Peter Railton's guest appearances

Peter Railton

Philosophy Bites

Future of Life Institute Podcast

Brave New World -- hosted by Vasant Dhar

The Valmy

David Chalmers

Peter Singer

Joshua Greene

Stuart Russell

David Eagleman

Isaiah Berlin

Ben Hunt

Andrew Yang

Robert Wright

Mike Johnson

Helena Rosenblatt

Caitlin Zaloom

Stephen Davies

Catherine Wilson

Yuval Noah Harari

OwlTail

Developments in AI are coming very quickly. But it's not easy to work out how to deal with the ethical questions that AI generates. Peter Railton discusses AI and Ethics with Nigel Warburton for this episode of the Philosophy Bites podcast

Developments in AI are coming very quickly. But it's not easy to work out how to deal with the ethical questions that AI generates. Peter Railton discusses AI and Ethics with Nigel Warburton for this episode of the Philosophy Bites podcast

Peter Railton on AI and Ethics

How do we come upon our morality? How much of our moral judgement is intuitive and how much is learned? Moral philosopher Peter Railton joins Vasant Dhar in episode 17 of Brave New World to talk about his thinking in this area -- and also how the fields of ethics and AI are colliding.  Useful resources: 1. Facts, Values, and Norms: Essays toward a Morality of Consequence -- Peter Railton.  2. Moral Learning: Conceptual foundations and normative relevance -- Peter Railton. 3. Ethical Learning, Natural and Artificial -- Peter Railton. 4. Ethics of Artificial Intelligence -- S Matthew Liao (Editor) 5. Can a Machine Have Human Values? -- Episode 13 of Brave New World (w Brian Christian). 6. Are We Becoming a New Species? -- Episode 12 of Brave New World (w Molly Crockett). 7. Samuel Moyn on Humane War -- Episode 16 of Brave New World. 8. Human-level performance in 3D multiplayer games with population-based reinforcement learning -- Max Jaderberg et al. 9. A multi-agent reinforcement learning model of common-pool resource appropriation -- Julien Perolat et al.

How do we come upon our morality? How much of our moral judgement is intuitive and how much is learned? Moral philosopher Peter Railton joins Vasant Dhar in episode 17 of Brave New World to talk about his thinking in this area -- and also how the fields of ethics and AI are colliding. Useful resources: 1. <a href="https://www.amazon.com/Facts-Values-Norms-Consequence-Philosophy-ebook-dp-B001GAQ4J4/dp/B001GAQ4J4/ref=mt_other?_encoding=UTF8&amp;me=&amp;qid=1626895182" rel="noopener nofollow" target="_blank">Facts, Values, and Norms: Essays toward a Morality of Consequence</a> -- Peter Railton.  2. <a href="https://www.sciencedirect.com/science/article/pii/S0010027716302050" rel="noopener nofollow" target="_blank">Moral Learning: Conceptual foundations and normative relevance</a> -- Peter Railton. 3. <a href="https://oxford.universitypressscholarship.com/view/10.1093/oso/9780190905033.001.0001/oso-9780190905033-chapter-2" rel="noopener nofollow" target="_blank">Ethical Learning, Natural and Artificial</a> -- Peter Railton. 4. <a href="https://www.amazon.com/Ethics-Artificial-Intelligence-Matthew-Liao-ebook/dp/B08D3VWXPS/ref=sr_1_1?dchild=1&amp;keywords=Ethics+of+Artificial+Intelligence&amp;qid=1626895342&amp;s=digital-text&amp;sr=1-1" rel="noopener nofollow" target="_blank">Ethics of Artificial Intelligence</a> -- S Matthew Liao (Editor) 5. <a href="https://bravenewpodcast.com/episodes/2021/05/27/episode-13-can-a-machine-have-human-values/" rel="noopener nofollow" target="_blank">Can a Machine Have Human Values?</a> -- Episode 13 of Brave New World (w Brian Christian). 6. <a href="https://bravenewpodcast.com/episodes/2021/05/13/episode-12-are-we-becoming-a-new-species/" rel="noopener nofollow" target="_blank">Are We Becoming a New Species?</a> -- Episode 12 of Brave New World (w Molly Crockett). 7. <a href="https://bravenewpodcast.com/episodes/2021/07/08/episode-16-samuel-moyn-on-humane-war/" rel="noopener nofollow" target="_blank">Samuel Moyn on Humane War</a> -- Episode 16 of Brave New World. 8. <a href="https://science.sciencemag.org/content/364/6443/859" rel="nofollow" target="_blank">Human-level performance in 3D multiplayer games with population-based reinforcement learning</a> -- Max Jaderberg et al. 9. <a href="https://arxiv.org/abs/1707.06600" rel="nofollow" target="_blank">A multi-agent reinforcement learning model of common-pool resource appropriation</a> -- Julien Perolat et al.

Ep 17: Peter Railton on Moral Intuitions

From a young age, humans are capable of developing moral competency and autonomy through experience. We begin life by constructing sophisticated moral representations of the world that allow for us to successfully navigate our way through complex social situations with sensitivity to morally relevant information and variables. This capacity for moral learning allows us to solve open-ended problems with other persons who may hold complex beliefs and preferences. As AI systems become increasingly autonomous and active in social situations involving human and non-human agents, AI moral competency via the capacity for moral learning will become more and more critical. On this episode of the AI Alignment Podcast, Peter Railton joins us to discuss the potential role of moral learning and moral epistemology in AI systems, as well as his views on metaethics.Topics discussed in this episode include:-Moral epistemology-The potential relevance of metaethics to AI alignment-The importance of moral learning in AI systems-Peter Railton's, Derek Parfit's, and Peter Singer's metaethical viewsYou can find the page for this podcast here: https://futureoflife.org/2020/08/18/peter-railton-on-moral-learning-and-metaethics-in-ai-systems/Timestamps: 0:00 Intro3:05 Does metaethics matter for AI alignment?22:49 Long-reflection considerations26:05 Moral learning in humans35:07 The need for moral learning in artificial intelligence53:57 Peter Railton's views on metaethics and his discussions with Derek Parfit1:38:50 The need for engagement between philosophers and the AI alignment community1:40:37 Where to find Peter's workThis podcast is possible because of the support of listeners like you. If you found this conversation to be meaningful or valuable, consider supporting it directly by donating at futureoflife.org/donate. Contributions like yours make these conversations possible.

From a young age, humans are capable of developing moral competency and autonomy through experience. We begin life by constructing sophisticated moral representations of the world that allow for us to successfully navigate our way through complex social situations with sensitivity to morally relevant information and variables. This capacity for moral learning allows us to solve open-ended problems with other persons who may hold complex beliefs and preferences. As AI systems become increasingly autonomous and active in social situations involving human and non-human agents, AI moral competency via the capacity for moral learning will become more and more critical. On this episode of the AI Alignment Podcast, Peter Railton joins us to discuss the potential role of moral learning and moral epistemology in AI systems, as well as his views on metaethics. Topics discussed in this episode include: -Moral epistemology -The potential relevance of metaethics to AI alignment -The importance of moral learning in AI systems -Peter Railton's, Derek Parfit's, and Peter Singer's metaethical views You can find the page for this podcast here: <a href="https://futureoflife.org/2020/08/18/peter-railton-on-moral-learning-and-metaethics-in-ai-systems/" rel="nofollow" target="_blank">https://futureoflife.org/2020/08/18/peter-railton-on-moral-learning-and-metaethics-in-ai-systems/</a> Timestamps:  0:00 Intro 3:05 Does metaethics matter for AI alignment? 22:49 Long-reflection considerations 26:05 Moral learning in humans 35:07 The need for moral learning in artificial intelligence 53:57 Peter Railton's views on metaethics and his discussions with Derek Parfit 1:38:50 The need for engagement between philosophers and the AI alignment community 1:40:37 Where to find Peter's work This podcast is possible because of the support of listeners like you. If you found this conversation to be meaningful or valuable, consider supporting it directly by donating at <a href="http://futureoflife.org/donate" rel="nofollow" target="_blank">futureoflife.org/donate</a>. Contributions like yours make these conversations possible.

Peter Railton on Moral Learning and Metaethics in AI Systems