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

191–200 of 664 posts

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

#191

Post by unyttigfjelltol »

bastard_op wrote: post #108

I've been doing something a lot like this, using a claude-desktop instance attached to my personal mcp server to spawn claude-code worker nodes for things, and for a month or two now it's been working great using the main desktop chat as a project manager of sorts. I even started paying for MAX plan as I've been using it effectively to write software now (I am NOT a developer). Lately it's gotten entirely flaky, wher…

> I'm paying for a service now that has become almost unusable, with absolutely NO means of support to fix it.

Isn’t the future of support a series of automations and LLMs? I mean, have you considered that the AI bot is their tech support, and that it’s about to be everyone else’s approach too?

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

#192

Post by eightysixfour »

mikkupikku wrote: post #174
eightysixfour wrote: post #171

Earlier quoted context omitted.

Sorry, I disagree here. For the specific flow I'm talking about - monthly recurring payments - the UX is about as highly optimized for success as it gets. There are ways to do it via the web, on the phone with a bot, bill pay in your own bank, set it up in-store, in an app, etc. These people don't want the thing done, they want to talk to someone on the phone. The monthly payment is an excuse to do so. I know, we did…

Recurring monthly payments I set to go automatic, but setting that up in the first place I usually do through a phone call. I know some people just want somebody to talk to, same as going through the normal checkout lines at the grocery store, but I think an equally large part of this is people just wanting somebody else to do the work (using the website, or scanning groceries) for them.

> but I think an equally large part of this is people just wanting somebody else to do the work (using the website, or scanning groceries) for them.

Again, this is something my firm studied. Not UX "interviews," actual behavioral studies with observation, different interventions, etc. When you're operating at utility scale there are a non-negligible number of customers who will do more work to talk to a human than to accomplish the task. It isn't about work, ease of use, or anything else - they legitimately just want to talk.

There are also some customers who will do whatever they can to avoid talking to a human, but that's a different problem than we're talking about.

But this is a digression from my main point. Most of the "easy things" AI can do for customer support are things that are already easily solved in other places, people (like you) are choosing not to use those solutions, and adding AI doesn't reduce the number of calls that make it to your customer service team, even when it is an objectively better experience that "does the work."

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

#193

Post by afandian »

kordlessagain wrote: post #185

> My guess is that this likely tripped the "Prompt Injection" heuristics that the non-disabled organization has. Is it me or is this word salad?

It's deliberately not straightforward. Just like the joke about Americans being shoutier than Brits. But it is meaningful.

I read "the non-disabled organization" to refer to Anthropic. And I imagine the author used it as a joke to ridicule the use of the word 'organization'. By putting themselves on the same axis as Anthropic, but separating them by the state of 'disabled' vs 'non-disabled' rather than size.

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

#194

Post by nawgz »

Aurornis wrote: post #175
nawgz wrote: post #148

Earlier quoted context omitted.

> I'm talking about obvious abusive behavior, akin to griefing other users Right, but we're talking about a private isolated AI account. There is no sense of social interaction, collaboration, shared spaces, shared behaviors... Nothing. How can you have such an analogue here?

Plenty of reasons: Abusing private APIs, using false info to sign up (attempts to circumvent local regulations), etc.

These are in no way similar to griefing other users, they are attacks on the platform...

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

#195

Post by throwup238 »

sixtyj wrote: post #149
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…

They whistleblowed themselves that Claude Cowork was coded by Claude Code… :)

You can tell they’re all vibe coded.

Claude iOS app, Claude on the web (including Claude Code on the web) and Claude Code are some of the buggiest tools I have ever had to use on a daily basis. I’m including monstrosities like Altium and Solidworks and Vivado in the mix - software that actually does real shit constrained by the laws of physics rather than slinging basic JSON and strings around over HTTP.

It’s an utter embarrassment to the field of software engineering that they can’t even beat a single nine of reliability in their consumer facing products and if it wasn’t for the advantage Opus has over other models, they’d be dead in the water.

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

#196

Post by wwweston »

tuhgdetzhh wrote: post #150
Bombthecat wrote: post #126

Earlier quoted context omitted.

Well, they vibe code almost every tool at least

Claude Code has accumulated so much technical dept (+emojis) that Claude Code can no longer code itself.

What’s the opposite of bootstrapping? Stakebooting?

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

#197

Post by ankit219 »

phreack wrote: post #178
ankit219 wrote: post #91

Earlier quoted context omitted.

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…

Wait what? Really? All caps is a bannable offense? That should be in all caps, pardon me, in the terms of use if that's the case. Even more so since there's no support at the highest price point.

Its a combination. All caps is used in prompts for extra insistence, and has been common in cases of prompt hijacking. OP was doing it in combination with attempting to direct claude a certain way, multiple times, which might have looked similar to attempting to bypass teh system prompt.

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

#198

Post by b00ty4breakfast »

notsure2 wrote: post #159
sixtyj wrote: post #149

Earlier quoted context omitted.

They whistleblowed themselves that Claude Cowork was coded by Claude Code… :)

Whistleblowed dog food.

normally you don't share your dog food when you find out it actually sucks.

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

#199

Post by verdverm »

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.

Sounds like OP has multiple org accounts with Anthropic.

The main one in the story (disabled) is banned because iterating on claude.md files looks a lot like iterating on prompt injections, especially as it sounds the multiple Claude's got into it with each other a bit

The other org sounds like the primary account with all the important stuff. Good on OP for doing this work in a separate org, a good recommendation across a lot of vendors and products.

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

#200

Post by benjiro »

pixl97 wrote: post #151
raincole wrote: post #60

Earlier quoted context omitted.

Which shouldn't be bannable imo. Rate throttle is a more reasonable response. But Anthropic didn't reply to the author, so we don't even know if it's the real reason they got banned.

>if it's the real reason they got banned. I mean, what a country should do it put a law in effect. If you ban a user, the user can submit a request with their government issued ID and you must give an exact reason why they were banned. The company can keep this record in encrypted form for 10 years. Failure to give the exact reason will lead to a $100,000 fine for the first offense and increase from there up to suspe…

Companies will simply give some kind of standard answer, that is legally "cover our butts" and be done with it.

Its like that cookie wall stuff, how much dark patterns are implemented. They followed the letter of the law, not the spirit of the law.

To be honest, i can also see the point from the company side. Giving a honest answer can just anger people, to the point they sue. People are often not as rational as we all like our fellow humans to be.

Even if the ex-client lose in court, that is how much time you wasted on issue clients... Its one thing if your a big corporation with tons of lawyers but small companies are often not in the position to deal with that drama. And it can take years to resolve. Every letter, every phone call to a lawyer, it stacks up fast! Do you get your money back? Maybe, depends on the country, but your time?

I am not pro companies but its often simply better to have the attitude "you do not want me as your client, let me advocate for your competitor and go there".

Post reply on HN