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

61–70 of 664 posts

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

#61

Post by Aurornis »

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.

Years ago I was involved in a service where we some times had to disable accounts for abusive behavior. I'm talking about obvious abusive behavior, akin to griefing other users.

Every once in while someone would take it personally and go on a social media rampage. The one thing I learned from being on the other side of this is that if someone seems like an unreliable narrator, they probably are. They know the company can't or won't reveal the true reason they were banned, so they're virtually free to tell any story they want.

There are so many things about this article that don't make sense:

> I'm glad this happened with this particular non-disabled-organization. Because if this by chance had happened with the other non-disabled-organization that also provides such tools... then I would be out of e-mail, photos, documents, and phone OS.

I can't even understand what they're trying to communicate. I guess they're referring to Google?

There is, without a doubt, more to this story than is being relayed.

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

#62

Post by Romario77 »

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.

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

#64

Post by WarmWash »

embedding-shape wrote: post #30
WarmWash wrote: post #25

Earlier quoted context omitted.

Claude is an amazing coding model, its other abilities are middling. Anthropic's strategy seems to be to just focus on coding, and they do it well.

> Anthropic's strategy seems to be to just focus on coding, and they do it well. Based on their homepage, that doesn't seem to be true at all. Claude Code yes, focuses just on programming, but for "Claude" it seems they're marketing as a general "problem solving" tool, not just for coding. https://claude.com/product/overview

Anthropic isn't bothering with image models, audio models, video models, world models. They don't have science/math models, they don't bother with mathematics competitions, and they don't have open model models either.

Anthropic has claude code, it's a hit product, SWE's love claude models. Watching Anthropic rather than listening to them makes their goals clear.

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

#65

Post by Aurornis »

superb_dev wrote: post #31
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.

The author was using instance A of Claude to update a `claude.md` while another instance B of Claude was consuming that file. When Claude B did something wrong, the author asked Claude A to update the `claude.md` so that Claude B didn’t make the same mistake again

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.

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

#66

Post by falloutx »

alistairSH wrote: post #12
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're not alone. I think the author was doing some sort of circular prompt injection between two instances of Claude? The author claims "I'm just scaffolding a project" but that doesn't appear to be the case, or what resulted in the ban...

This tracks with Anthropic, they are actively hostile to security researchers.

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

#67

Post by epolanski »

NitpickLawyer wrote: post #57
epolanski wrote: post #22

Earlier quoted context omitted.

What would be bad in that? Writing the best possible specs for these agents seems the most productive goal they could achieve.

I think the idea is fine, but what might end up happening is that one agent gets unhinged and "asks" another agent to do more and more crazy stuff, and they get in a loop where everything gets flagged. Remember that "bots configured to add a book at +0.01$ on amazon, reached 1M$ for the book" a while ago. Kinda like that, but with prompts.

I still don't get it, get your models better for this far fetched case, don't ban users for a legitimate use case.

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

#68

Post by danielbln »

eightysixfour wrote: post #45
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…

> 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.

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

#69

Post by Aurornis »

tobyhinloopen wrote: post #7

So you were generating and evaluating the performance of your CLAUDE.md files? And you got banned for it?

I think it's more likely that their account was disabled for other reasons, but they blamed the last thing they were doing before the account was closed.

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

#70

Post by codazoda »

properbrew wrote: post #8
lifetimerubyist wrote: post #2

bow down to our new overlords - dont' like it? banned, with no recourse - enjoy getting left behind, welcome to the future old man

I didn't even get to send 1 prompt to Claude and my "account has been disabled after an automatic review of your recent activities" back in 2024, still blocked. Even filled in the appeal form, never got anything back. Still to this day don't know why I was banned, have never been able to use any Claude stuff. It's a big reason I'm a fan of local LLMs. They'll never be SOTA level, but at least they'll keep chugging al…

Since you were forced, are you getting good results from them?

I’ve experimented, and I like them when I’m on an airplane or away from wifi, but they don’t work anywhere near as well as Claude code, Codex CLI, or Gemini CLI.

Then again, I haven’t found a workable CLI with tool and MCP support that I could use in the same way.

Edit: I was also trying local models I could run on my own MacBook Air. Those are a lot more limited than something like a larger Llama3 in some cloud provider. I hadn’t done that yet.

Post reply on HN