跳到正文
Lisan al Gaib· @scaling01 · X·· 23 小时前AI 评分22
AI 导读

我认为他们选择的案例无法证明保护原始推理轨迹是值得的。 数据量看起来不多,且在低推理预算下表现更差。 似乎强化学习环境(RL environments)和算力的影响更大。 (也许是我读错了,不确定)

正文 · 原文

I don't think they could've chosen worse plots to show that protecting raw reasoning traces is worth it

it sure doesn't look like a lot and is worse at low inference budgets

it seems like RL environments and compute have a much greater impact

(maybe I'm misreading this idk)

引用OpenAI@OpenAI
Distillation can reproduce powerful AI capabilities without the safeguards built around them. We’re sharing new research on our work to combat distillation of our models, how these capabilities transfer, and how we detect and disrupt coordinated attempts. These findings are helping us sharpen our defenses and support safeguards across the industry. https://openai.com/index/combatting-adversarial-distillation/
在 X 查看被引用的帖子

来源:Lisan al Gaib · x.com