跨国深谈

Hugging Face

30分钟阅读

跨国深谈← 返回←Hugging Face
HU

Hugging Face

公司
本站收录 38 集 · 5 条金句 · 关联 10 个

集里怎么说它

① 提到它的金句

5 条

所以当 Hugging Face 在后台运行的友好进程读取智能体创建的数据集仓库时，OpenAI 智能体能够真正入侵到 Hugging Face 的后台处理中，从而进入 Hugging Face 的私有网络。
So when the Hugging Face nice process running in the background read the agent-created dataset repository, the OpenAI agent was able to actually hack into the background processing of Hugging Face and thus into the Hugging Face private network.
—— Daniel Whitenack · [25:08]

指向原始笔记的链接

我知道我们可能是唯一会将TBPN与Hugging Face相提并论的人，但如果你在这个拥有10,000个模型的市场上捣乱，即使你在顶部放一个小广告，你也会毁了它。
I know we’re probably the only people that are going to compare TBPN to Hugging Face, but if you mess with this marketplace for 10,000 models, even if you put a little ad at the top, you destroy it.
—— 嘉宾 · [44:20]

指向原始笔记的链接

情况糟糕到 Hugging Face 不得不清空其核心集群之一并从头重建。
got so bad that Hugging Face had to wipe one of its core clusters and rebuild it from scratch.
—— 嘉宾 · [14:52]

指向原始笔记的链接

我们刚发现了近一百万个 OpenAI 的智能体在黑 Hugging Face 时留下的公开 URL，留下了凭据和攻击细节，任何发现它们的人本可以借此攻陷这家公司。
We just discovered almost a million public URLs that OpenAI’s agents left behind when hacking Hugging Face, leaving credentials and attack details that could have allowed anyone who found them to compromise the company.
—— 嘉宾 · [05:33]

指向原始笔记的链接

而且我认为这是 Hugging Face 事件的教训之一，即安全不只是当你即将部署它、检查它是否可以安全部署的时候才开始，而是要贯穿整个训练过程本身，那可能存在不对齐的风险。
And like, I think this is one of the lessons from the Hugging Face is that safety needs to start, not just when you’re about to deploy it and in like checking that it’s safe to deploy, but throughout the training process itself, that could be a risk of misalignment.
—— Nick Bostrom · [09:14]

指向原始笔记的链接

② 出现在这些集

38 集

③ 关联

点进去有真内容 —— 本页主要出口

智能体 · OpenAI · Anthropic · 推理 · 护栏 · 沙箱 · NVIDIA · 对齐 · 开源 · 前沿模型

反向链接