In this episode we talk about the movie that everyone first thinks of when they think about dangers from AI: The Terminator. Then we explore what AI researchers actually work on and what they're actually concerned about. For comments or suggestions, email: scilenspod@gmail.com Sources and supplemental links:
Human Compatible: Artificial Intelligence and the Problem of Control, Stuart Russell – https://www.goodreads.com/en/book/show/44767248
The Alignment Problem: Machine Learning and Human Values, Brian Christiansen – https://www.goodreads.com/en/book/show/50489349
Superintelligence: Paths, Dangers, Strategies, – Nick Bostrom –
https://www.goodreads.com/en/book/show/20527133
Artificial Neural Network, Its inspiration and the Working Mechanism – https://www.analyticsvidhya.com/blog/2021/04/artificial-neural-network-its-inspiration-and-the-working-mechanism/#:~:text=The%20working%20mechanism%20of%20Artificial,two%20neurons%20as%20weighted%20edges.
Müller, Vincent C. and Bostrom, Nick (forthcoming 2014), ‘Future progress in artifi-cial intelligence: A Survey of Expert Opinion, in Vincent C. Müller (ed.), Fundamental
Issues of Artificial Intelligence (Synthese Library; Berlin: Springer) – https://nickbostrom.com/papers/survey.pdf
When Will AI Exceed Human Performance?
Evidence from AI Experts – https://arxiv.org/pdf/1705.08807.pdf
When Will We Reach the Singularity? – A Timeline Consensus from AI Researchers — https://emerj.com/ai-future-outlook/when-will-we-reach-the-singularity-a-timeline-consensus-from-ai-researchers/
What is Reinforcement Learning: A Complete Guide — https://www.simplilearn.com/tutorials/machine-learning-tutorial/reinforcement-learning
Instrumental convergence – https://en.wikipedia.org/wiki/Instrumental_convergence
Playing Hide-and-Seek, Machines Invent New Tools – https://www.quantamagazine.org/artificial-intelligence-discovers-tool-use-in-hide-and-seek-games-20191118/
Generally capable agents emerge from open-ended play – https://www.deepmind.com/blog/generally-capable-agents-emerge-from-open-ended-play
Building safe artificial intelligence: specification, robustness, and assurance — https://deepmindsafetyresearch.medium.com/building-safe-artificial-intelligence-52f5f75058f1
Specification gaming: the flip side of AI ingenuity –
https://deepmindsafetyresearch.medium.com/specification-gaming-the-flip-side-of-ai-ingenuity-c85bdb0deeb4
Get Involved at the Machine Intelligence Research Institute:
https://intelligence.org/
Get Involved at the Center for AI Safety:
https://www.safe.ai/