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

91–100 of 664 posts

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

#91

Post by ankit219 »

cortesoft wrote: post #5

I am really confused as to what happened here. The use of ‘disabled organization’ to refer to the author made it extra confusing. I think I kind of have an idea what the author was doing, but not really.

My rudimentary guess is this. When you write in all caps, it triggers sort of a alert at Anthropic, especially as an attempt to hijack system prompt. When one claude was writing to other, it resorted to all caps, which triggered the alert, and then the context was instructing the model to do something (which likely would be similar to a prompt injection attack) and that triggered the ban. not just caps part, but that in combination of trying to change the system characteristics of claude. OP does not know much better because it seems he wasn't closely watching what claude was writing to other file.

if this is true, the learning is opus 4.5 can hijack system prompts of other models.

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

#92

Post by kmeisthax »

Another instance of "Risk Department Maoism".

If you're wondering, the "risk department" means people in an organization who are responsible for finding and firing customers who are either engaged in illegal behavior, scamming the business, or both. They're like mall rent-a-cops, in that they don't have any real power beyond kicking you out, and they don't have any investigatory powers either. But this lack of power also means the only effective enforcement strategy is summary judgment, at scale with no legal recourse. And the rules have to be secret, with inconsistent enforcement, to make honest customers second-guess themselves into doing something risky. "You know what you did."

Of course, the flipside of this is that we have no idea what the fuck Hugo Daniel was actually doing. Anthropic knows more than we do, in fact: they at least have the Claude.md files he was generating and the prompts used to generate them. It's entirely possible that these prompts were about how to write malware or something else equally illegal. Or, alternatively, Anthropic's risk department is just a handful of log analysis tools running on autopilot that gave no consideration to what was in this guy's prompts and just banned him for the behavior he thinks he was banned for.

Because the risk department is an unaccountable secret police, the only recourse for their actions is to make hay in the media. But that's not scalable. There isn't enough space in the newspaper for everyone who gets banned to complain about it, no matter how egregious their case is. So we get all these vague blog posts about getting banned for seemingly innocuous behavior that could actually be fraud.

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

#93

Post by causalmodels »

bee_rider wrote: post #47
ipaddr wrote: post #17

You are lucky they refunded you. Imagine they didn't ban you and you continued to pay 220 a month. I once tried Claude made a new account and asked it to create a sample program it refused. I asked it to create a simple game and it refused. I asked it to create anything and it refused. For playing around just go local and write your own multi agent wrapper. Much more fun and it opens many more possibilities with unce…

LLMs are kind of fun to play with (this is a website for nerds, who among us doesn’t find a computer that talks back kind of fun), but I don’t really understand why people pay for these hosted versions. While the tech is still nascent, why not do a local install and learn how everything works?

Because my local is a laptop and doesn't have a GPU cluster or TPU pod attached to it.

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

#94

Post by dragonwriter »

Romario77 wrote: post #62
cortesoft wrote: post #5

I am really confused as to what happened here. The use of ‘disabled organization’ to refer to the author made it extra confusing. I think I kind of have an idea what the author was doing, but not really.

You are confused because the message from Claude is confusing. Author is not an organization, they had an account with anthropic which got disabled and Anthropic addressed them as organization.

> Author is not an organization, they had an account with anthropic which got disabled and Anthropic addressed them as organization.

Anthropic accounts are always associated with an organization; for personal accounts the Organization and User name are identical. If you have an Anthropic API account, you can verify this in the Settings pane of the Dashboard (or even just look at the profile button which shows the org and account name.)

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

#95

Post by jitl »

I always take these sorts of "oh no I was banned while doing something innocent" posts with a large helping of salt. At least the ones where someone is complaining about a ban from Stripe, usually it turns out they are doing something that either violates the terms of service or is actually fraudulent. None the less its quite frustrating dealing with these because either way.

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

#96

Post by ryandrake »

superb_dev wrote: post #35
lazyfanatic42 wrote: post #29

Earlier quoted context omitted.

Author really comes off unhinged throughout the article to be frank.

Did we read the same article? The author comes of as pretty frustrated but not unhinged

I wouldn't say "unhinged" either, but maybe just struggling to organize and express thoughts clearly in writing. "Organizations of late capitalism, unite"?

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

#97

Post by munk-a »

throwawaysleep wrote: post #88
munk-a wrote: post #51

Earlier quoted context omitted.

> They're begging corporate decision makers to ask the question, "If Anthropic doesn't trust Claude to run its support, then why should we?" Don't worry - I'm sure they won't and those stakeholders will feel confident in their enlightened decision to send their most frustrated customers through a chatbot that repeatedly asks them for detailed and irrelevant information and won't let them proceed to any other support…

> to send their most frustrated customers through a chatbot But do those frustrated customers matter?

I just checked - frustrated customers isn't a metric we track for performance incentives so no, they do not.

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

#98

Post by eightysixfour »

danielbln wrote: post #68
eightysixfour wrote: post #45

Earlier quoted context omitted.

> Out of all of the different things these agents can do, surely most forms of "routine" customer support are the lowest hanging fruit? I come from a world where customer support is a significant expense for operations and everyone was SO excited to implement AI for this. It doesn't work particularly well and shows a profound gap between what people think working in customer service is like and how fucking hard it ac…

There are some solid usecases for AI in support, like document/inquiry triage and categorization, entity extraction, even the dreaded chatbots can be made to not be frustrating, and voice as well. But these things also need to be implemented with customer support stakeholders that are on board, not just pushed down the gullet by top brass.

Yes but no. Do you know how many people call support in legacy industries, ignore the voice prompt, and demand to speak to a person to pay their recurring, same-cost-every-month bill? It is honestly shocking.

There are legitimate support cases that could be made better with AI but just getting to them is honestly harder than I thought when I was first exposed. It will be a while.

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

#99

Post by pinkmuffinere »

eightysixfour wrote: post #84
pinkmuffinere wrote: post #79

Earlier quoted context omitted.

Perhaps even more-so given the following tagline, "Honestly, AI is better at replacing the cost of upper-middle management and executives than it is the customer service problems", lol. I suppose it's possible eightysixfour is an upper-middle management executive though.

Consultant to, so yes. It could have replaced me and a ton of the work of the people I was supporting.

Ah I see, that definitely lends some weight claim then.

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

#100

Post by csours »

areoform wrote: post #11

I recently found out that there's no such thing as Anthropic support. And that made me sad, but not for reasons that you expect. Out of all of the tech organizations, frontier labs are the one org you'd expect to be trying out cutting edge forms of support. Out of all of the different things these agents can do, surely most forms of "routine" customer support are the lowest hanging fruit? I think it's possible for An…

Human attention will be the luxury product of the next decade.
Post reply on HN