Future of Life Institute Podcast

In this episode of the AI Alignment Podcast, Andrew Critch joins us to discuss a recent paper he co-authored with David Krueger titled AI Research Considerations for Human Existential Safety. We explore a wide range of issues, from how the mainstream computer science community views AI existential risk, to the need for more accurate terminology in the field of AI existential safety and the risks of what Andrew calls prepotent AI systems. Crucially, we also discuss what Andrew sees as being the most likely source of existential risk: the possibility of externalities from multiple AIs and AI stakeholders competing in a context where alignment and AI existential safety issues are not naturally covered by industry incentives.  Topics discussed in this episode include: - The mainstream computer science view of AI existential risk - Distinguishing AI safety from AI existential safety  - The need for more precise terminology in the field of AI existential safety and alignment - The concept of prepotent AI systems and the problem of delegation  - Which alignment problems get solved by commercial incentives and which don’t - The threat of diffusion of responsibility on AI existential safety considerations not covered by commercial incentives - Prepotent AI risk types that lead to unsurvivability for humanity You can find the page for this podcast here: https://futureoflife.org/2020/09/15/andrew-critch-on-ai-research-considerations-for-human-existential-safety/ Timestamps:  0:00 Intro 2:53 Why Andrew wrote ARCHES and what it’s about 6:46 The perspective of the mainstream CS community on AI existential risk 13:03 ARCHES in relation to AI existential risk literature 16:05 The distinction between safety and existential safety  24:27 Existential risk is most likely to obtain through externalities  29:03 The relationship between existential safety and safety for current systems  33:17 Research areas that may not be solved by natural commercial incentives 51:40 What’s an AI system and an AI technology?  53:42 Prepotent AI  59:41 Misaligned prepotent AI technology  01:05:13 Human frailty  01:07:37 The importance of delegation  01:14:11 Single-single, single-multi, multi-single, and multi-multi  01:15:26 Control, instruction, and comprehension  01:20:40 The multiplicity thesis  01:22:16 Risk types from prepotent AI that lead to human unsurvivability  01:34:06 Flow-through effects  01:41:00 Multi-stakeholder objectives  01:49:08 Final words from Andrew 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 futureoflife.org/donate. Contributions like yours make these conversations possible.

In the contemporary practice of many scientific disciplines, questions of values, norms, and political thought rarely explicitly enter the picture. In the realm of AI alignment, however, the normative and technical come together in an important and inseparable way. How do we decide on an appropriate procedure for aligning AI systems to human values when there is disagreement over what constitutes a moral alignment procedure? Choosing any procedure or set of values with which to align AI brings its own normative and metaethical beliefs that will require close examination and reflection if we hope to succeed at alignment. Iason Gabriel, Senior Research Scientist at DeepMind, joins us on this episode of the AI Alignment Podcast to explore the interdependence of the normative and technical in AI alignment and to discuss his recent paper Artificial Intelligence, Values and Alignment.     Topics discussed in this episode include: -How moral philosophy and political theory are deeply related to AI alignment -The problem of dealing with a plurality of preferences and philosophical views in AI alignment -How the is-ought problem and metaethics fits into alignment  -What we should be aligning AI systems to -The importance of democratic solutions to questions of AI alignment  -The long reflection You can find the page for this podcast here: https://futureoflife.org/2020/09/03/iason-gabriel-on-foundational-philosophical-questions-in-ai-alignment/ Timestamps:  0:00 Intro 2:10 Why Iason wrote Artificial Intelligence, Values and Alignment 3:12 What AI alignment is 6:07 The technical and normative aspects of AI alignment 9:11 The normative being dependent on the technical 14:30 Coming up with an appropriate alignment procedure given the is-ought problem 31:15 What systems are subject to an alignment procedure? 39:55 What is it that we're trying to align AI systems to? 01:02:30 Single agent and multi agent alignment scenarios 01:27:00 What is the procedure for choosing which evaluative model(s) will be used to judge different alignment proposals 01:30:28 The long reflection 01:53:55 Where to follow and contact Iason 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 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: https://futureoflife.org/2020/08/18/peter-railton-on-moral-learning-and-metaethics-in-ai-systems/ 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 futureoflife.org/donate. Contributions like yours make these conversations possible.

It's well-established in the AI alignment literature what happens when an AI system learns or is given an objective that doesn't fully capture what we want.  Human preferences and values are inevitably left out and the AI, likely being a powerful optimizer, will take advantage of the dimensions of freedom afforded by the misspecified objective and set them to extreme values. This may allow for better optimization on the goals in the objective function, but can have catastrophic consequences for human preferences and values the system fails to consider. Is it possible for misalignment to also occur between the model being trained and the objective function used for training? The answer looks like yes. Evan Hubinger from the Machine Intelligence Research Institute joins us on this episode of the AI Alignment Podcast to discuss how to ensure alignment between a model being trained and the objective function used to train it, as well as to evaluate three proposals for building safe advanced AI.  Topics discussed in this episode include: -Inner and outer alignment -How and why inner alignment can fail -Training competitiveness and performance competitiveness -Evaluating imitative amplification, AI safety via debate, and microscope AI You can find the page for this podcast here: https://futureoflife.org/2020/07/01/evan-hubinger-on-inner-alignment-outer-alignment-and-proposals-for-building-safe-advanced-ai/ Timestamps:  0:00 Intro  2:07 How Evan got into AI alignment research 4:42 What is AI alignment? 7:30 How Evan approaches AI alignment 13:05 What are inner alignment and outer alignment? 24:23 Gradient descent 36:30 Testing for inner alignment 38:38 Wrapping up on outer alignment 44:24 Why is inner alignment a priority? 45:30 How inner alignment fails 01:11:12 Training competitiveness and performance competitiveness 01:16:17 Evaluating proposals for building safe and advanced AI via inner and outer alignment, as well as training and performance competitiveness 01:17:30 Imitative amplification 01:23:00 AI safety via debate 01:26:32 Microscope AI 01:30:19 AGI timelines and humanity's prospects for succeeding in AI alignment 01:34:45 Where to follow Evan and find more of his 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 futureoflife.org/donate. Contributions like yours make these conversations possible.

Sam Barker, a Berlin-based music producer, and David Pearce, philosopher and author of The Hedonistic Imperative, join us on a special episode of the FLI Podcast to spread some existential hope. Sam is the author of euphoric sound landscapes inspired by the writings of David Pearce, largely exemplified in his latest album — aptly named "Utility." Sam's artistic excellence, motivated by blissful visions of the future, and David's philosophical and technological writings on the potential for the biological domestication of heaven are a perfect match made for the fusion of artistic, moral, and intellectual excellence. This podcast explores what significance Sam found in David's work, how it informed his music production, and Sam and David's optimistic visions of the future; it also features a guest mix by Sam and plenty of musical content. Topics discussed in this episode include: -The relationship between Sam's music and David's writing -Existential hope -Ideas from the Hedonistic Imperative -Sam's albums -The future of art and music You can find the page for this podcast here: https://futureoflife.org/2020/06/24/sam-barker-and-david-pearce-on-art-paradise-engineering-and-existential-hope-featuring-a-guest-mix/ You can find the mix with no interview portion of the podcast here: https://soundcloud.com/futureoflife/barker-hedonic-recalibration-mix Where to follow Sam Barker : Soundcloud: https://soundcloud.com/voltek Twitter: https://twitter.com/samvoltek Instagram: https://www.instagram.com/samvoltek/ Website: https://www.voltek-labs.net/ Bandcamp: https://sambarker.bandcamp.com/ Where to follow Sam's label, Ostgut Ton:  Soundcloud: https://soundcloud.com/ostgutton-official Facebook: https://www.facebook.com/Ostgut.Ton.OFFICIAL/ Twitter: https://twitter.com/ostgutton Instagram: https://www.instagram.com/ostgut_ton/ Bandcamp: https://ostgut.bandcamp.com/ Timestamps:  0:00 Intro 5:40 The inspiration around Sam's music 17:38 Barker - Maximum Utility 20:03 David and Sam on their work 23:45 Do any of the tracks evoke specific visions or hopes? 24:40 Barker - Die-Hards Of The Darwinian Order 28:15 Barker - Paradise Engineering 31:20 Barker - Hedonic Treadmill 33:05 The future and evolution of art 54:03 David on how good the future can be 58:36 Guest mix by Barker Tracklist: Delta Rain Dance – 1 John Beltran – A Different Dream Rrose – Horizon Alexandroid – lvpt3 Datassette – Drizzle Fort Conrad Sprenger – Opening JakoJako – Wavetable#1 Barker & David Goldberg – #3 Barker & Baumecker – Organik (Intro) Anthony Linell – Fractal Vision Ametsub – Skydroppin’ Ladyfish\Mewark – Comfortable JakoJako & Barker – [unreleased] 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 futureoflife.org/donate. Contributions like yours make these conversations possible.

Over the past several centuries, the human condition has been profoundly changed by the agricultural and industrial revolutions. With the creation and continued development of AI, we stand in the midst of an ongoing intelligence revolution that may prove far more transformative than the previous two. How did we get here, and what were the intellectual foundations necessary for the creation of AI? What benefits might we realize from aligned AI systems, and what are the risks and potential pitfalls along the way? In the longer term, will superintelligent AI systems pose an existential risk to humanity? Steven Pinker, best selling author and Professor of Psychology at Harvard, and Stuart Russell, UC Berkeley Professor of Computer Science, join us on this episode of the AI Alignment Podcast to discuss these questions and more.  Topics discussed in this episode include: -The historical and intellectual foundations of AI  -How AI systems achieve or do not achieve intelligence in the same way as the human mind -The rise of AI and what it signifies  -The benefits and risks of AI in both the short and long term  -Whether superintelligent AI will pose an existential risk to humanity You can find the page for this podcast here: https://futureoflife.org/2020/06/15/steven-pinker-and-stuart-russell-on-the-foundations-benefits-and-possible-existential-risk-of-ai/ You can take a survey about the podcast here: https://www.surveymonkey.com/r/W8YLYD3 You can submit a nominee for the Future of Life Award here: https://futureoflife.org/future-of-life-award-unsung-hero-search/ Timestamps:  0:00 Intro  4:30 The historical and intellectual foundations of AI  11:11 Moving beyond dualism  13:16 Regarding the objectives of an agent as fixed  17:20 The distinction between artificial intelligence and deep learning  22:00 How AI systems achieve or do not achieve intelligence in the same way as the human mind 49:46 What changes to human society does the rise of AI signal?  54:57 What are the benefits and risks of AI?  01:09:38 Do superintelligent AI systems pose an existential threat to humanity?  01:51:30 Where to find and follow Steve and Stuart 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 futureoflife.org/donate. Contributions like yours make these conversations possible.

Human civilization increasingly has the potential both to improve the lives of everyone and to completely destroy everything. The proliferation of emerging technologies calls our attention to this never-before-seen power — and the need to cultivate the wisdom with which to steer it towards beneficial outcomes. If we're serious both as individuals and as a species about improving the world, it's crucial that we converge around the reality of our situation and what matters most. What are the most important problems in the world today and why? In this episode of the Future of Life Institute Podcast, Sam Harris joins us to discuss some of these global priorities, the ethics surrounding them, and what we can do to address them. Topics discussed in this episode include: -The problem of communication  -Global priorities  -Existential risk  -Animal suffering in both wild animals and factory farmed animals  -Global poverty  -Artificial general intelligence risk and AI alignment  -Ethics -Sam’s book, The Moral Landscape You can find the page for this podcast here: https://futureoflife.org/2020/06/01/on-global-priorities-existential-risk-and-what-matters-most-with-sam-harris/ You can take a survey about the podcast here: www.surveymonkey.com/r/W8YLYD3 You can submit a nominee for the Future of Life Award here: https://futureoflife.org/future-of-life-award-unsung-hero-search/ Timestamps:  0:00 Intro 3:52 What are the most important problems in the world? 13:14 Global priorities: existential risk 20:15 Why global catastrophic risks are more likely than existential risks 25:09 Longtermist philosophy 31:36 Making existential and global catastrophic risk more emotionally salient 34:41 How analyzing the self makes longtermism more attractive 40:28 Global priorities & effective altruism: animal suffering and global poverty 56:03 Is machine suffering the next global moral catastrophe? 59:36 AI alignment and artificial general intelligence/superintelligence risk 01:11:25 Expanding our moral circle of compassion 01:13:00 The Moral Landscape, consciousness, and moral realism 01:30:14 Can bliss and wellbeing be mathematically defined? 01:31:03 Where to follow Sam and concluding thoughts Photo by Christopher Michel: https://www.flickr.com/photos/cmichel67/ 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 futureoflife.org/donate. Contributions like yours make these conversations possible.

Progress in synthetic biology and genetic engineering promise to bring advancements in human health sciences by curing disease, augmenting human capabilities, and even reversing aging. At the same time, such technology could be used to unleash novel diseases and biological agents which could pose global catastrophic and existential risks to life on Earth. George Church, a titan of synthetic biology, joins us on this episode of the FLI Podcast to discuss the benefits and risks of our growing knowledge of synthetic biology, its role in the future of life, and what we can do to make sure it remains beneficial. Will our wisdom keep pace with our expanding capabilities? Topics discussed in this episode include: -Existential risk -Computational substrates and AGI -Genetics and aging -Risks of synthetic biology -Obstacles to space colonization -Great Filters, consciousness, and eliminating suffering You can find the page for this podcast here: https://futureoflife.org/2020/05/15/on-the-future-of-computation-synthetic-biology-and-life-with-george-church/ You can take a survey about the podcast here: www.surveymonkey.com/r/W8YLYD3 You can submit a nominee for the Future of Life Award here: https://futureoflife.org/future-of-life-award-unsung-hero-search/ Timestamps:  0:00 Intro 3:58 What are the most important issues in the world? 12:20 Collective intelligence, AI, and the evolution of computational systems 33:06 Where we are with genetics 38:20 Timeline on progress for anti-aging technology 39:29 Synthetic biology risk 46:19 George's thoughts on COVID-19 49:44 Obstacles to overcome for space colonization 56:36 Possibilities for "Great Filters" 59:57 Genetic engineering for combating climate change 01:02:00 George's thoughts on the topic of "consciousness" 01:08:40 Using genetic engineering to phase out voluntary suffering 01:12:17 Where to find and follow George 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 futureoflife.org/donate. Contributions like yours make these conversations possible.

Essential to our assessment of risk and ability to plan for the future is our understanding of the probability of certain events occurring. If we can estimate the likelihood of risks, then we can evaluate their relative importance and apply our risk mitigation resources effectively. Predicting the future is, obviously, far from easy — and yet a community of "superforecasters" are attempting to do just that. Not only are they trying, but these superforecasters are also reliably outperforming subject matter experts at making predictions in their own fields. Robert de Neufville joins us on this episode of the FLI Podcast to explain what superforecasting is, how it's done, and the ways it can help us with crucial decision making.  Topics discussed in this episode include: -What superforecasting is and what the community looks like -How superforecasting is done and its potential use in decision making -The challenges of making predictions -Predictions about and lessons from COVID-19 You can find the page for this podcast here: https://futureoflife.org/2020/04/30/on-superforecasting-with-robert-de-neufville/ You can take a survey about the podcast here: https://www.surveymonkey.com/r/W8YLYD3 You can submit a nominee for the Future of Life Award here: https://futureoflife.org/future-of-life-award-unsung-hero-search/ Timestamps:  0:00 Intro 5:00 What is superforecasting? 7:22 Who are superforecasters and where did they come from? 10:43 How is superforecasting done and what are the relevant skills? 15:12 Developing a better understanding of probabilities 18:42 How is it that superforecasters are better at making predictions than subject matter experts? 21:43 COVID-19 and a failure to understand exponentials 24:27 What organizations and platforms exist in the space of superforecasting? 27:31 Whats up for consideration in an actual forecast 28:55 How are forecasts aggregated? Are they used? 31:37 How accurate are superforecasters? 34:34 How is superforecasting complementary to global catastrophic risk research and efforts? 39:15 The kinds of superforecasting platforms that exist 43:00 How accurate can we get around global catastrophic and existential risks? 46:20 How to deal with extremely rare risk and how to evaluate your prediction after the fact 53:33 Superforecasting, expected value calculations, and their use in decision making 56:46 Failure to prepare for COVID-19 and if superforecasting will be increasingly applied to critical decision making 01:01:55 What can we do to improve the use of superforecasting? 01:02:54 Forecasts about COVID-19 01:11:43 How do you convince others of your ability as a superforecaster? 01:13:55 Expanding the kinds of questions we do forecasting on 01:15:49 How to utilize subject experts and superforecasters 01:17:54 Where to find and follow Robert 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 futureoflife.org/donate. Contributions like yours make these conversations possible.

Just a year ago we released a two part episode titled An Overview of Technical AI Alignment with Rohin Shah. That conversation provided details on the views of central AI alignment research organizations and many of the ongoing research efforts for designing safe and aligned systems. Much has happened in the past twelve months, so we've invited Rohin — along with fellow researcher Buck Shlegeris — back for a follow-up conversation. Today's episode focuses especially on the state of current research efforts for beneficial AI, as well as Buck's and Rohin's thoughts about the varying approaches and the difficulties we still face. This podcast thus serves as a non-exhaustive overview of how the field of AI alignment has updated and how thinking is progressing.  Topics discussed in this episode include: -Rohin's and Buck's optimism and pessimism about different approaches to aligned AI -Traditional arguments for AI as an x-risk -Modeling agents as expected utility maximizers -Ambitious value learning and specification learning/narrow value learning -Agency and optimization -Robustness -Scaling to superhuman abilities -Universality -Impact regularization -Causal models, oracles, and decision theory -Discontinuous and continuous takeoff scenarios -Probability of AI-induced existential risk -Timelines for AGI -Information hazards You can find the page for this podcast here: https://futureoflife.org/2020/04/15/an-overview-of-technical-ai-alignment-in-2018-and-2019-with-buck-shlegeris-and-rohin-shah/ Timestamps:  0:00 Intro 3:48 Traditional arguments for AI as an existential risk 5:40 What is AI alignment? 7:30 Back to a basic analysis of AI as an existential risk 18:25 Can we model agents in ways other than as expected utility maximizers? 19:34 Is it skillful to try and model human preferences as a utility function? 27:09 Suggestions for alternatives to modeling humans with utility functions 40:30 Agency and optimization 45:55 Embedded decision theory 48:30 More on value learning 49:58 What is robustness and why does it matter? 01:13:00 Scaling to superhuman abilities 01:26:13 Universality 01:33:40 Impact regularization 01:40:34 Causal models, oracles, and decision theory 01:43:05 Forecasting as well as discontinuous and continuous takeoff scenarios 01:53:18 What is the probability of AI-induced existential risk? 02:00:53 Likelihood of continuous and discontinuous take off scenarios 02:08:08 What would you both do if you had more power and resources? 02:12:38 AI timelines 02:14:00 Information hazards 02:19:19 Where to follow Buck and Rohin and learn more 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 futureoflife.org/donate. Contributions like yours make these conversations possible.