Live data from Hacker News

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

github.com

521–530 of 568 posts

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

#521
post #264

Hey everyone, Thariq from the Claude Code team. We've been on this since the bug surfaced. Everyone affected is getting a full refund and an extra grant of usage credits equal to their monthly subscription as our apology. You can see my original post here: https://x.com/trq212/status/2048495545375990245 . We’re still working on sending emails to everyone affected. Our support flow wasn't set up to route a complex bug…

> Our support flow wasn't set up to route a complex bug like this to engineering.

What does that even mean? Does it mean, "our support flow is just an LLM that fobs off customers and puts their issues into the bin"? Or is there some genuine "routing" of simple bugs to engineering which accidentally drops "complex" bugs? Could you drescibe that process, it sounds fascinating?

Also, how is changing a customer's billing based on detecting a certain string in a certain place a "complex" bug? Grep the string, remove the if statement, done. I'd love a post-mortem about why this was a complex bug.

More questions than answers here Thariq.

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

#522
post #264

Hey everyone, Thariq from the Claude Code team. We've been on this since the bug surfaced. Everyone affected is getting a full refund and an extra grant of usage credits equal to their monthly subscription as our apology. You can see my original post here: https://x.com/trq212/status/2048495545375990245 . We’re still working on sending emails to everyone affected. Our support flow wasn't set up to route a complex bug…

I try to avoid jumping on the bandwagon when it's already covered but billing bugs being treated like other software issue and the major comms channel being X (which I can't get to load half the time) is ridiculous.

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

#523
post #520

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…

I don't know why anyone is still using this - much less defending them.. In the last MONTH, I've asked how you can defend implementing (or even choose implementing) AI when: the AI you have implemented throughout your company changes the results you've come to trust? https://www.theregister.com/2026/04/13/claude_outage_quality... or won't let you log in?: https://github.com/anthropics/claude-code/issues/44257 or make…

The problem in most of those cases is not specifically AI. Many of the issues you cited are related to Anthropic specifically and many could have been avoided with better testing.

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

#524
post #222

Earlier quoted context omitted.

Unsure how true that is. Google cloud is tiny compared to aws for a reason. It matters. People will switch if you piss them off.

Google's lack of customer service isn't new or limited to GCP. They also don't provide any human help if you're an advertiser with them unless you spend a crazy amount of money. Twenty years ago I used to spend upwards of $20-30k a month with them and I couldn't get a single reply to any inquiry I ever sent. If you spend $XXX million / year with them on GCP they will, however, assign a person to be your main point of…

Even if you spend a crazy amount of money with them for advertising they will try to gaslight you if they make a mistake.

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

#525
post #413

Earlier quoted context omitted.

I don't perceive an AI as impersonating a human if it uses first person pronouns. Emulating is not impersonating. One is behaving similarly, the other is asserting that the similarity implies equivalence. I have not personally encountered an AI who claimed to be human (as far as I could detect)

I agree with you, but I also envy you for having never encountered an AI scam bot (where someone would hack someone's WhatsApp or other account and use an Ai to get money from them, or even do the "hey sorry I missed your call" scam).

Maybe this is a regional thing, I don't think anyone who I have encountered in real life has mentioned anything like this happening to them.

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

#527

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

You're absolutely right!

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

#529
I realise anthropic needs to move fast and break things, I realise its the nature of the LLM business, but if you're going to do that with paying customers, surely the least you could do is redirect a tiny portion of those hundreds of billions to proper human support?

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

#530
post #520

Earlier quoted context omitted.

I don't know why anyone is still using this - much less defending them.. In the last MONTH, I've asked how you can defend implementing (or even choose implementing) AI when: the AI you have implemented throughout your company changes the results you've come to trust? https://www.theregister.com/2026/04/13/claude_outage_quality... or won't let you log in?: https://github.com/anthropics/claude-code/issues/44257 or make…

The problem in most of those cases is not specifically AI. Many of the issues you cited are related to Anthropic specifically and many could have been avoided with better testing.

Yes, I am assuming the AI/LLM of choice you've implemented in your software engineering org is Claude because as far as I can tell there aren't really alternatives that come close to its quality in software.
Post reply on HN