Kimi's response to "hello. what are you" is "I'm Claude "

kristianp 2 days ago | parent | next [-]

What's the context of that? It's an opencode session share site, so is that based on opencode's system prompt?

▲

alentodorov 2 days ago | parent [-]

first question asked, didnt want to trigger it to do that. i ran it it root homedir

▲

kristianp 2 days ago | parent [-]

From https://github.com/bgauryy/open-docs/blob/main/docs/opencode...

> 1. Provider Header Purpose: Some providers benefit from identity "spoofing" to improve behavior.

> "You are Claude, a large language model trained by Anthropic. Knowledge cutoff: 2024-04 Current date: 2025-01-15"

	▲	alentodorov a day ago \| parent [-]
		so that’s whete it comes from…

▲

polski-g 2 days ago | parent | prev [-]

Both Kimi and Minimax are distilled Anthropic models. They said as much in January when the Chinese companies spun up 24,000 "fraudulent" accounts to perform their training. What makes Moonshot's accounts fraudulent and not mine? Nobody knows.