I was banned from Claude for scaffolding a Claude.md file? • Hacker News Board

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

#321

Post by measurablefunc » Fri, Jan 23, 2026, 4:16 AM UTC

genewitch wrote: post #286

measurablefunc wrote: post #265

This is very cool. I looked at the Claude.md he was generating and it is basically all of Claude's failure modes in one file. I can think of a few reasons why Anthropic would not want this information out in the open or for someone to systematically collate all the data into one file.

i read the related parts of the linked file in the repo, and it took me a while to find your comment here again to reply to. Are you saying that the failure modes of claude with "coding" webapps or whatever OP was doing? i originally thought it might have meant like... jailbreak. But having read it, i assume you meant the former, as we both read the same thing and it seemed like a series of admonitions to the LLM, wr…

I'm not saying he did anything wrong. I'm saying I can see how Anthropic's automated systems might have flagged & banned the account b/c one of the heuristics they probably use is that there should be no short feedback loops where outputs of Claude are fed back into inputs. So basically Anthropic tracks all calls to their API & they have some heuristics for going through the history & then assigning scores based on what they think is "abusive" or "loopy".

Of course none of it is actually written anywhere so this guy just tripped the heuristics even though he wasn't doing anything "abusive" in any meaningful sense of the word.

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

#322

Post by bpanon » Fri, Jan 23, 2026, 4:24 AM UTC

do you know for sure this was the reason why?

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

#323

Post by jrflowers » Fri, Jan 23, 2026, 4:24 AM UTC

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 nine could be just 9% :D

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

#324

Post by heavyset_go » Fri, Jan 23, 2026, 4:26 AM UTC

areoform wrote: post #11

I recently found out that there's no such thing as Anthropic support. And that made me sad, but not for reasons that you expect. Out of all of the tech organizations, frontier labs are the one org you'd expect to be trying out cutting edge forms of support. Out of all of the different things these agents can do, surely most forms of "routine" customer support are the lowest hanging fruit? I think it's possible for An…

Offering any support is setting expectations of receiving support.

If you don't offer support, reality meets expectations, which sucks, but not enough for the money machine to care.

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

#325

Post by jumploops » Fri, Jan 23, 2026, 4:29 AM UTC

genewitch wrote: post #276

vunderba wrote: post #268

Earlier quoted context omitted.

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"

I believe Claude Code recently turned on max reasoning for all requests. Previously you’d have to set it manually or use the word “ultrathink”

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

#326

Post by nwatson » Fri, Jan 23, 2026, 4:33 AM UTC

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…

Self-hosted might be the way to go soon. I'm getting 2x Olares One boxes, each with an RTX 5090 GPU (NVIDIA 24GB VRAM), and a built-in ecosystem of AI apps, many of which should be useful, and Kubernetes + Docker will let me deploy whatever else I want. Presumably I will manage to host a good coding model and use Claude Code as the framework (or some other). There will be many good options out there soon.

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

#327

Post by ph4evers » Fri, Jan 23, 2026, 4:34 AM UTC

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…

The desktop app is pretty terrible and super flaky, throwing vague errors all the time. Claude code seems to be doing much better. I also use it for non-code related tasks.

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

#328

Post by georgemcbay » Fri, Jan 23, 2026, 4:45 AM UTC

b00ty4breakfast wrote: post #202

unyttigfjelltol wrote: post #191

Earlier quoted context omitted.

> 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?

Support has been automated for a while, LLMs just made it even less useful (and it wasn't very useful to begin with; for over a decade it's been a Byzantine labyrinth of dead-ends, punji-pits and endless hours spent listening to smooth jazz).

Yup, the main goal of customer support for almost every Internet-based company for over a decade now is to just be so frustrating that you give up before you can reach an actual human (since that is the point where there is a real cost to the company in giving you that support).

I'm not really sure LLMs have made it worse. They also haven't made it better, but it was already so awful that it just feels like a different flavor of awful.

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

#329

Post by failerk » Fri, Jan 23, 2026, 4:47 AM UTC

I also got banned from Claude over a year ago. The signup process threw an error and I couldn't try again because they took my phone number. The support system was a Google form petition to be unblocked. I am still mad about it to this day.

Edit: my only other comment on HN is also complaining about this 11 months ago

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

#330

Post by btbuildem » Fri, Jan 23, 2026, 4:48 AM UTC

Exactly as predicted: the means of production yet again taken away from the masses to be centralized in a few absurdly rich hands.

I ran out of tokens for not just the 5 hour sessions, but all models for the week. Had to wait a day -- so my methadone equivalent was to strap an endpoint-rewriting proxy to Claude Code and backend it with a local Qwen3 30B Coder. It was.. somewhat adequate. Just as fast, but not as capable as Opus 4.5 - I think it could handle carefully specced small greenfield projects, but it was getting tangled in my Claudefield mess.

All that to say -- be prepared, have a local fallback! The lords are coming for your ploughshares.