wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026I also talk about it a little on the 80,000 Hours podcast: www.youtube.com/watch?v=g0M...youtube.com80,000 Hours167 likes, 42 comments. "How we survive the intelligence explosion | Will MacAskill" 000
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026The full first-draft paper, with *much* more detail, is here: www.forethought.org/research/th...forethought.orgThe Saturation ViewWill MacAskill presents a new theory of population ethics, the Saturation View. It is motivated mainly by the observation that virtually all existing population axiologies prefer a *homogeneous* universe, full of a vast amount of whatever sort of thing that axiology rates as best. Intuitively, such a world feels impoverished relative to a universe filled with variety. The article discusses how the Saturation View addresses this problem, as well as a number of either classic problems in population ethics, such as the Repugnant Conclusion and difficulties with infinite ethics. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026If the Saturation View is right, then the best future isn't the one where we've found the optimal experience and copy-pasted it across the cosmos. The best future is the one where we've gone exploring, and we've fully lit up the landscape of possible experiences. 100
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026Separability: Like nearly all non-totalist views, Saturationism is non-separable — background populations can affect how we rank options. But the violations are tame: populations with sufficiently different populations simply add, and at small scales the view behaves just like totalism. 100
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026Infinite ethics: In any infinite universe, the value of a world is finite and well-defined — even if some locations have infinite wellbeing. Unlike other approaches, this does not depend on spatiotemporal structure or choice of ultrafilter. 100
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026The path to the Repugnant Conclusion is blocked. Fanaticism: Total achievable value is bounded above. That means no tiny-probability gamble can have arbitrarily high expected value. 100
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026Repugnant Conclusion: The classic path to the Repugnant Conclusion requires trading a utopian world for an enormous population of barely-positive lives. But, on the Saturation view, barely-positive lives can only illuminate a tiny corner of the landscape. 100
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026Monoculture: Because there are diminishing returns to increasing wellbeing of very similar types, there’s greater value in having a diversity of lives. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026Think of types of life as forming a landscape. Adding different types of life lights up different parts of the landscape. The value of the world is given by how fully illuminated the landscape is. Why does this help? In brief: 100
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026Endlessly creating replicas of the same identical life becomes progressively less valuable, tending to an upper bound. The total value of a world is given by the integral of realisation value over the space of types. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026The core idea is that the realisation value of a type of life (or experience) is determined by both the wellbeing of that life, and by how many very similar lives there are in the world. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026But a monoculture seems far from ideal. Endless galaxies containing nothing but the same blissful experience, repeated and repeated, seem impoverished; like a song with only one note. The Saturation view deals with all these problems at once, using broadly the same machinery for all of them. 100
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026Essentially all extant impartial accounts of population ethics suffer from the monoculture problem. It follows from Pareto and Anonymity alone — you don't need totalism. And perfectly-replicable digital minds mean this is a real issue that future generations will face. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026The Monoculture Problem: Given fixed resources, the best-possible future consists essentially only of qualitatively identical replicas of a small number of lives. 100
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026Infinitarian Paralysis: Given that the universe contains an infinite number of both positive and negative lives, no finite or infinite change to the world makes any difference to overall value. These are pretty bad! But there’s another less-discussed problem, too: 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026Fanaticism: For any guaranteed utopian outcome, there’s always some gamble with a vanishingly small probability of an even better outcome that has higher expected value. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026The Repugnant Conclusion: For any utopian outcome, there’s always another outcome containing an enormous number of barely-positive lives that is better. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026The motivation is that many views of population ethics, like the total view, suffer from some major problems. Some are already widely discussed: 100
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 24/04/2026In collaboration with Christian Tarsney, I’ve developed a new theory of population ethics, which I call the Saturation View. I think that, from a purely intellectual perspective, it’s probably the best idea I’ve ever had. It was certainly great fun to work on. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 29/03/2026newsletter.forethought.org/p/concrete-...newsletter.forethought.orgConcrete projects to prepare for superintelligenceThis article was created by Forethought. See the original on our website. 040
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 29/03/2026This isn’t a final list by any means, and I'd love to hear about other very concrete projects for handling the intelligence explosion. There’s so much to do! Link in reply. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 29/03/2026We also sketch out a CSET-style think tank focused on the governance of outer space. And we propose a coalition of concerned ML researchers who commit to coordinated action if AI companies cross clear red lines. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 29/03/2026Others are about building tools on top of AI. There’s so much low-hanging fruit in tools that improve collective epistemics (e.g. reliability tracking for public figures) and enable coordination (e.g. monitoring and verification tools). 220
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 29/03/2026Some are about shaping AI systems themselves: independently evaluating AI character traits, benchmarking AI for strategic and philosophical reasoning, auditing models for sabotage and backdoors, and brokering deals with AIs to disclose early forms of misalignment. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 29/03/2026There are lots of projects that could really help the transition to superintelligence go much better, which almost nobody is working on. With Fin Moorhouse, I’ve written up eight ideas that seem especially promising. 140
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026EA Forum and LessWrong discussion here: forum.effectivealtruism.org/posts/7adm5... www.lesswrong.com/posts/wSFmL...lesswrong.comAI character is a big deal — LessWrongDue to Claude’s Constitution and OpenAI’s model spec, the issue of AI character has started getting more attention, particularly concerning… 030
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026Full paper here: www.forethought.org/research/th...forethought.orgThe importance of AI characterForethought argues that AI character—e.g. how obedient, honest, or altruistic AI systems are—will shape power, conflict, and society far more than is recognized. Work to shape AI character could be hugely impactful. 120
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026Given how neglected the area is, too, I think work on AI character is among the most promising ways to help the intelligence explosion go well. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026AI character is most important in worlds where alignment gets solved. But it can affect the chance of AI takeover, too. Some styles of character training may make alignment easier; and some characters are more likely to make deals rather than foment rebellion, even if they have misaligned goals. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026And there will, predictably, be many future conflicts over AI character. It’s a safer world if we work through these tradeoffs ahead of time, before a crisis forces it. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026This is partly true, but the constraints are not binding. At the crucial moment, there might be just one leading AI company, facing none of the usual competitive pressures. Some decisions may have path-dependent outcomes, due to stickiness of training or user expectations. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026The main counterargument to the importance of AI character is that competitive dynamics and human instructions will determine the range of AI characters we get, so there’s little we can do today to affect it one way or the other. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026The cumulative effect of AIs’ character traits across hundreds of millions of interactions, and in rare but critical moments, will have an enormous impact on the course of society. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026A general, aiming to stage a coup, instructs an AI to build a military unit loyal only to him. Does it comply, or refuse? Two countries are on the brink of conflict, each advised by AI systems. Do those AIs search for de-escalatory options, or are they bellicose? 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026AI character — how honest, cooperative, and altruistic these systems are, and the hard rules they follow — will affect all of it. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026And, as capabilities improve, AI systems will become involved in almost all of the world's most important decisions: advising leaders, drafting legislation, running organisations, and researching new technologies. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026Churchill refused to negotiate with Hitler after the fall of France, despite some strongly pushing him to do so. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026History shows the importance of individual character. Stanislav Petrov chose to ignore a false nuclear alarm when protocol demanded he report it; the world avoided nuclear armageddon that day. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026Should they tell you what you want to hear, or push back when you’re off base? I think the nature of frontier AIs’ characters is among the most important features of the transition to a post-superintelligence world. In a new article with Tom Davidson, I explain why. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026Due to Claude’s Constitution and OpenAI’s model spec, more people are paying attention to the characters of the AI’s that companies are building, and the rules they follow. Should AIs be wholly obedient, or have their own ethical code? What should they refuse to help with? 150
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026The 10th anniversary edition of Doing Good Better is out now: linktr.ee/DoingGoodBe...linktr.eeDoing Good Better | LinktreeEffective Altruism and a Radical New Way to Make a Difference from William MacAskill 020
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026You can watch the full conversation here: www.youtube.com/watch?v=xjb....youtube.comWILL MACASKILL: we are unprepared for the intelligence explosionWill MacAskill is a co-founder of the effective altruist movement, who shares his perspective on doing good, moral philosophy, and the potential of AI to rev... 140
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026We talked about the origins of effective altruism, what EA has achieved in the last decade, preparing for the intelligence explosion, and whether I think I'm living well. 140
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 23/03/2026It was Peter Singer's arguments that first convinced me we have a moral obligation to do more good, so it was a pleasure to sit down with Peter & Kasia on their Lives Well Lived podcast. 130
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 25/02/2026linktr.ee/DoingGoodBe...linktr.eeDoing Good Better | LinktreeEffective Altruism and a Radical New Way to Make a Difference from William MacAskill 030
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 25/02/2026It’s been an honour to have been a part of it all. 110
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 25/02/2026- Corporate cage-free campaigns have led to billions of hens spared from caged confinement. - AI safety has gone from a fringe concern to a thriving field. And in the last year alone, money moved to effective charities was up by around 40%, now closing in on $2B per year. 130
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 25/02/2026It feels crazy that 10 years have passed, but a lot has happened since: - The number of people taking Giving What We Can’s 10% pledge has grown tenfold. - GiveWell has moved over $2 billion to highly effective global health and development charities, saving over 300,000 lives. 140
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 25/02/2026The core of the book is the same - explaining some principles for how we can have a bigger positive impact in our lives, whether through our donations, our career choice, or what we buy. Link to buy the book in the comments! 120
wdmacaskill.bsky.social @wdmacaskill.bsky.social · 25/02/2026I’m excited to say that the revised 10-yr anniversary edition of Doing Good Better is out now! It’s got updated statistics and a new foreword, reflecting on the last ten years and responding to some key criticisms. 190
