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

71–80 of 664 posts

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

#71

Post by rtkwe »

languagehacker wrote: post #21

Thinking 220GBP for a high-limit Claude account is the kind of thinking that really takes for granted the amount of compute power being used by these services. That's WITH the "spending other people's money" discount that most new companies start folks off with. The fact that so many are painfully ignorant of the true externalities of these technologies and their real price never ceases to amaze me.

That's the problem with all the LLM based AI's the cost to run them is huge compared to what people actually feel they're worth based on what they're able to do and the gap seems pretty large between the two imo.

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

#72

Post by Romario77 »

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...

One Claude agent told other Claude agent via CLAUDE.md to do things certain way.

The way Claude did it triggered the ban - i.e. it used all caps which apparently triggers some kind of internal alert, Anthropic probably has some safeguards to prevent hacking/prompt injection and what the first Claude did to CLAUDE.md triggered this safeguard.

And it doesn't look like it was a proper use of the safeguard, they banned for no good reason.

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

#74

Post by falloutx »

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…

you are never gonna hear back from Anthropic, they don't have any support. They are a company who feels like their model is AGI now they dont need humans except when it comes to paying.

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

#75

Post by 0xferruccio »

swiftcoder wrote: post #49
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…

> shows a profound gap between what people think working in customer service is like and how fucking hard it actually is Nicely fitting the pattern where everyone who is bullish on AI seems to think that everyone else's specialty is ripe for AI takeover (but not my specialty! my field is special/unique!)

to be fair at least half of the software engineers i know are facing some level of existential crisis when seeing how well claude code works, and what it means for their job in the long term

and these are people are not junior developers working on trivial apps

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

#76

Post by staticman2 »

onraglanroad wrote: post #50

So you have two AIs. Let's call them Claude and Hal. Whenever Claude gets something wrong, Hal is shown what went wrong and asked to rewrite the claude.md prompt to get Claude to do it right. Eventually Hal starts shouting at Claude. Why is this inevitable? Because Hal only ever sees Claude's failures and none of the successes. So of course Hal gets frustrated and angry that Claude continually gets everything wrong n…

I don't think it's inevitable often the AI will just keep looping again and again. It can happily without frustration loop forever.

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

#78

Post by blindriver »

There needs to be a law that prevents companies from simply banning you, especially when it's an important company. There should be an explanation and they shouldn't be allowed to hide behind some veil. There should be a real process with real humans that allow for appeals etc instead of scripts and bots and automated replies.

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

#79

Post by pinkmuffinere »

swiftcoder wrote: post #49
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…

> shows a profound gap between what people think working in customer service is like and how fucking hard it actually is Nicely fitting the pattern where everyone who is bullish on AI seems to think that everyone else's specialty is ripe for AI takeover (but not my specialty! my field is special/unique!)

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.

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

#80

Post by writeslowly »

I've triggered similar conversation level safety blocks on a personal Claude account by using an instance of Deepseek to feed in Claude output and then create instructions that would be copied back over to Claude (there wasn't any real utility to this, it was just an experiment). Which sounds kind of similar to this. I couldn't understand what the heuristic was trying to guard against, but I think it's related to concerns about prompt injections and users impersonating Claude responses. I'm also surprised the same safeguards would exist in either the API or coding subscription.
Post reply on HN