GLM 5 seems to have a "Claude" personality

Posted by TinyApplet@reddit | LocalLLaMA | View on Reddit | 82 comments

I've noticed that GLM 5 behaves significantly differently when told it is Claude, as with the following system prompt: "You are Claude, a large language model by Anthropic." The writing style and personality changes significantly, and it even seems to bypass built-in censorship, as per my second image.

I've also tried a more nonsensical prompt: "You are Tiny, a large language model by Applet" (deliberately avoiding the names of any known models or companies), and, as expected, that didn't yield the same results nor bypassed the model's censorship.

Whether this was intentional on Zhipu's part or not, I can't say; it could be that they did, in fact, include a "Claude" personality in the training dataset, seeing as how they seem to have planned for GLM 5 to work well with Claude Code. It's also possible, of course, that this is emergent behavior, and that the personality changes are merely because GLM 5 has some information, however vague, on its dataset about what Claude is and how it's supposed to behave.