NI

Nick Bostrom

Big Technology Podcast 联合主持
本站收录 1 集 · 5 条金句 · 关联 10

① 他说过的话

5 条

开源模型将很快,如果不是已经的话,变得能够为某些人可能追求的破坏性用途提供有意义的帮助。
The open source models will very soon, if not already, become capable of lending meaningful assistance to destructive uses that some people might pursue.
—— Nick Bostrom · [09:07]

指向原始笔记的链接

最有价值的时机是在尽可能晚的时刻,因为那时你将拥有你试图对齐的实际系统可以与之合作。
The most valuable time for that to happen is at the latest possible moment because then you would have the actual system that you’re trying to align to work with.
—— Nick Bostrom · [30:11]

指向原始笔记的链接

我想大约每 25 分钟,世界各地就会发生大约相当于 9-11 规模的死亡。
I think every 25 minutes or so there is like a kind of 9-11 worth of deaths happening around the world.
—— Nick Bostrom · [35:01]

指向原始笔记的链接

我认为目前一些 AI 模型具有某种形式的主观体验是合理的。
I think it’s plausible that some AI models have some forms of subjective experience by now.
—— Nick Bostrom · [47:13]

指向原始笔记的链接

结果表明,当你这样做时,它们更有可能报告说它们有意识并有主观体验。
And it turns out when you do that, they become more likely to report that they are conscious and have subjective experience.
—— Nick Bostrom · [48:32]

指向原始笔记的链接

② 出现在这些集

1 集

③ 他谈到的

点进去有真内容 —— 本页主要出口

Alex · OpenAI · Anthropic · Hugging Face · NVIDIA · 智能体 · 对齐 · AI 安全 · 护栏 · 开源模型

④ 也在聊「AI 安全」的人