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

221–230 of 664 posts

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

#221

Post by plagiarist »

xtracto wrote: post #215

That's why we should strive to use and optimize local LLMs. Or better yet, we should setup something that allows people to share a part of their local GPU processing (like SETI@home) for a distributed LLM that cannot be censored. And somehow be compensated when it's used for inference

Yeah we really have to strive not to rely on these corporations because they absolutely will not do customer support or actually review account closures. This article is also mentioning I assume Google, has control over a lot more than just AI.

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

#222

Post by Leynos »

uxcolumbo wrote: post #164
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…

Have you tried any of the leading open weight models, like GLM etc. And how does chatGPT or Gemini compare? And kudos for refusing to use anything from the guy who's OK with his platform proliferating generated CSAM.

I tried GLM 4.7 in Opencode today. In terms of capability and autonomy, it's about on par with Sonnet 3.7. Not terrible for a 10th the price of an Anthropic plan, but not a replacement.

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

#223

Post by laserDinosaur »

throwup238 wrote: post #117
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…

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…

The Pro plan quota seems to be getting worse. I can get maybe 20-30 minutes work done before I hit my 4 hour quota. I found myself using it more just for the planning phase to get a little bit more time out of it, but yesterday I managed to ask it ONE question in plan mode (from a fresh quota window), and while it was thinking it ran out of quota. I'm assuming it probably pulled in a ton of references from my project automatically and blew out the token count. I find I get good answers from it when it does work, but it's getting very annoying to use.

(on the flip side, Codex seems like it's being SO efficient with the tokens it can be hard to understand its answers sometimes, it rarely includes files without you doing it manually, and often takes quite a few attempts to get the right answer because it's so strict what it's doing each iteration. But I never run out of quota!)

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

#224

Post by fluoridation »

gruez wrote: post #217
fluoridation wrote: post #85

Earlier quoted context omitted.

"I'm glad this happened with Anthropic instead of Google, which provides Gemini, email, etc. or I would have been locked out of the actually important non-AI services as well." Non-disabled organization = the first party provider Disabled organization = me I don't know why they're using these weird euphemisms or ironic monikers, but that's what they mean.

No, "another non-disabled organization" sounds like they used the account of someone else, or sockpuppet to craft the response. He was using "organization" to refer to himself earlier in the post, so it doesn't make sense to use that to refer to another model provider.

No, I don't think so. I think my interpretation is correct.

> a textbox where I tried to convince some Claude C in the multi-trillion-quadrillion dollar non-disabled organization

> So I wrote to their support, this time I wrote the text with the help of an LLM from another non-disabled organization.

> My guess is that this likely tripped the "Prompt Injection" heuristics that the non-disabled organization has.

A "non-disabled organization" is just a big company. Again, I don't understand the why, but I can't see any other way to interpret the term and end up with a coherent idea.

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

#225

Post by fluoridation »

mattnewton wrote: post #213
fluoridation wrote: post #85

Earlier quoted context omitted.

"I'm glad this happened with Anthropic instead of Google, which provides Gemini, email, etc. or I would have been locked out of the actually important non-AI services as well." Non-disabled organization = the first party provider Disabled organization = me I don't know why they're using these weird euphemisms or ironic monikers, but that's what they mean.

Because they bought a claude subscription on a personal account and the error message said that they belongs to a "disabled organization" (probably leaking some implementation details).

That's the part I understand. It's the other term that I don't understand.

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

#227

Post by lysace »

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…

Had a similar experience, like 20 years ago. This somehow made me remember his name - so I just checked out what he's been up to professionally. It seems quite boring, "basic" and expected. He certainly didn't reach what he was shooting for.

So there's that :).

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

#228

Post by olalonde »

renewiltord wrote: post #219
olalonde wrote: post #160

Earlier quoted context omitted.

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...

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?

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.

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

#229

Post by stareatgoats »

laserDinosaur wrote: post #223
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…

The Pro plan quota seems to be getting worse. I can get maybe 20-30 minutes work done before I hit my 4 hour quota. I found myself using it more just for the planning phase to get a little bit more time out of it, but yesterday I managed to ask it ONE question in plan mode (from a fresh quota window), and while it was thinking it ran out of quota. I'm assuming it probably pulled in a ton of references from my project…

Claude Code allegedly auto-includes the currently active file and often all visible tabs and sometimes neighboring files it thinks are 'related' - on every prompt.

The advice I got when scouring the internets was primarily to close everything except the file you’re editing and maybe one reference file (before asking Claude anything). For added effect add something like 'Only use the currently open file. Do not read or reference any other files' to the prompt.

I don't have any hard facts to back this up, but I'm sure going to try it myself tomorrow (when my weekly cap is lifted ...).

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

#230

Post by renewiltord »

olalonde wrote: post #228
renewiltord wrote: post #219

Earlier quoted context omitted.

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?

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.

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.
Post reply on HN