logoalt Hacker News

Combatting Adversarial Distillation

10 points • by pretext • today at 8:11 PM • 5 comments • view on HN

Comments

bob1029 • today at 9:02 PM

Distillation comes in many forms.

Hypothetically I can put a black box around their black box and log every single token in and out as part of ordinary business. This can be a profound amount of data. I can turn around and train my own model using this data. How would anyone detect this? Reasoning tokens are only so much of a moat.

WiSaGaN • today at 8:58 PM

It's just sad this company is named OpenAI, and then put out things like this. You trained all your models without giving back to authors, coders, directors, mathematicians . And you are putting them out of work. And finally you want to make sure only you have such models. You people won't go down well in human history.

➕ show 1 reply
9072997 • today at 8:56 PM

OpenAI would like to make sure you don't use something they made to train an LLM in a way they don't approve of. Also, this is a safety issue and has nothing to do with how their overseas competitors might be trying to build models cheaper by copying OpenAI's work.

snackbroken • today at 8:56 PM

That's a lot of post-hoc rationalization for justifying ruthlessly defending their competitive edge.

_verandaguy • today at 8:54 PM

Yeah, god forbid someone scrape IP en masse to make a derivative product, especially just as the hyperscalers are trying to build a moat around their closed models.