever, no multiple windows open (except using Claude to write a letter between claude code thoughts). I highly doubt I am a top 5%er - but wont be shocked if my week ends on a wednessday. I was just starting to use Claude chat more as it is in my subscription but if I can not rely on it to be available for multiple days its functionally useless - I wont even bother. |
|
| ▲ | Aurornis 5 days ago | parent | next [-] |
| > If I use claude code & claude its over in about 30 minutes. Can you share what you're doing? I've been experimenting with Claude Code and I feel like I have to be doing a lot with it before I even start seeing the usage warning limits on the $20/month plan. When I see people claiming they're getting rate limited after 30 minutes on the $100/month plan I have a hard time understanding what they're doing so different. For what it's worth I don't use it every day, so maybe there's a separate rate that applies to heavy and frequent users? |
| |
| ▲ | gorbypark 4 days ago | parent | next [-] | | As a $20 month user, I can tell you in my experience it's "refactoring" jobs that really smash through those tokens quickly. If you do a "write a component that does this" kinda thing, you can use the $20 plan almost an unlimited amount of time. If you are doing "find all instances of ComponentFoo, change to ComponentBar, refactor each screen for correct usage of ComponentBar" kinda things, it's going to grep through your code, find multiple files, read all of them into context and start making changes one by one and/or spin up a subagent to do it. You'll be rate limited pretty quick doing things that way. | | |
| ▲ | mike_hearn 4 days ago | parent | next [-] | | Are people really using LLMs this way? Can't your IDE at least attempt global refactorings? I get that it's harder with dynamic languages like Python but using an LLM to rename a class seems like using a nuke to crack a nut. | | |
| ▲ | gorbypark 2 days ago | parent [-] | | For sure, it was a bit of a simplified example, but you can imagine prompts that are asking the LLM to touch dozens of files at once. A lot of people will use fairly high level requests, "make a screen in my app that does this" and that ends up making screens, components, queries, local state changes, etc etc. It adds up quick having so much in the context at once (and if you /clear the context and ask it to do anything more than one off changes in a file, it's gonna grep and glob it's way through your code looking for the right files) |
| |
| ▲ | nkassis 4 days ago | parent | prev | next [-] | | That kind of gives a point in favor of AI enabled IDEs, these kind of operations could often be achieved with simple refactoring tools available without AI today and save massive amount of trees. | |
| ▲ | gaws 2 days ago | parent | prev [-] | | > If you are doing "find all instances of ComponentFoo, change to ComponentBar, refactor each screen for correct usage of ComponentBar" kinda things, it's going to grep through your code, find multiple files, read all of them into context and start making changes one by one and/or spin up a subagent to do it. You'll be rate limited pretty quick doing things that way. Huh?? grep and sed do this for free; you don't need A.I. for that. |
| |
| ▲ | flutas 5 days ago | parent | prev [-] | | $20/mo plan doesn't include opus (the larger model) like the $100+ plans do, it's likely they are hitting the opus limit which is fairly low. | | |
| ▲ | r053bud 4 days ago | parent | next [-] | | The $20/month plan most definitely does include Opus. Just not a ton of usage allowed. | | | |
| ▲ | flowerthoughts 4 days ago | parent | prev [-] | | I'm on the $20 and was hitting the limit quite often. It lasted 2.5 h out of 5 h if I went all in. So even before this questionable change, we were at 50% utilization at most. And I guess it'll go downhill from here. Anthropic, I wish you the best. Claude is a great tool at good value. But if you keep changing the product after my purchase, that's bad value. |
|
|
|
| ▲ | bogtog 5 days ago | parent | prev | next [-] |
| > I highly doubt I am a top 5%er - but wont be shocked if my week ends on a wednessday. I was just starting to use Claude chat more as it is in my subscription but if I can not rely on it to be available for multiple days its functionally useless - I wont even bother. You very well might be a top 5%er among people only on the Pro rather than Max plan |
|
| ▲ | ketzo 5 days ago | parent | prev | next [-] |
| What does your Claude code usage look like if you’re getting limited in 30 minutes without running multiple instances? Massive codebase or something? |
| |
| ▲ | blitzar 5 days ago | parent [-] | | I set claude about writing docstrings on a handful of files - 4/5 files couple 100 lines each - couple of classes in each - it didnt need to scan codebase (much). Low danger task so I let it do as it pleased - 30 minutes and was maxed out. Could probably have reduced context with a /clear after every file but then I would have to participate. | | |
| ▲ | tlbsofware 5 days ago | parent | next [-] | | You can tell it to review and edit each file within a Task/subagent and can even say to run them in parallel and it will use a separate context for each file without having to clear them manually | | |
| ▲ | blitzar 5 days ago | parent [-] | | Every day is a school day - I feel like this is a quicker way to burn usage but it does manage context nicely. | | |
| ▲ | tlbsofware 5 days ago | parent [-] | | I haven’t ran any experiments about token usage with tasks, but if you ran them all together without tasks, then each files full operation _should_ be contributing as cached tokens for each subsequent request. But if you use a task then only the summary returned from that task would contribute to the cached tokens. From my understanding it actually might save you usage rates (depending on what else it’s doing within the task itself). I usually use Tasks for running tests, code generation, summarizing code flows, and performing web searches on docs and summarizing the necessary parts I need for later operations. Running them in parallel is nice if you want to document code flows and have each task focus on a higher level grouping, that way each task is hyper focused on its own domain and they all run together so you don’t have to wait as long, for example: - “Feature A’s configuration”
- “Feature A’s access control”
- “Feature A’s invoicing” |
|
| |
| ▲ | stuaxo 5 days ago | parent | prev | next [-] | | I hope you thoroughly go through these as a human, purely AI written stuff can be horrible to read. | | |
| ▲ | blitzar 5 days ago | parent [-] | | Docstring slop is better than code slop - anyway that is what git commits are for - and I have 4.5 hours to do that till next reset. | | |
| |
| ▲ | Kurtz79 4 days ago | parent | prev [-] | | If I understand correctly, looking at API pricing for Sonnet, output tokens are 5 times more expensive than input tokens. So, if rate limits are based on an overall token cost, it is likely that one will hit them first if CC reads a few files and writes a lot of text as output (comments/documentation) rather than if it analyzes a large codebase and then makes a few edits in code. |
|
|
|
| ▲ | rapind 4 days ago | parent | prev [-] |
| I think you'll want to specify your /model to not use opus. Strangely unintuitive, but I opted out of opus on the max plan myself and aren't really having any usage issues since. |
| |
| ▲ | blitzar 4 days ago | parent [-] | | no opus in claude code on my el'cheapo plan ($20 - pro) - used it occasionally in claude desktop and its as expensive as they advertise. |
|
