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

551–560 of 664 posts

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

#551

Post by jfyi »

fauigerzigerk wrote: post #523
user3939382 wrote: post #502

Earlier quoted context omitted.

Yeah kind of ironic to make a comment about controlling your emotions while cursing at a stranger because you disagreed with their reasonable perspective.

You are assuming that hinkley intended to control their emotions and that cursing wasn't just a rhetorical thing in this instance. There clearly is a link between words and emotions. But this link - and even more so the link between emotions and actions - is very complex. Too many fears are based on the assumption of a rather more reductionist and mechanistic sort of link where no one has any control over anything. T…

I agree, it's rhetorical. It was meant to be pointed. It's just too ironic in this scenario.

It loses meaning instead of accentuating it, and predictably so. It probably wasn't the best device to get this specific point across and certainly left the expected counter argument as low hanging fruit.

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

#552

Post by mohsen1 »

Mashimo wrote: post #418
mohsen1 wrote: post #340

I am doing very similar thing to this and no issue. Even though I am using GLM 4.7 due to cost I have a complete org hierarchy for Claudes. Director, EM and Worker Claude Code instances working on a very long horizon task. Code is open source: https://github.com/mohsen1/claude-code-orchestrator

How is your experience with GLM 4.7? I'm thinking about trying it after my Github Copilot runs out end of month. Just hobby projects.

Pay the $3 and try it with Claude code. It’s great!

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

#553

Post by Sparkyte »

We need a collapse in AI to right the ships of AI like the the dotcom bubble burst. If we do it now, it will hurt less. Novel ideas in AI will succeed and materials costs will lower. Memory being so bought up till 2029 is not a good thing for anyone especially if we need to see a successful future in AI. More efficient systems and so on.

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

#555

Post by fluoridation »

hluska wrote: post #445
fluoridation wrote: post #373

Earlier quoted context omitted.

Again, I don't agree. If you replace every instance of "non-disabled organization" with just "company", the sentences make sense. There's no need to suppose that the term means anything else, when this interpretation resolves all the outstanding questions satisfactorily and simply.

I’m sorry but the fact this has turned into a multi comment debate is proof that that phrase was way too ambiguous to be included. That phrase made no sense and the article, while unreliable, would have at least been more readable without it.

No argument there.

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

#556

Post by jsw97 »

This is scary and it affects the degree to which I invest in building Claude-specific tooling, either code or in my brain. You can never guarantee that a dangerously-skip-permissions session is going to stay on the rails, what flags it might trip while you're not looking.

I wonder if Anthropic realizes the chilling effect this kind of event has on developers. It's not just the ones who get locked out -- it's a cost for everybody, because we can't depend on the tool when it's doing precisely what it's best at.

Personally, I am already avoiding Gemini because a) I don't really understand their policy for training on your data; and b) if Google gets mad at me I lose my email. (Which the author also notes.)

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

#557

Post by croes »

urbandw311er wrote: post #431
PunchyHamster wrote: post #394

We really need some law to stop "you have been banned and we won't even tell you actual reason for it", it's become a plague, made worse with automated systems giving out a ban

Do we though? It’s an important question about liberty - at what point does a business become so large that it’s not allowed to decide who gets to use it? There was a famous case here in the UK of a cake shop that banned a customer for wanting a cake made for a gay wedding because it was contra the owners’ religious beliefs. That was taken all the way up to the Supreme Court IIRC.

You missed the 2nd part "and we won't even tell you actual reason for it".

The cake shop said why. FB, Google, Anthropic don't say why, so you don't even know what exactly you need to sue for. That is kafkaesque

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

#558

Post by naasking »

kuerbel wrote: post #518
midtake wrote: post #494

Earlier quoted context omitted.

What do you mean? This is very much true. We are economically compelled to buy food from supermarkets, for instance, because hunting and fishing have become regulated, niche activities. Compared to someone from the 1600s who could scoop a salmon out of the river with a bucket, we are quite oppressed.

On the flip side, fishing quotas are the reason there are some fish left. However you are free to grow your own vegetables.

Actually, cities often regulate gardens:

https://www.savingadvice.com/articles/2025/07/07/10160132_th...

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

#559

Post by erichocean »

Whoops, I literally did the same thing as this guy earlier this week, but did the testing using `claude -p` so I can identify when Claude Code would (or would not) load Skills for a particular prompt, so that I could improve the skill definition.

Who knew that using Claude to introspect on itself was against the ToS?

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

#560

Post by kerblang »

direwolf20 wrote: post #247
kerblang wrote: post #216

Earlier quoted context omitted.

[flagged]

I don't see any such agreement here, and your comment is very rude toward the author.

I'm not being rude to parent poster (instead, am agreeing) or the person who wrote the article.

I might have been rude to all the people/bots who insist the article's author is lying because it contradicts AI-everything.

Post reply on HN