Remix clone Hacker News

new | show | ask | jobs Github

▲

teyopi 3 hours ago

'just copy the US's homework'

elaborate please.

▲

axpy906 3 hours ago | parent [-]

Distilled off of OpenAI and Anthropic models

▲

russli1993 2 hours ago | parent [-]

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?

	▲	adenta an hour ago \| parent [-]
		I have no idea how you block distillation. Every time you do inference, thats basically distilation.