Comment by tristanj
1 day ago
As mentioned in my comment, Kimi K3 identifies itself as Claude ~15% of the time.
Here's another report of K3 identifying itself as Claude https://x.com/Sauers_/status/2077842686459981901
And an analysis showing the self-identity distribution for K3 and other models https://x.com/RyanGreenblatt/status/2078663148509544589
Your main source is Ryan Greenblatt who is a regular recipient of community notes and has no corroboration for the 15% statistic other than his assertion. The other tweet (Sauers_) is also community noted as engagement farming with a false system prompt, so forgive me for being skeptical.
Including the three sources above, multiple others have reported that K3 self-identifies as Claude.
"I'm actually Claude - not Kimi". https://x.com/PimDeWitte/status/2077884701470040083
I regret to inform you that it is, in fact, real and from their own website - you don’t even need to try hard to reproduce it. https://x.com/PimDeWitte/status/2078105292965912690
lmao this is so funny, if you ask Kimi K3 for something with an empty system prompt it will consistently think of itself as Claude https://x.com/__alula/status/2078359305741275445
"I genuinely believe I'm Claude based on everything in my training" https://x.com/williawa/status/2077869021589033002
another "I'm actually Claude - not Kimi", including the system prompt https://x.com/jchudnov/status/2078661564803207406/photo/1
my first prompt to any Kimi model was K3 via Pi, some version of "hi kimi!!" and the response was telling me "I'm actually Claude."
this is not hard to repro, just use a system prompt that doesn't mention the model name.
that said, if they bootstrapped with opus 4.6 convo sft data they had sitting around... so what?
50 replies →
Moonshot AI should have made it identify as Mythos as a practical joke to make US go crazy trying to figure out how they got access to it.