跳到正文
原文
Mikita Balesni· @balesni · X·本站收录· 原文发表· 观点 →· 扫描记录里的位置 →

研究者称 OpenAI 员工不再公开解读 System Card,恐因寒蝉效应

AI 导读

X 用户 @balesni 发帖称,OpenAI 解雇风波之前,“我们的同事”常在 X 上发帖解读前沿模型的 System Card,向更广泛的公众解释其中的重要安全影响,如今似乎已不再这样做;他希望他们只是太忙、仍能坦率地向公众分享想法,但担心他们受到了寒蝉效应影响。帖中引用的 @tomekkorbak 帖子则评估了 GPT-6.2 Astra 的可监控性:他认为,尽管该模型看起来可能变好了,但在他们所关心的场景下,GPT-6.2 Astra 整体上比 GPT-6 Astra 更难监控,且这一点在 System Card 图表中容易被忽略。

正文 · 原文

Back before the OpenAI's firings, our colleagues would tweet about system cards of frontier models, explaining important safety implications to a wider audience. They seem to no longer do that. I hope they're just busy and still feel able to share their thoughts candidly with the public, but I worry they're chilled.

引用Tomek Korbak@tomekkorbak
How monitorable is GPT-6.2 Astra? While it might look like it got better, overall I think GPT-6.2 Astra harder to monitor than GPT-6 Astra in the contexts we care about. That’s easy to miss in the system card plots, so here's a short thread.
在 X 查看被引用的帖子

来源:Mikita Balesni · x.com