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

271–280 of 664 posts

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

#271

Post by slimebot80 »

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

I often ask Claude to update Claude.md and skills..... and sometimes I'll just do that in a new window while my main window is busy and I have time.

Wonder if this is close to triggering a warning? I only ever run in the same codebase, so maybe ok?

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

#272

Post by measurablefunc »

inimino wrote: post #266
measurablefunc wrote: post #262

Earlier quoted context omitted.

Only people who work at Anthropic know why the account was flagged & banned & they will never tell you.

...if anyone.

Good point. They might not know why either.

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

#273

Post by throwup238 »

loopdoend wrote: post #269
throwup238 wrote: post #195

Earlier quoted context omitted.

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 utte…

Single nine reliability would be 90% uptime lol. For 99.9% we call it triple 9 reliability.

Single 9 would be 90%, which is roughly what I’m experiencing between CC for Web and the Claude iOS app. About 1 in 10 messages fail because of an unknown error and 1 in 10 CC for web sessions die irrecoverably. It’d probably be worse except for the fact that CC’s bugs in the terminal aren’t show stoppers like they are on web/mobile.

The only way Anthropic has two or three nines is in read only mode, but that’s be like measuring AWS using the console uptime while ignoring the actual control plane.

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

#274

Post by genewitch »

tlogan wrote: post #240

Can someone explain what he was actually doing here? Was the issue that he was reselling these Claude.md files, or that he was selling project setup or creation services to his clients? Or maybe all scaffolding activity (back and forth) looked like automated usage?

if possible, can you quote the part of their TOS/TOU that says i can't use something like aider? (aider is the only one i know, i'm not promoting it)

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

#275

Post by mattnewton »

fluoridation wrote: post #237
mattnewton wrote: post #235

Earlier quoted context omitted.

Then I’m confused about what is confusing you haha. The absurd language is meant to highlight the absurdity they feel over the vague terms in their sparse communication with anthropic. It worked for me.

Because what is meant by "this organization has been disabled" is fairly obvious. The object in Anthropic's systems belonging to the class Organization has changed to the state Disabled, so the call cannot be executed. Anthropic itself is not an organization in this sense, nor is Google, so I would say that referring to them as "non-disabled organizations" is an equivocation fallacy. Besides that, I can't tell if it'…

It’s a joke because they do not see themselves as an organization, they bought a personal account, were banned without explanation and their only communication refers to them as a “disabled organization”.

Anthropic and Google are organizations, and so an “un disabled organization” here is using that absurdly vague language as a way to highlight how bad their error message was. It’s obtuseness to show how obtuse the error message was to them.

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

#276

Post by genewitch »

vunderba wrote: post #268
genewitch wrote: post #246

Earlier quoted context omitted.

sounds like the "thinking tokens" are a mechanism to extract more money from users?

Anecdotally but it definitely feels like in the last couple weeks CC tends to be more aggressive at pulling in significantly larger chunks of an existing code base - even for some simple queries I'll see it easily ramp up to 50-60k token usage.

I'm curious if anyone has logged the number of thinking tokens over time. My implication was the "thinking/reasoning" modes are a way for LLM providers to put their thumb on the scale for how much the service costs.

they get to see (if not opted-out) your context, idea, source code, etc. and in return you give them $220 and they give you back "out of tokens"

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

#277

Post by netsharc »

epolanski wrote: post #218
Aurornis wrote: post #61

Earlier quoted context omitted.

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…

Tangential but you reminded me of why I don't give feedback to people I interview. It's a huge risk and you have very low benefit. It once happened to me to interview a developer who's had a 20-something long list of "skills" and technologies he worked with. I tried basic questions on different topics but the candidate would kinda default to "haven't touched it in a while", "we didn't use that feature". Tried general…

I wonder if there needs to be an "NDA for feedback"... or at least a "non-disparagement agreement".

Something along the lines of "here's the contract, we give you feedback, you don't make it public [is some sharing ok? e.g. if they want to ask their life coach or similar], if you make it public the penalty is $10000 [no need to be crazy punitive], and if you make it public you agree we can release our notes about you in response."

(Looking forward to the NALs responding why this is terrible.)

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

#278

Post by elevation »

I can't wait to be able to run this kind of software locally, on my own buck.

But I've seen orgs bite the bullet in the last 18 months and what they deployed is miles behind what Claude Code can do today. When the "Moore's Law" curve for LLM capability improvements flattens out, it will be a better time to lock into a locally hosted solution.

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

#279

Post by measurablefunc »

tomwphillips wrote: post #139

The post is light on details. I'd guess the author ended up hammering the API and they decided it was abuse. I expect more reports like this. LLM providers are already selling tokens at a loss. If everyone starts to use tmux or orchestrate multiple agents then their loss on each plan is going to get much larger.

There are people on twitter bragging about using 100s of agents. Here's one example: https://twitter.com/nearcyan/status/2012948508764946484

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

#280

Post by Ronsenshi »

vimda wrote: post #134
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.

Yeah, referring to yourself once as a "disabled organisation" is a good bit, referencing anthropics silly terminology. Keeping it for the duration made this a very hard follow

Sounds like author of the post might have needed an AI to review and fix his convoluted writing. Maybe even two AIs!
Post reply on HN