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

▲ Aurornis 6 hours ago | parent | next [-]

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.

	▲	schnebbau 5 hours ago \| parent \| next [-]
		They were probably using an unapproved harness, which are now banned.
	▲	tstrimple 6 hours ago \| parent \| prev [-]
		This does sound sus. I have CC update other project's claude.md files all the time. I've got a game engine that I'm tinkering with. The engine and each of the game concepts I play around with have their own claude.md. The purpose of writing the games is to enhance the engine, so the games have to be familiar with the engine and often engine features come from the game CC rather than the engine CC. To keep the engine CC from becoming "lost" about features implemented each game project has instructions to update the engine's claude.md when adding / updating features. The engine CC bootstraps new game projects with a claude.md file instructing it how to keep the engine in sync with game changes as well as details of what that particular game is designed to test or implement within the engine. All sorts of projects writing to other project's claude.md files.

▲ olalonde 5 hours ago | parent | prev | next [-]

I don't understand how having two separate instances of Claude helps here. I can understand using multiple Claude instances to work in parallel but in this case, it seems all this process is linear...

▲ layer8 4 hours ago | parent | next [-]

The point is to get better prompt corrections by not sharing the same context.

▲ renewiltord 3 hours ago | parent | prev [-]

If you look at the code it will be obvious. Imagine I’m the creator of React. When someone does “create new app” I want to put a Claude.md in the dir so that they can get started easily.

I want this Claude.md to be useful. What is the natural solution to me?

▲ olalonde 3 hours ago | parent [-]

I'd probably do it like this: ask Claude to do a task, and when it fails, have it update its Claude.md so it doesn’t repeat the mistake. After a few iterations, once the Claude.md looks good, just copy-paste it into the scaffolding tool.

▲ renewiltord 3 hours ago | parent [-]

Right, so you see the part where you "ask Claude to do a task" and then "copy-paste it into the template"? He was automating that because he has some n tasks he wants it to do without damaging the prior tasks.

▲ olalonde 2 hours ago | parent [-]

You can just clear the context or restart your Claude instance between tasks. e.g.:

  > do task 1
  ...task fails...
  > please update Claude.md so you don't make X mistake
  > /clear
  > do task 2
  ... task fails ...
  > please update Claude.md so you don't make Y mistake
  > /clear
  etc.

If you want a clean state between tasks you can just commit your Claude.md and `git reset --hard`.

I just don't get why you'd need have to a separate Claude that is solely responsible for updating Claude.md. Maybe they didn't want to bother with git?

▲

renewiltord 2 hours ago | parent [-]

Presumably they didn't want to sit there and monitor Claude Code doing this for each of the 14 things they want done. Using a harness around Claude Code (or its SDK) is perfectly sane for this. I do it routinely. You just automate the entire process so that if you change APIs or you change the tasks, the harness can run and ensure that all of your sets are correctly re-done.

Sitting there and manually typing in "do thing 1; oh it failed? make it not fail. okay, now commit" is incredibly tedious.

	▲	olalonde an hour ago \| parent [-]
		They said they were copy/pasting back and forth. But regardless, what do you mean by "harness" and "sets"? Are you referring to a specific tool that orchestrates Claude Code instances? This is not terminology I'm familiar with in this context. If you have any link that explains what you are talking about, would be appreciated.

▲ slimebot80 an hour ago | parent | prev | next [-]

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?

▲ raincole 6 hours ago | parent | prev [-]

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.

▲

pixl97 5 hours ago | parent | next [-]

>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 suspension of operations privileges in said country.

"But, but, but hackers/spammers will abuse this". For one, boo fucking hoo. For two, just add to the bill "Fraudulent use of law to bypass system restrictions is a criminal offense".

This puts companies in a position where they must be able to justify their actual actions, and it also puts scammers at risk if they abuse the system.

▲

benjiro 4 hours ago | parent [-]

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".

▲

pixl97 2 hours ago | parent | next [-]

>Giving a honest answer can just anger people, to the point they sue.

Again, I'm kind of on a 'suck it dear company' attitude. The reason they ban you must align with the terms of service and must be backed up with data that is kept X amount of time.

Simply put, we've seen no shortage of individuals here on HN or other sites like Twitter that need to use social media to resolve whatever occurred because said company randomly banned an account under false pretenses.

This really matters when we are talking about giants like Google, or any other service in a near monopoly position.

	▲	handoflixue an hour ago \| parent [-]
		You mean actually enforce contracts? What sort of mad communist ideology is this?! (/sarcasm)

▲

direwolf20 2 hours ago | parent | prev [-]

I think companies shouldn't ban people for reasons that would lead to successful lawsuits against the company.

▲

pocksuppet 6 hours ago | parent | prev [-]

[dead]