Hacker News new | ask | show | jobs
by nixosbestos 31 days ago
I am also really confused and annoyingly stuck on this. I understand that the model name might appear in prompts for distillation (I guess? "You are RipOffModelv2, learn from these responses from Claude")?

I guess the only explanation is that there's a side-telemetry channel that still sends some data to Anthropic, regardless of ANTHROPIC_BASE_URL overrides.

2 comments

There are a lot of companies reselling Claude to Chinese users. You use their base URL but it's still going to Anthropic.
To clarify why Anthropic wants to catch these parties: they save all session logs and sell them to other LLM firms (for distillation) and have been known to use stolen credit-cards to pay for the Anthropic accounts.

I'm quite all right with the first, not with the second of course.

> I understand that the model name might appear in prompts for distillation (I guess? "You are RipOffModelv2, learn from these responses from Claude")

This does not make sense. You wouldn't send such a prompt to the Claude model. And when you're sending the prompt (anywhere) you don't have the response yet. This is not how distillation works.

Right, sorry, I'm trying to catch up (in general) here, and am working through assumptions to get my bearings.

What you say makes sense, but further adds to my confusion as to why those model names would appear in input sent to Claude at all, then. EDIT: I guess it might be because someone might point Claude at a compatible API, with its model in the URL, which is of interest to them.

Yes I think that's the theory. I also noticed something today - when a stakeholder asked if Claude had an affiliate program, my instant response was "no" (because why would they need to deal with that) but a quick search surfaced that there are websites that actively present themselves as "Claude" official sellers/resellers, and simply act as a middleman proxy for the Anthropic/bedrock API.

It's unclear to me if they do this to arbitrage on API costs or to steal data, but it makes sense that Anthropic would be interested in detecting when traffic is being proxied to them.