alt Hacker Newssince openAI and Anthropic are public about their anti-distillation mechanism, its either their anti-distillation doesn't work or kimi got here because their own training and RLs. Which one is it?
since openAI and Anthropic are public about their anti-distillation mechanism, its either their anti-distillation doesn't work or kimi got here because their own training and RLs. Which one is it?
I have no idea how you block distillation. Every time you do inference, thats basically distilation.