X · @teortaxesTex
· X / Twitter
Not enough people talking about distillation consider the costs of heavy reliance on distillation in the case of comparable model strength. Thinking t…
Not enough people talking about distillation consider the costs of heavy reliance on distillation in the case of comparable model strength. Thinking that Chinese labs can cheaply syphon off the fruit of Anthropic's data labeling + RL and suffer no downside is a bit naive