PickVidsIntelligence and Stupidity: The Orthogonality Thesis
推荐理由
this video to me states the problem in a nutshell (that whole channel is gold)
强烈推荐pegasus · 原文
说明
这是2018年由Robert Miles AI Safety 发布的一部讲解，主题归在AI safety, AGI & impact。它讲的是AI alignment这一支里的具体问题，而不是把整个领域扫一遍。适合第一次接触、还没有先修课的人。内容上可以概括成：Robert Miles explains the orthogonality thesis: how an agent can be highly intelligent while pursuing goals that seem stupid or alien to humans. He separates intelligence from goals and touches on the stamp-collector example.这些读者给出的理由，核心是：HN people use it as the standard short explanation for why AI can understand human ethics without sharing them, and often recommend the whole channel.讲法不绑某一条新闻，过几年仍然可以当材料看。从2022年到2026年，有6位不同的读者在6个不同月份把它推荐出来，其中明确叫别人去看的有3次。适合用一集把一个概念补上的人。抓住它用的那个图像或类比，比背公式重要。如果已经会了基本定义，就把注意力放在它怎么把AI alignment变成能跟着复述的例子。
视频信息
- 频道
- Robert Miles AI Safety
- 时长
- 13 分 3 秒
- 发布年份
- 2018
同主题更多
- What Happened to Horses Is Happening to Us
- Why Would AI Want to do Bad Things? Instrumental Convergence
- Veritasium: What Everyone Gets Wrong About AI and Learning – Derek Muller Explains
- We're building a dystopia just to make people click on ads | Zeynep Tufekci
- Intro to AI Safety, Remastered
- Sparks of AGI: early experiments with GPT-4