① 他说过的话

12 条

我觉得当我们先担心安全，再担心我们搁置了什么、延迟的代价是什么时，我们有点本末倒置了。
I think we’re putting the cart before the horse a little bit when we worry about safety before we worry about what we’re leaving on the table and what the costs of delay are.
—— Eddy Lazzarin · [02:13]

指向原始笔记的链接

而且在我看来，它们并不是一个即将挣脱枷锁、对我们撒野的超级智能的小小预兆。
And they’re not, in my view, they’re not little glimpses of a superintelligence that’s about to throw off its shackles, so to speak, and go wild on us.
—— Eddy Lazzarin · [05:11]

指向原始笔记的链接

对齐这东西有点像，它几乎就像，几乎有一点宗教式思维。
The alignment is kind of this, it’s almost like, it’s a little religious thinking almost.
—— Eddy Lazzarin · [06:38]

指向原始笔记的链接

重新设计一下神明，而不是让自己扎根于现实世界，然后说：好吧，我们需要设计更好的控制手段、更好的网络安全。
Redesign the deity a little bit instead of rooting yourself in the world and saying, well, we need to design better controls, better cybersecurity.
—— Eddy Lazzarin · [06:44]

指向原始笔记的链接

一个是，随着能力提升，我们可能会拥有比想象中更好的机制可解释性，而能力提升会带来更好的机制可解释性，这意味着我们不应该推迟能力提升。
One is that we will probably have better mech interpretability than we think as capabilities improve and that capability improvement will lead to better mech interpret, which means we should not delay capabilities improvements.
—— Eddy Lazzarin · [07:34]

指向原始笔记的链接

如果有人在那里宣称，我们最终能进入一个没有坏模型的世界，那他是在骗你。
If anybody is going out there and saying, we can end up in a world where there are no bad models, they are lying to you.
—— Eddy Lazzarin · [07:56]

指向原始笔记的链接

所有的控制系统在拥有足够智能的情况下都是稳健的。
All control systems are robust when you have enough intelligence on them.
—— Eddy Lazzarin · [08:22]

指向原始笔记的链接

我们不需要为这种我们正在学习使用的新型特殊数学制定新的特殊法律。
We don’t need new special laws for the new special math that we’re learning how to do.
—— Eddy Lazzarin · [09:58]

指向原始笔记的链接

人们很容易利用我们正在讨论的这种安全诉求，钻进安全这个兔子洞，最终在安全的幌子下，碰巧设计出某种完美地微妙控制一个整个至关重要的行业的东西，而且表面上看是去中心化的，但实际上不是。
It’s very easy to use the calls for safety like we’re discussing and to go down this rabbit hole of safety and end up in a place where you just by coincidence have designed something that is perfect to subtly control an entire critically important industry under the pretense of safety and with something that superficially looks decentralized but is not.
—— Eddy Lazzarin · [11:38]

指向原始笔记的链接

我认为市场仍然是一个很好的问责机制。人们不想购买那些甚至让他们感到难堪的东西，更不用说伤害人的东西了。
I think the market is still a great accountability mechanism. People don’t want to buy things that even embarrass them, let alone harm people.
—— Eddy Lazzarin · [14:07]

指向原始笔记的链接

我们很可能会围绕特定模型形成声誉，对吧？我们会说，你知道，也许这个模型更聪明一点，但那个模型是我信任的模型。
We’ll probably develop reputation around specific models, right? We’ll say, you know, maybe this model is a little smarter, but this model is a model that I trust.
—— Eddy Lazzarin · [18:21]

指向原始笔记的链接

它们看起来更政治化，而不是对技术特别感兴趣。
that seem more political than they are particularly interested in technology.
—— Eddy Lazzarin · [21:40]

指向原始笔记的链接

② 出现在这些集

1 集

• 《丰裕的概率：为什么「先担心安全」是本末倒置》 — 作为联合主持

③ 他谈到的

点进去有真内容 —— 本页主要出口

Theo Jaffe · AI 安全 · 对齐 · 超级智能 · 欺骗性对齐 · 机制可解释性 · 开源 · 有效利他主义 · 网络安全 · 去中心化

④ 也在聊「AI 安全」的人