Human-Compatible Artificial Intelligence
people.eecs.berkeley.edu · 9,457 words · saved by 1 readers
N/A
Human-Compatible Artificial Intelligence Stuart Russell Computer Science Division, University of California, Berkeley 1 1 Human-Compatible Artificial Intelligence 1.1 Introduction Artificial intelligence (AI) has as its aim the creation of intelligent machines. An entity is considered to be intelligent, roughly speaking, if it chooses actions that are expected to achieve its objectives, given what it has perceived.1 Applying this definition to machines, one can deduce that AI aims to create machines that choose actions…
related reading
- Using Artificial Intelligence to Augment Human Intelligencedistill.pub
- Why Tool AIs Want to Be Agent AIs · Gwern.netgwern.net
- [1911.01547] On the Measure of Intelligencearxiv.org
- The Artificial Intelligence Revolution: Part 2 - Wait But Whywaitbutwhy.com
- TechnicalAgenda.pdfintelligence.org
- The Artificiality of Alignmentjoinreboot.org
- The Artificial Selftheartificialself.ai
- Double Standards and AI Pessimism1a3orn.com
- Book: AI is Good for You | Eric Jangevjang.com
- Why AI is harder than we thinknews.ycombinator.com
- pdfopenreview.net
- The Problem — LessWronglesswrong.com