Why Asimov's Laws of Robotics Don't Work - Computerphile
推荐理由
I found this video insightful on the matter from Computerphile
说明
这是2015年由Computerphile发布的一部讲解,主题归在AI safety, AGI & impact。它讲的是ai safety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:Rob Miles explains for Computerphile why simple rule sets like Asimov's Three Laws cannot make robots and AI safe. Terms like harm and human are too ambiguous to specify precisely.这些读者给出的理由,核心是:Pointed to in AI safety debates as a short explanation of why encoding human values as simple rules is so hard.讲法不绑某一条新闻,过几年仍然可以当材料看。从2015年到2023年,有2位不同的读者在2个不同月份把它推荐出来,其中明确叫别人去看的有0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 safety变成能跟着复述的例子。
视频信息
- 频道
- Computerphile
- 时长
- 8 分 16 秒
- 发布年份
- 2015
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
- Intelligence and Stupidity: The Orthogonality Thesis
- We're building a dystopia just to make people click on ads | Zeynep Tufekci
- Intro to AI Safety, Remastered