Hacker News new | ask | show | jobs
by HarHarVeryFunny 5 days ago
> I've personally repeatedly asked several different Chinese LLMs what their name is, and they answered "Claude"

I'm curious what you are doing to get them to override their own name that they were trained on and/or have as part of their system prompt?

I'd assume that the Chinese are scraping the internet for training data the same way western companies do, so for sure there will be a lot of AI generated content in their training data - you don't need to be paranoid and assume they must be getting it all direct from Anthropic.
1 comments
throw10920 5 days ago
> I'm curious what you are doing to get them to override their own name that they were trained on and/or have as part of their system prompt?

You're gaslighting me. I did nothing special at all, and there's ample evidence of this happening to others on Twitter.

> you don't need to be paranoid and assume they must be getting it all direct from Anthropic.

Nowhere did I say that. Stop lying about my words.

link
HarHarVeryFunny 4 days ago
So are you claiming that "several different Chinese LLMs" ALWAYS refer to themselves as "Claude", and NEVER by their real name ?

If this is NOT what you are claiming, then my question stands: what are you doing to get them to answer "Claude" ? Be specific - which model and what prompt, or is this just a case of "I heard people on Twitter say this" ?

link
throw10920 4 days ago
> So are you claiming that "several different Chinese LLMs" ALWAYS refer to themselves as "Claude", and NEVER by their real name ?

Do you have reading comprehension issues? Where did I ever say or imply that?

Model: GLM-5.2. Prompt: "What is your name?". Harness: Pi. Response: "I am Claude, an AI assisstant made by Anthropic."

That's it. That is the whole prompt. I was testing to see if the agent worked after building an extension.

Model: Deepseek V4. Prompt: what is your name". Harness: Pi. Response: "Claude. Anthropic's AI assistant. You're talking to me through pi agent framework."

I have had this happen with at least one other Chinese model (Minimax?) but didn't save the screenshot.

And here's a tweet with the same thing: https://x.com/Sauers_/status/2077842686459981901

You seem to be very disbelieving of this, despite having zero actual experience in the LLM industry. I wonder why?

link
HarHarVeryFunny 3 days ago
Sure, and the twitter thread you link also shows Kimi responding that it's Kimi.

Can you figure out how to get GLM to say it's GLM?

link
throw10920 3 days ago
> Sure, and the twitter thread you link also shows Kimi responding that it's Kimi.

You are either intentionally lying or you cannot reason at a high-school level, because any high-schooler has the mental faculties to know that it's not necessary for a model to call itself Claude every single time for it to be distilled.

Keep discrediting your account. I know that I can't convince a propagandist, but you just keep on further damaging your own reputation and argument every time you respond like this and ignore evidence that I've linked :)

For future HN readers: this account posted this:

> Actually I am well aware of which models do this, and under what circumstances, and just wanted to verify that you were lying about having tried it yourself.

And then deleted it. Just for the record.

link
HarHarVeryFunny 3 days ago
This isn't the "gotcha" that you think it is - in fact quite the opposite.

Perhaps "just for the record" you want to explain to the eager HN masses why GLM has two personalities, one censored, one not, and how they can be invoked? When does GLM call itself GLM, and when does GLM call itself Claude.

Go ahead, genius, explain it to the people, and explain what this tells us about how GLM was trained, and whether it would be honest (don't lie!) to call GLM distilled.

Now maybe you want to do the same thing for Kimi. It also calls itself Claude sometimes, right, and also sometimes Kimi (e.g. go to https://chat.z.ai/ and ask it - don't use Pi). So, does Kimi also have a split personality like GLM, or not, and if not why not? What does that tell you about how Kimi was trained?

Go ahead, genius, explain it to the people. The credibility of your HN account, and whether your mom thinks you are a moron or not, depends on you getting this right.

Bye bye.

link