It seems just fine to me. This is what Anthropic needs to do if they want to survive. I'm always looking out for someone to integrate an actually good harness to a good model. Once that happens, I'm jumping ship if Anthropic keeps playing these tricks.
It's almost unusable for me now. A simple prompt to merge 3 sub-100-line files with simple node code, on Sonnet 4.6, uses up 20% of my 5 hour quota, on a new/fresh session.
To be fair, my comment was a bit harsher before the update. The way they handle the development, communication and how they treat customers isn't fine. I've seen some angry people post and comment in manners which truly deserved the label hostile.
The whole product with the infrastructure and Claude Code's code appear to be vibe coded.
They appear to take issues seriously mostly when they become posts on hacker news and when articles are published online by major news sites. Customer support is mostly a bot. I don't even know how to reach some actual humans to get support.
I'm sorry if you and others are offended. They've had these issues for several weeks now. I haven't seen any real improvements during this time. I see more features and more bugs.
There have been several releases made over the last few days without any changelogs. The quotas are still as opaque as they've been. This company has some extremely shady business practices.
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 requests where number of cache hits > 0 (to avoid people setting this flag without intent to use it), and you solved the whole issue.
In this case, they handled things pretty well. You can still use openclaw etc with your regular Anthropic subscription, it will just count towards your extra credits / usage which you can buy for a 30% discount compared to API pricing. And they gave everyone one month’s value in credits.
I don’t think they could have done that much better I’d say.
There is very poor clarity about what is and isn't allowed with the Claude SDK/claude -p. Are we allowed to use it to automate stuff? What kind of tasks is it permitted to be used for? What if you call your script 'OrangeClaw' and release that on GitHub? What if your script gets super popular, does it suddenly become against TOS?
This is exactly my point. At what point does it become a ToS violation? Right now it's a huge grey area and the idea of getting my account banned because I crossed an invisible line with zero recourse other than to switch providers is... frustrating.
It's pretty easy to read between the lines tbh. Personal, non-automated use is fine. Using it as a means to automate depleting your 5-hour limit 24/7 ("leftover usage") is not fine. They don't want to put in in the ToS because it's almost impossible because writing what I just said will still have people going "well what's automated, where's the exact line!" when it's all pretty clear what the intended use case here is. The Anthropic peeps have said about as much.
I get that the traditional dev is allergic to the concept of reading between the lines and demands everything to be spelled out explicitly, but maybe you should just see it as something to learn because it's an incredibly useful life skill.
When you're using the SDK, yes it can. Example: I used the Python SDK to translate a bunch of source code recently. I spawned a subagent for each module that needed translating and left it to run for a few hours with a parallelism limit of 5. It blasted through the 5 hour usage and dug into extra usage credits.
I have zero assurances that the above can't result in a ban. The usage pattern is not distinct from OpenClaw.
Just in case it wasn't clear, what they described doesn't need extra tooling. You can write this in your CLI and it will easily cap a Max 20x plan in an hour: "we are converting this entire codebase from TS to C#. Following the guidelines I've written in MIGRATION.md, convert each file individually. Use up to 32 parallel subagents. Track your work for each file in a PROGRESS.md file, which you will update for each file starting and completing. Using an agent team, as a secondary step, add a verification layer where you verify each file individually for accurate migration following the instructions in VERIFICATION.md"
Yea there are other ways to do this, you can set up a separate harness sure to make it more efficient, but just the above will also work, it's just text you paste into your CC terminal, and it will absolutely cap the largest subscription plan available no problem.
That "non-automated" part is where I feel like there is a lack of clarity. They even have some stuff in to allow for scheduling in Claude Code. Seems similar to a cron but "non-automated" would rule out using a cron (right?). I'd love to feel comfortable setting up daily/hourly tasks for Claude Code but that feels iffy. Like I said, I don't think the line is clear.
The lack of clarity doesn't matter because they obviously can't tell if you ran a claude -p a few times today with usual prompts or whether your cron job did. It's impossible for them to reliably tell.
It can tell if your cron is running them every 10 minutes 24/7, because basic biology rules out you doing that for more than a day or so.
Wait, this is news to me. I thought 3rd party use of the sub was unequivocally prohibited?
If I'm understanding you correctly: they changed that policy, you can now use 3rd party software unofficially with the undocumented Claude Code endpoint, and their servers auto-detect this and charge you extra for it?
EDIT: Yeah, something like that?
> Starting April 4 at 12pm PT / 8pm BST, you’ll no longer be able to use your Claude subscription limits for third-party harnesses including OpenClaw. Instead, they’ll require extra usage.
This seems to mean that unauthorized usage of the sub endpoint is tolerated now (and billed as though it were the regular API). And possibly affects claude -p, though I don't know yet.
> If I'm understanding you correctly: they changed that policy, you can now use 3rd party software unofficially with the undocumented Claude Code endpoint, and their servers auto-detect this and charge you extra for it?
That’s correct. It’s more like a convenience technicality: you can use your sub account, but you’re paying extra. So it doesn’t really count towards your subscription in any way.
Subscriptions can buy extra credits against a 30% discount, though, so it’s a decent amount cheaper than actual API, but still prohibitively expensive.
This is already well known, all these AI benchmarks use a different model to judge whether or not the solution was correct.
It’s… remarkably poor, and as demonstrated in the paper, easily gamed. Worst yet, these benchmarks teach AIs to be very short-sighted and hyper-focused on completing the task, rather than figuring out the best solution.
Yes. Apple's not going to come after you for running too many VMs on your personal machine, but if you're running a commercial enterprise involving macOS VMs they do care.
Yes. And the license only allows you to run macOS guests on macOS hosts. So using esxi means you don’t have any license for whatever macOS guests you run.
You are confusing macos guests on KVM (Linux) and macos guests on ESXi which is a real enterprise product, and officially enables you to run as many macos vms as your hardware supports.
Nah, Apple has been extremely restrictive about virtual machines in all kinds of ways, e.g. the minimum terms anyone is able to lease out a VM or Mac to someone else is 24h, making cloud-like workloads practically impossible. For some reason, Apple really doesn’t like virtual machines, and it’s much more intentional than just “probably multiple users”.
I mean, as someone who was in that situation as a customer, we couldn't find a great cloud option for our needs, and we ended up building our first hardware lab with a bunch of macs.
It definitely caused us to buy macs we would have rented and shared.
Correct, us as well, but we’re mainly harvesting refurbished Mac Mini’s.
My biggest problem is the lack of a good CI/CD flow when you can’t work with images and virtual machines. We’re using ansible now to manage the fleet and I’m not a fan.
If they would more than 2 VMs, we’d still buy the hardware, we’d just buy larger ones and have more virtual machines on them. Very likely also use Linux as the host.
I hope one day Apple sees the light like Microsoft also did, but I’m not hopeful.
Frustrating for you, hilarious for me. I had no idea they had hobbled MacOS in this way. It doesn't surprise me at all really, and it's pretty ridiculous.
I'm not sure why people keep giving Apple their money, especially tech-savvy people that would want to run VMs.
The limit is for macOS running in a VM (which is mainly useful for developing iOS and macOS apps, for example cloud-based testing and CI/CD workflows.)
Most developers build web- and server-based systems that use Linux VMs as back-ends.
Most containers used for development are Linux containers, which also run in a Linux VM.
Thanks for this suggestion, I installed it yesterday after seeing this comment and this surely is a breath of fresh air! It appears that everything is designed reasonably well from the ground up. It’s more limited, but what’s there works well.
They don't use Claude Code, they get accused that they don't even trust it themselves.
They use Claude Code, they get accused the code is shit because it's slop.
I think dogfooding is known to be a legitimate approach here.
reply