Live data from Hacker News

HERMES.md in commit messages causes requests to route to extra usage billing

github.com

111–120 of 568 posts

Re: HERMES.md in commit messages causes requests to route to extra usage billing

#111
Is github the correct channel to report a billing issue? I would assume github is a place where you report issues with the github project. When there's a billing problem, there are usually different lines of support.

For example, chatgpt when asked "How to report a billing issue with Anthropic subscription?" says:

Best way: Use Claude’s built-in support Log in to your Claude account at Anthropic / Claude.ai Click your initials or name in the lower-left corner Select “Get help” Use the support messenger to describe your billing issue (duplicate charge, failed renewal, refund request, missing credits, invoice issue, etc.)

Re: HERMES.md in commit messages causes requests to route to extra usage billing

#112
Searching for the strings of configuration files of other agents in a codebase's git history in order to "detect" unauthorised usage is such a stupid idea I know it 100% came from Claude, and I doubt any of the vibesloppers working at Anthropic bothered to turn their brain on enough for the 5 seconds of thinking it would take to grasp that fact.

Re: HERMES.md in commit messages causes requests to route to extra usage billing

#113
post #56

I recently had my automatic reload double charge me $100. I tried reaching out to Anthropic, but my only option (of course) was a chat agent. After going through a conversation with it, I was told someone would reach out to help with the matter. Never happened. I eventually reached out to my credit-card company and did a dispute, which they just ruled in my favor.

Once the dispute was resolved on the card side did anthropic claw back the $100? Was your account penalized in anyway?

Nothing so far, but I'm keeping an eye on it and debating just canceling entirely.

Re: HERMES.md in commit messages causes requests to route to extra usage billing

#114
post #51

Earlier quoted context omitted.

The official response feels AI generated. I suspect this is a preview of our future. "You're totally right! I'm sorry but you're going to have to piss off anyway. Would you like to spend a few more hours discussing it with our AI chatbot? It won't help. But if it makes you feel better, it will probably cost us an extra $0.12 in tokens." I'll bet the first human at Anthropic learns about this from HN.

And then you use the smallest, cheapest local model to keep their AI bot busy

How long until we have to solve a captcha per message to counter that?

Re: HERMES.md in commit messages causes requests to route to extra usage billing

#115
post #60

Earlier quoted context omitted.

This is exactly what small claims court is for. Small claims court is exempt from arbitration requirements (which are primarily aimed at avoiding class action suits). It doesn't require you to hire a lawyer, and probably won't get your account automatically nuked the way a credit-card chargeback would.

I don't think you even need to go that far. Just refute the charges with your credit card. Very high likelihood of a successful refund since they already acknowledged their error in writing.

doing charge back means Anthropic will ban you forever.

Re: HERMES.md in commit messages causes requests to route to extra usage billing

#116
post #51

Earlier quoted context omitted.

And then you use the smallest, cheapest local model to keep their AI bot busy

My insurance company and Synology would be my first targets. I'd gladly throw ~1k at each. Of course, I suspect the true business model to be to do nothing. You sell the "service" to people customers, but your enterprise customers pay you a subscription fee to not execute the order. ELaaS: Everybody Loses as a Service

You must have worked for Yelp

Re: HERMES.md in commit messages causes requests to route to extra usage billing

#117

Is sasha-id an Anthropic employee or official bot, or a prank? The structure of its response is strange, plus that gif. Cherny's response seems like the only legitimate one. My question is serious; apologies if the answer is obvious to you.

He is the original author who faced the bug. I believe he just copied the response he received from Antrophic

Thanks for clarifying. The interesting thing is, confusion is due to finding not too hard to believe Anthropic is audacious enough to respond publicly and include a gif.

Re: HERMES.md in commit messages causes requests to route to extra usage billing

#118
post #108

Earlier quoted context omitted.

The official response feels AI generated. I suspect this is a preview of our future. "You're totally right! I'm sorry but you're going to have to piss off anyway. Would you like to spend a few more hours discussing it with our AI chatbot? It won't help. But if it makes you feel better, it will probably cost us an extra $0.12 in tokens." I'll bet the first human at Anthropic learns about this from HN.

Anthropic doesn't even use their own harnesses for their support chatbots (they're using fin.ai) - that's how little support matters to them. Seems like either you get attention on HN, know someone working there, or are at a large enough company to have an enterprise contact - otherwise, no reply.

They saw how Google providing absolutely terrible customer service for a very long time has done nothing to hurt their bottom line and decided to copy.

Re: HERMES.md in commit messages causes requests to route to extra usage billing

#119

What a series of disasters that are happening at Anthropic nowadays. I am not even sure what is going on with Opus 4.7 I had to switch back to 4.6 and 4.6 was already a downgrade (anecdotal + the github thread with the harness changes). I am cancelling my subscription as it is impossible to justify these degradations and paying for a subpar service especially now that we have at least 3 more models that are as good a…

Too much vibe coding

Re: HERMES.md in commit messages causes requests to route to extra usage billing

#120

Earlier quoted context omitted.

If anyone with principles quit the moment a company did something bad, you'd be left with only people who are cynical and/or bad and/or sufficiently indentured to be unable to push back against management, and there would be no hope of the company ever improving. Sure, everyone probably has their own personal line such as "will quit if my employer is declared complicit in genocide by the UN", but bad customer service…

> left with only people who are cynical and/or bad and/or sufficiently indentured to be unable to push back against management, and there would be no hope of the company ever improving. So basically all of big tech.

Not in the slightest. There is robust discourse and vocal objection to bad actions at companies such as Microsoft (I used to work there) and Alphabet (currently do). It may not always change the course, but it has absolutely played into decision-making, changed whether features launch or what they look like, etc.
Post reply on HN