logoalt Hacker News

sosodevyesterday at 4:46 PM1 replyview on HN

Realistically you can't prevent distillation. OpenAI / Anthropic are slowly moving towards hiding the steps in-between input and output (hidden thinking), but that only helps so much. Imagine you put a file into Claude and say "do X to this" and it returns it to you without showing any of its internal reasoning. That's harder to distill, but the simple mapping of input to output still creates very valuable training data. It is reflective of all the training the model did to learn how to do that transformation.


Replies

make3yesterday at 5:15 PM

You can also get it to think in the output tokens pretty easily, eg "Here's a math problem, I want your reasoning first, then the answer" which is what I assume they're doing.