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

I was banned from Claude for scaffolding a Claude.md file?

hugodaniel.com

Post reply on HN
Print view View original

631–640 of 664 posts

Re: I was banned from Claude for scaffolding a Claude.md file?

#631

Post by cryptonector »

StefanBatory wrote: post #391
cryptonector wrote: post #385

Earlier quoted context omitted.

No, being beholden to a payments and banking system that can cancel you at any time, for any reason, with little hope for redress.

Because in the past you weren't beholden to payments?

In the pre-banking era you could get robbed, killed, taxed to death, made to fight in a war, etc. That's all still true, but now most of your resources (savings) will be stuck in a place where there is no need for violence to cause you to lose all of it.

The way we normally deal with all these problems as a society is to apply force (via police, courts) to ensure that everyone has certain 'rights'.

The problem today is that while you have certain rights, like fairly strong rights to private property interests in real estate and such, we generally have very weak private property rights in financial properties. This is a problem world-wide. We need to fix this in our countries.

Re: I was banned from Claude for scaffolding a Claude.md file?

#632

Post by swordsith »

furyofantares wrote: post #163
kmoser wrote: post #103

Earlier quoted context omitted.

If you want to split hairs, it seem that Anthropic has support as a noun but not as a verb.

I mean the comment says they literally don't have support and also complains they don't have a support bot, when they have both. https://support.claude.com/en/collections/4078531-claude > As a paid user of Claude or the Console, you have full access to: > All help documentation > Fin, our AI support bot > Further assistance from our Product Support team > Note: While we don't offer phone or live chat support, our Pro…

I would think on his suspension and refund he would not have access to that support channel anymore?

Re: I was banned from Claude for scaffolding a Claude.md file?

#634

Post by dloranc »

I was also banned several months ago, but I don’t think it happened because I created a CLAUDE.md file or anything like that. I have no idea why I was banned, since I only used Claude Code for typical CRUD projects - where AI really excels. Here’s my timeline:

1. Claude Code stopped working. 2. I received an email about the ban. 3. Fine, time to contact support. I've wrote to them. 4. I got an automated message saying they were reviewing my case. 5. I received a refund (I had a Pro plan) in the meantime. 6. After a few days I got this funny email:

Hi there,

We're reaching out to people who recently canceled their Claude Code subscription in order to understand why you decided to cancel.

We'd like to invite you to participate in an AI-moderated interview about your experience with Claude Code—including what improvements you'd like to see us make.

This approach uses an AI interviewer to ask you questions and respond to your answers, creating a conversational experience you can complete at your convenience.

Here's what you need to know:

The interview takes 15-20 minutes to complete This interview will be available until Monday October 13 at 9pm PT For completing the interview, you'll receive a $40 USD (or local equivalent) Amazon gift card within 3-5 business days Please complete only one interview per person As much as possible, help us know you're not a bot by showing your beautiful human face!

Your survey may terminate early if you record illegible video content (ex: overly loud environments, aren't well lighted, etc) Participate Now

This interview is administered by a third party, Listen Labs. By participating in the interview, you agree to Listen Labs' Privacy Policy. Anthropic may use your responses to improve our services and follow up.

Your honest feedback—whether your experience was positive, challenging, or mixed—is invaluable in helping us understand how to make Claude Code work better for developers like you.

Thank you for your time and insights!

–The Anthropic Team

7. Wait, you banned me and now you’re sending me this email? Seriously? Okay, I decided to participate in the survey. Unfortunately, when I selected the option that it was due to a bug or some issue, they ended the survey. No gift card.

8. A few days later, I received an email saying they couldn’t reinstate my account because I had violated their usage policy. How? No idea.

9. After a few more days, I got an email saying they had reinstated my account. They also mentioned they believed it was a bug.

It was crazy ¯\_(ツ)_/¯

Re: I was banned from Claude for scaffolding a Claude.md file?

#635

Post by redeeman »

schnebbau wrote: post #143
Aurornis wrote: post #65

Earlier quoted context omitted.

More likely explanation: Their account was closed for some other reason, but it went into effect as they were trying this. They assumed the last thing they were doing triggered the ban.

They were probably using an unapproved harness, which are now banned.

what? you are not allowed to use anything but a few blessed things with claude code?

Re: I was banned from Claude for scaffolding a Claude.md file?

#636

Post by LTL_FTC »

CamperBob2 wrote: post #625
LTL_FTC wrote: post #612

Earlier quoted context omitted.

I mean, you could put together a cluster of dgx sparks (8 of them) and hit 100tps with high concurrency: https://forums.developer.nvidia.com/t/6x-spark-setup/354399/... Or a single user at about 10tps. This is probably around $30k if you go with the 1tb models.

10 tps, maybe, given the Spark's hobbled memory bandwidth. That's too slow, though. That thread is all about training, which is more compute-intensive. A couple of DGX Stations are more likely to work well for what I have in mind. But at this point, I'd be pleasantly surprised if those ever ship. If they do, they will be more like $200K each than $100K.

I linked results where the user ran Kimi k2 across his 8-node cluster. Inference results are listed for 1,10,100 concurrent requests.

Edit to add:

Yeah, those stations with the GB300 look more along the lines of what I would want as well but I agree, they’re probably way beyond my reach.

Re: I was banned from Claude for scaffolding a Claude.md file?

#637

Post by oblio »

xattt wrote: post #601
7777777phil wrote: post #582

Earlier quoted context omitted.

Can you elaborate on "using the allowed limits to their fullest extent?"

Likely using timers/alarms to keep track of when jobs can resume.

That sounds benign but I'm guessing all of that was in a 24/7 loop and probably running in parallel a bunch of times.

It's like the "unlimited Gmail storage" that's now stuck at 15GB since 2012, despite the cost of storage probably going down probably 20x since 2012.

Companies launch products with deceptive marketing and features they can't possibly support and then when they get called on their bluff, they have to fall back to realistic terms and conditions.

Re: I was banned from Claude for scaffolding a Claude.md file?

#638

Post by oblio »

kachapopopow wrote: post #609
TyrunDemeg101 wrote: post #570

I was banned as well, out of the blue suddenly and without warning. I believe it was because I was either doing something like what OP was doing AND/OR using the allowed limits to their fullest extent. It completely blew me away and I felt suddenly so betrayed. I was paying $200/mo to fully utilize a service they offered and then without warning I apparently did something wrong and had no recourse. No one to ask, no…

this is just wrong, I have several 3x x20 accounts running full tilt hitting limits every week I did get few accounts banned, but that's because my proxy was leaking nginx headers.

> but that's because my proxy was leaking nginx headers.

What do you mean with this?

Re: I was banned from Claude for scaffolding a Claude.md file?

#639

Post by oblio »

cyanydeez wrote: post #522
throwup238 wrote: post #117

Earlier quoted context omitted.

Anthropic has been flying by the seat of their pants for a while now and it shows across the board. From the terminal flashing bug that’s been around for months to the lack of support to instabilities in Claude mobile and Code for the web (I get 10-20% message failure rates on the former and 5-10% on CC for web). They’re growing too fast and it’s bursting the seams of the company. If there’s ever a correction in the…

I think your surmise is probably wrong. It's not that their growing to fast, it's that their service is cheaper than the actual cost of doing business. Growth isn't a problem unless you dont actually pay for the cost of every user you subscribe. Uber, but for poorly profitable business models.

Interesting comparison, Uber.

> Since its founding in 2009, Uber has incurred a cumulative net loss of approximately $10.9 billion.

Now, Uber has become profitable, and will probably become a bit more profitable over time.

But except for speculators and probably a handful of early shareholders, Uber will have lost everyone else money for 20 years since its founding.

For comparison, Lyft, Didi, Grab, Bolt are in the same boat, most of them are barely turning profitable after 10+ years. Turns out taxis are a hard business, even when you ramp up the scale to 11. Though they might become profitable over the long term and we'll all get even worse and more abusive service, and probably more expensive than regular taxis would have been, 15-20 years from now.

I mean, we got some better mobile apps from taxi services, so there's that.

Oh, also a massive erosion of labor rights around the world.

Re: I was banned from Claude for scaffolding a Claude.md file?

#640

Post by bastard_op »

cyanydeez wrote: post #528
bastard_op wrote: post #184

Earlier quoted context omitted.

I started using claude-code, but found it pretty useless without any ability to talk to other chats. Claude recommended I make my own MCP server, so I did. I built a wrapper script to invoke anthropic's sandbox-runtime toolkit to invoke claude-code in a project with tmux, and my mcp server allows desktop to talk to tmux. Later I built in my own filesystem tools, and now it just spawns konsole sessions for itself invo…

what do you actually do besides build tools to build tools to build tools?

My normal day job is IT consulting, network/security mostly, so I'm using it largely to connect to my workers, sandboxed or not, to make me scripts to do things, modify configurations, and I built out an ansible/terraform integration in my mcp to be able to start doing direct automation tasking them directly via it as well.

The whole thing I needed was to let AI reach out and touch things, be my hands essentially. This is why I built my tmux/worker system, I built out an xdg-portal integration to let it screen shot and soon interact with my desktop as a poc.

I could let it just start logging into devices and letting them modify configs, but it's pretty dumb about stuff like modifying fortigate configurations at times what it thinks it should do vs what the cli actually let's it do, so I have to proof much of it, but that's why I'm building it to be able to run ansible/terraform jobs instead using frameworks that are provided by the vendors for direct configurations to allow for atomic config changes as much as vendor implementations allow for.

Post reply on HN