Datasets:
SlumberDemon
/
ChatML-Collection

Dataset card Data Studio Files
xet
 Community
1
text
stringlengths
82
65.5k
<|im_start|>user "First, I should explain what I mean by space-like separated from you. Imagine a world that looks like a Bayesian network, and imagine that you are a node in that Bayesian network. If there is a path from you to another node following edges in the network, I will say that node is time-like separated fr...
<|im_start|>user "Followup to: The Many Faces of Status (This post co-authored by Morendil and Kaj Sotala - see note at end of post.) In brief: status is a measure of general purpose optimization power in complex social domains, mediated by "power conversions" or "status conversions". What is status? Kaj previously pro...
<|im_start|>user "(An idea I had while responding to this quotes thread) "Correlation does not imply causation" is bandied around inexpertly and inappropriately all over the internet. Lots of us hate this. But get this: the phrase, and the most obvious follow-up phrases like "what does imply causation?" are not high-co...
<|im_start|>user "Greg Burch said: "I think people should have a right to be stupid and, if they have that right, the market's going to respond by supplying as much stupidity as can be sold." Greg Burch was speaking about sport-utility vehicles, which he feels are very poorly designed. Note that Burch was not advocatin...
<|im_start|>user "Here’s an insight I had about how incentives work in practice, that I’ve not seen explained in an econ textbook/course. There are at least three ways in which incentives affect behaviour: 1) via consciously motivating agents, 2) via unconsciously reinforcing certain behaviour, and 3) via selection eff...
<|im_start|>user ""Newton was the greatest genius who ever lived, and the most fortunate; for we cannot find more than once a system of the world to establish." —Lagrange I have more fun discovering things for myself than reading about them in textbooks. This is right and proper, and only to be expected. But discoverin...
<|im_start|>user "Honest disagreement is often a good sign of progress. - Gandhi Now that most communication is remote rather than face-to-face, people are comfortable disagreeing more often. How, then, can we disagree well? If the goal is intellectual progress, those who disagree should aim not for name-calling but fo...
<|im_start|>user "[Epistemic status: Sharing current impressions in a quick, simplified way in case others have details to add or have a more illuminating account. Medium-confidence that this is one of the most important parts of the story.]Here's my current sense of how we ended up in this weird world where:I still in...
<|im_start|>user "Related to: Privileging the Hypothesis Remember the exercises in critical reading you did in school, where you had to look at a piece of writing and step back and ask whether the author was telling the whole truth? If you really want to be a critical reader, it turns out you have to step back one step...
<|im_start|>user "This website is devoted to the art of rationality, and as such, is a wonderful corrective to wrong facts and, more importantly, wrong procedures for finding out facts.There is, however, another type of cognitive phenomenon that I’ve come to consider particularly troublesome, because it militates again...
<|im_start|>user ""Why do humans reason" (PDF), a paper by Hugo Mercier and Dan Sperber, reviewing an impressive amount of research with a lot of overlap with themes previously explored on Less Wrong, suggests that our collective efforts in "refining the art of human rationality" may ultimately be more successful than ...
<|im_start|>user "LessWrong is looking to hire an additional programmer. Ideally, someone with 5+ years experience who is up for a CTO role, or seems like a strong candidate to grow into such a role.We're looking for someone excited about our longterm vision. Over the next several years, we want to build a platform for...
<|im_start|>user "After over a year of building the organisation and working and reworking the product, I’m glad to announce that RAISE will begin publishing lessons on a regular basis starting next Monday.These lessons will include:An Inverse Reinforcement Learning (IRL) track, sourced from a set of papers that we hav...
<|im_start|>user "(This article expands upon my response to a question posed by pjeby here) I've seen a few back-and-forths lately debating the instrumental use of epistemic irrationality -- to put the matter in very broad strokes, you'll have one commenter claiming that a particular trick for enhancing your effectiven...
<|im_start|>user "An excellent habit that I've noticed among professional players of the game Magic: The Gathering is asking the question "how do I lose?" - a sort of strategic looking into the dark. Imagine this situation: you have an army ready to destroy your opponent in two turns. Your opponent has no creatures und...
<|im_start|>user "I previously wrote about some practical game-theoretical (game-practical?) realizations I had while buying a house. Today I want to talk about how bureaucracy is a ritualistic, magical place.In our home-buying process, every step of the way, there were papers to be signed. Paperwork is how the magic o...
<|im_start|>user "In the nerd community, we have lots of warm, fuzzy associations around 'science'. And, of course, science is indeed awesome. But, seeing how awesome science is, shouldn't we try to have more of it in our lives? When was the last time we did an experiment to test a theory? Here, I will try to introduce...
<|im_start|>user "Epistemic Status: Confident about the problem, solution and exact mechanism is more of an untested hypothesis.There's a saying for communities: if you're not gaining members, you're losing members. Sometimes you hit just the right size and you'd prefer things stay exactly as they are. But in practice,...
<|im_start|>user "One morning, I got out of bed, turned on my computer, and my Netscape email client automatically downloaded that day’s news pane. On that particular day, the news was that two hijacked planes had been flown into the World Trade Center. These were my first three thoughts, in order: I guess I really am ...
<|im_start|>user "Related to: Politics is the mind-killer, Entangled Truths, Contagious Lies, The Importance of Saying "Oops", Leave a Line of Retreat, You Can Face Reality This is something I wrote, sort of in brain-dump mode, in the process of trying to organize my thoughts for a song I'm working on. I don't think it...
<|im_start|>user "When I was a kid I thought the news came from "investigative reporters" like Clark Kent were who were paid to research stories. Since then, I have gotten my startup on national television, placed a press release into the world news, discussed biological warfare as a podcast guest, written a blog which...
<|im_start|>user "Related to: Logical Rudeness, Semantic Stopsigns While working on my book, I found in passing that I'd developed a list of what I started out calling "stonewalls", but have since decided to refer to as "conversation halters". These tactics of argument are distinguished by their being attempts to cut o...
<|im_start|>user "Martial arts can be a good training to ensure your personal security, if you assume the worst about your tools and environment. If you expect to find yourself unarmed in a dark alley, or fighting hand to hand in a war, it makes sense. But most people do a lot better at ensuring their personal security...
<|im_start|>user "In the post 'Four layers of Intellectual Conversation', Eliezer says that both the writer of an idea, and the person writing a critique of that idea, need to expect to have to publicly defend what they say at least one time. Otherwise they can write something stupid and never lose status because they ...
<|im_start|>user "Almost all instances of the word "true" can be eliminated from the sentences in which they appear by applying Tarski's formula. For example, if you say, "I believe the sky is blue, and that's true!" then this can be rephrased as the statement, "I believe the sky is blue, and the sky is blue." For ever...
<|im_start|>user "I’ve just founded a nonprofit, the Longevity Research Institute — you can check it out here.The basic premise is: we know there are more than 50 compounds that have been reported to extend healthy lifespan in mammals, but most of these have never been tested independently, and in many cases the experi...
<|im_start|>user "Did you ever wonder, when you were a kid, whether your inane "summer camp" actually had some kind of elaborate hidden purpose—say, it was all a science experiment and the "camp counselors" were really researchers observing your behavior? Me neither. But we'd have been more paranoid if we'd read Interg...
<|im_start|>user "(Note: The Junto was a secret society formed by Benjamin Franklin for the purpose of intellectual discourse and business networking. The following is the debate rules they used to maintain an atmosphere of reason.) Our debates were to be under the direction of a president, and to be conducted in the s...
<|im_start|>user "Related to: Cynicism in Ev Psych and Econ In Finding the Source, a commenter says: I have begun wondering whether claiming to be victim of 'akrasia' might just be a way of admitting that your real preferences, as revealed in your actions, don't match the preferences you want to signal (believing what ...
<|im_start|>user "A question that used to puzzle me is “Why can people be so much better at doing a thing for fun, or to help their friends and family, than they are at doing the exact same thing as a job?” I’ve seen it in myself and I’ve seen it in others. People can be hugely more productive, creative, intelligent, a...
<|im_start|>user "You’ve listened to the LessWrong team talk about our new tagging feature for months. First a steady drip of we’re working on it, then announcements of various milestones like you can now filter Coronavirus in or out and anyone can create tags. Well, now, it's an open call for taggers.We’ve sufficientl...
<|im_start|>user "Originally posted at sandymaguire.me. I have to get you to drop modesty and say to yourself, "Yes, I would like to do first-class work." Our society frowns on people who set out to do really good work. You're not supposed to; luck is supposed to descend on you and you do great things by chance. Well, ...
<|im_start|>user "I’ve been interested in drawing ever since I was a little kid. I like drawing people. I practiced a lot by looking at a cool picture of a character I like, and copying it as closely as I can.The better I got at copying, the better my work became. I got some great results this way. I even advanced to t...
<|im_start|>user "I have had the following situation happen several times during my research career: I write code to analyze data; there is some expectation about what the results will be; after running the program, the results are not what was expected; I go back and carefully check the code to make sure there are no ...
<|im_start|>user "Related to: Why Our Kind Can't Cooperate Eliezer described a scene that's familiar to all of us: Imagine that you're at a conference, and the speaker gives a 30-minute talk. Afterward, people line up at the microphones for questions. The first questioner objects to the graph used in slide 14 using a l...
<|im_start|>user "Category theory is the mathematics of math—specifically, it's a mathematical theory of mathematical structure. It turns out that every kind of mathematics you're likely to encounter in a normal university education is just another kind of category—group theory falls under the category of groups, topol...
<|im_start|>user "Braudel is probably the most impressive historian I have read. His quantitative estimates of premodern populations and crop yields are exactly the sort of foundation you’d think any understanding of history would be based upon. Yet reading his magnum opus, it became steadily clearer as the books progr...
<|im_start|>user "Motte and bailey is a technique by which one protects an interesting but hard-to-defend view by making it similar to a less interesting but more defensible position. Whenever the more interesting position - the bailey - is attacked - one retreats to the more defensible one - the motte -, but when the ...
<|im_start|>user "Currently there are three active forks of Lesswrong; Itself, the alignment forum and the EA forum. Can adding a new fork that is more focused on good discourse on controversial/taboo topics be a good idea? I am an Iranian, and have a fair share of experience with bad epistemic conditions. Disengagemen...
<|im_start|>user "During the LessWrong 1.0 Wiki Import we (the LessWrong team) discovered a number of great articles that most of the LessWrong team hadn't read before. Since we expect many others to also not have have read these, we are creating a series of the best posts from the Wiki to help give those hidden gems s...
<|im_start|>user "I am writing a post on scenario-based planning, and thought it would be useful to get some example scenario symptoms on the topic of near-term AGI. So the scenario-based planning thought exercise goes like this: Imagine it is ten years from now and AGI has happened (for the thought experiment just ima...
<|im_start|>user "Unsurprisingly related to: Ugh fields. If I had to choose a single piece of evidence off of which to argue that the rationality assumption of neoclassical economics is totally, irretrievably incorrect, it's this article about financial incentives and medication compliance. In short, offering people sm...
<|im_start|>user "I spent the week prepping for finals. One is a year-long cumulative closed-book chemistry exam that I haven't had much time to practice for. I was worried about memorizing a few things:Periodic trends and exceptionsThe form and application of approximately 100 workhorse equations and various forms of ...
<|im_start|>user "Followup to: Newcomb's Problem and Regret of Rationality "Rationalists should win," I said, and I may have to stop saying it, for it seems to convey something other than what I meant by it. Where did the phrase come from originally? From considering such cases as Newcomb's Problem: The superbeing Omeg...
<|im_start|>user "Politics is the mind-killer. Debate is war, arguments are soldiers. There is the temptation to search for ways to interpret every possible experimental result to confirm your theory, like securing a citadel against every possible line of attack. This you cannot do. It is mathematically impossible. For...
<|im_start|>user "One or two research groups have published work on carbon dioxide and cognition. The state of the published literature is confusing.Here is one paper on the topic. The authors investigate a proprietary cognitive benchmark, and experimentally manipulate carbon dioxide levels (without affecting other mea...
<|im_start|>user "Related to: Shane Legg on Prospect Theory and Computational FinanceThis post is on prospect theory partly because it fits the theme of replacing simple utility functions with complicated reward functions, but mostly because somehow Less Wrong doesn't have any posts on prospect theory yet and that need...
<|im_start|>user ""What do you mean 'bureaucratically impossible'?" said Harry James Potter-Evans-Verres. "It just is," said Mad-Eye Moody. "Nothing 'just is'," Harry said, "Everything happens for a material reason. What precisely is preventing you from acquiring the permits?" "I suspect an unfriendly nation-state is e...
<|im_start|>user "Partial re-interpretation of: The Curse of IdentityAlso related to: Humans Are Not Automatically Strategic, The Affect Heuristic, The Planning Fallacy, The Availability Heuristic, The Conjunction Fallacy, Urges vs. Goals, Your Inner Google, signaling, etc... What are the best careers for making a lot ...
<|im_start|>user "Last month I investigated commonalities between recessions of the last 50 years or so. But of course this recession will be different, because (among other things) we will simultaneously have a labor shortage and a lot of people out of work. That’s really weird, and there’s almost no historical preced...
<|im_start|>user "My deconversion from Christianity had a large positive impact on my life. I suspect it had a small positive impact on the world, too. (For example, I no longer condemn gays or waste time and money on a relationship with an imaginary friend.) And my deconversion did not happen because I came to underst...
<|im_start|>user "One of the motivations for You have about five words was the post Politics is the Mindkiller. That post essentially makes four claims:Politics is the mindkiller. Therefore:If you're not making a point about politics, avoid needlessly political examples.If you are trying to make a point about general p...
<|im_start|>user "I thought this video was a really good question dissolving by Richard Feynman. But it's in 240p! Nobody likes watching 240p videos. So I transcribed it. (Edit: That was in jest. The real reasons are because I thought I could get more exposure this way, and because a lot of people appreciate transcript...
<|im_start|>user "I remember the moment when I became an atheist. I was reading Religion's Claim to Be Non-Disprovable, an uneasy feeling growing in my head, and then I reached the bottom of the article, stared at the screen for a couple of seconds, and got it. "There is no God," I whispered. (Then I braced myself to b...
<|im_start|>user "Last Friday, I finally packaged up the quarterly release of JCVI's automatic prokaryote functional annotation pipeline and distributed it to the other 3 sequencing centers for the Human Microbiome Project. It looks at genes found in newly-sequenced bacterial genomes and guesses what they do. As often ...
<|im_start|>user "The ProblemBasically ever since the first rationalists settled in Berkeley, people have been saying, “Why do you live in Berkeley, Berkeley sucks! You should all move to Location X instead, it’s so much better.” The problem has always been that no one agrees on what Location X is. Some common candidat...
<|im_start|>user "LW doesn't seem to have a discussion of the article Epiphany Addiction, by Chris at succeedsocially. First paragraph: "Epiphany Addiction" is an informal little term I came up with to describe a process that I've observed happen to people who try to work on their personal issues. How it works is that ...
<|im_start|>user "Honest rational agents should never agree to disagree. This idea is formalized in Aumann's agreement theorem and its various extensions (we can't foresee to disagree, uncommon priors require origin disputes, complexity bounds, &c.), but even without the sophisticated mathematics, a basic intuition sho...
<|im_start|>user "When you are faced with an unanswerable question—a question to which it seems impossible to even imagine an answer—there is a simple trick which can turn the question solvable. Compare: "Why do I have free will?" "Why do I think I have free will?" The nice thing about the second question is that it is...
<|im_start|>user "A few days ago romeostevensit wrote in response to me asking about downvotes on a post: I didn’t down­vote, but I do think that con­ver­sa­tions like this at­tract peo­ple who aren’t in­ter­ested in ar­gu­ing in good faith. I pre­fer that such dis­cus­sions oc­cur at one ab­strac­tion level up so that...
<|im_start|>user "So we (Richard Hollerith and me) tried out my anti-akrasia idea. Actually we've been doing it for more than a week now. Turns out it works just like I thought it would: when you know an actual person is checking your screen at random intervals, and they will IM you whenever you start procrastinating o...
<|im_start|>user "Related to: Half-assing it with everything you've got; Wasted motion; Say it Loud. Once upon a time (true story), I was on my way to a hotel in a new city. I knew the hotel was many miles down this long, branchless road. So I drove for a long while. After a while, I began to worry I had passed the hot...
<|im_start|>user "Summary: Rigorous scientific experiments are hard to apply in daily life but we still want to try out and evaluate things like self-improvement methods. In doing so we can look for things such as a) effect sizes that are so large that they don't seem likely to be attributable to bias, b) a deep unders...
<|im_start|>user "SUMMARY: Let's collect people who want to work on for-profit companies that have significant positive impacts on many people's lives. Google provides a huge service to the world - efficient search of a vast amount of data. I would really like to see more for-profit businesses like Google, especially i...
<|im_start|>user "Edit: contest closed now, will start assessing the entries. The contest I'm offering $1,000 for good questions to ask of AI Oracles. Good questions are those that are safe and useful: that allows us to get information out of the Oracle without increasing risk. To enter, put your suggestion in the comm...
<|im_start|>user ""Clever kids in Ravenclaw, evil kids in Slytherin, wannabe heroes in Gryffindor, and everyone who does the actual work in Hufflepuff.”- Harry Potter and the Methods of Rationality, Chapter 9“It is a common misconception that the best rationalists are Sorted into Ravenclaw, leaving none for other House...
<|im_start|>user "After the iterated prisoner's dilemma tournament organized by prase two years ago, there was discussion of running tournaments for several variants, including one in which two players submit programs, each of which are given the source code of the other player's program, and outputs either “cooperate”...
<|im_start|>user "And fear not lest Existence closing yourAccount, should lose, or know the type no more;The Eternal Saki from the Bowl has pour'dMillions of Bubbles like us, and will pour.When You and I behind the Veil are past,Oh, but the long long while the World shall last,Which of our Coming and Departure heedsAs ...
<|im_start|>user "Merely corroborative detail, intended to give artistic verisimilitude to an otherwise bald and unconvincing narrative . . .—Pooh-Bah, in Gilbert and Sullivan’s The MikadoThe conjunction fallacy is when humans assign a higher probability to a proposition of the form “A and B” than to one of the proposi...
<|im_start|>user "This is an exercise, and as such is a bit different from your ordinary question post...What? Come up with 50 ways of sending something to the moon. In less than 1 hour. I don’t care how stupid they are. My own list included “Slingshot”, “Massive trampoline” and “Bird with spacesuit”.What matters is th...
<|im_start|>user "An oblong slip of newspaper had appeared between O'Brien's fingers. For perhaps five seconds it was within the angle of Winston's vision. It was a photograph, and there was no question of its identity. It was the photograph. It was another copy of the photograph of Jones, Aaronson, and Rutherford at t...
<|im_start|>user "Optimism bias is well-known. Here are some examples. It's conventional to answer the question "How are you doing?" with "well", regardless of how you're actually doing. Why? People often believe that it's inherently good to be happy, rather than thinking that their happiness level should track the act...
<|im_start|>user "Eliezer Yudkowsky's original Sequences have been edited, reordered, and converted into an ebook! Rationality: From AI to Zombies is now available in PDF, EPUB, and MOBI versions on intelligence.org (link). You can choose your own price to pay for it (minimum $0.00), or buy it for $4.99 from Amazon (li...
<|im_start|>user "The Boeing Maneuvering Characteristics Augmentation System (MCAS) can be thought of, if reaching a bit, as a specialized AI: it performs a function normally reserved for a human pilot: pitching the nose down when it deems the angle of attack to be dangerously high. This is not, by itself, a problem. T...
<|im_start|>user "Would kind of like to excerpt the whole post, but that feels impolite, so I'll just quote the first four paragraphs and then suggest reading the whole thing:There’s this funny thing about Goodhart’s Law, where it’s easy to say “being affected by Goodhart’s Law is bad” and “it’s better to behave in way...
<|im_start|>user "This sequence of posts is a primer on game theory intended at an introductory level. Because it is introductory, Less Wrong veterans may find some parts boring, obvious, or simplistic - although hopefully nothing is so simplistic as to be outright wrong.Parts of this sequence draw heavily upon materia...
<|im_start|>user "God, say the religious fundamentalists, is the source of all morality; there can be no morality without a Judge who rewards and punishes. If we did not fear hell and yearn for heaven, then what would stop people from murdering each other left and right? Suppose Omega makes a credible threat that if yo...
<|im_start|>user "An oversimplified story of manufacturing progress during the Industrial Revolution is: “we automated manufacturing processes, and that decreased the cost of goods.” This is not wrong, but is not the full picture.Mechanization—and other progress in manufacturing, such as improved tools, materials, and ...
<|im_start|>user "There are many paradoxes with unbounded utility functions. For instance, consider whether it's rational to spend eternity in Hell: Suppose that you die, and God offers you a deal. You can spend 1 day in Hell, and he will give you 2 days in Heaven, and then you will spend the rest of eternity in Purgat...
<|im_start|>user "We’ve talked a lot about preparations and prevention, but statistically some of us, or people we care about, are going to actually get sick. What do we do once that happens?" The above is a chunk of text from a post created by a user on the website LessWrong. Could you elaborate on the specific measu...
<|im_start|>user "Parapsychologists are constantly protesting that they are playing by all the standard scientific rules, and yet their results are being ignored - that they are unfairly being held to higher standards than everyone else. I'm willing to believe that. It just means that the standard statistical methods o...
<|im_start|>user "Being on Earth when this happens is a big deal, no matter your objectives – you can't hoard pebbles if you're dead! People would feel the loss from anywhere in the cosmos. However, Pebblehoarders wouldn't mind if they weren't in harm's way. Appendix: Contrived ObjectivesA natural definitional objectio...
<|im_start|>user "It's that time of year again.If you are reading this post, and have not been sent here by some sort of conspiracy trying to throw off the survey results, then you are the target population for the Less Wrong Census/Survey. Please take it. Doesn't matter if you don't post much. Doesn't matter if you're...
<|im_start|>user "TL;DR: It can be helpful to reframe arguments about tone, trigger warnings, and political correctness as concerns about false cognates/false friends. You may be saying something that sounds innocuous to you, but translates to something much stronger/more vicious to your audience. Cultivating a debatin...
<|im_start|>user "Where the mind cuts against reality's grain, it generates wrong questions—questions that cannot possibly be answered on their own terms, but only dissolved by understanding the cognitive algorithm that generates the perception of a question. One good cue that you're dealing with a "wrong question" is ...
<|im_start|>user "Edit 11/28: Edited note at bottom to note that the random variables should have finite variance, and that this is essentially just L². Also some formatting changes. This is something that has been bugging me for a while. The correlation coefficient between two random variables can be interpreted as th...
<|im_start|>user "tl;dr version: Akrasia might be like an eating disorder! When I was a teenager, I ate ice. Lots of ice. Cups and cups and cups of ice, constantly, all day long, when it was freely available. This went on for years, during which time I ignored the fact that others found it peculiar. ("Oh," I would joke...
<|im_start|>user "I just finished reading a history of Enron’s downfall, The Smartest Guys in the Room, which hereby wins my award for “Least Appropriate Book Title.” An unsurprising feature of Enron’s slow rot and abrupt collapse was that the executive players never admitted to having made a large mistake. When catast...
<|im_start|>user "Open Philanthropy is planning a request for proposals (RFP) for AI alignment projects working with deep learning systems, and we’re looking for feedback on the RFP and on the research directions we’re looking for proposals within. We’d be really interested in feedback from people on the Alignment Foru...
<|im_start|>user "Casey Serin, a 24-year-old web programmer with no prior experience in real estate, owes banks 2.2 million dollars after lying on mortgage applications in order to simultaneously buy eight different houses in different states. He took cash out of the mortgage (applied for larger amounts than the price ...
<|im_start|>user "Friendship is Optimal has launched and is being published in chunks on FIMFiction. Friendship is Optimal is a story about an optimizer written to "satisfy human values through friendship and ponies." I would like to thank everyone on LessWrong who came out and helped edit it. Friendship is Optimal wou...
<|im_start|>user "When someone asks me why I did or said something I usually lie because the truthful answer is "I don't know". I literally don't know why I make >99% of my decisions. I think through none of these decisions rationally. It's usually some mixture of gut instinct, intuition, cultural norms, common sense a...
<|im_start|>user "LookatthisglorioustableCelebrations! The new editor is finally here! Starting from today, all desktop users will by-default use the new visual editor that we've been testing for a while. While the primary goal of this is to have a better foundation on which to build future editor features, here are a ...
<|im_start|>user "A green humvee arrived at Jieyang Chaoshan International Airport. Vi got in the back with Molly Miriam who handed her clipboard to Vi. "健重制造公司. A no-name Chinese factory that makes barbells and similar equipment. It's not even fully-automated," read Vi. "They are registered to use a low-intelligence A...
<|im_start|>user "At the Singularity Summit 2007, one of the speakers called for democratic, multinational development of artificial intelligence. So I stepped up to the microphone and asked:Suppose that a group of democratic republics form a consortium to develop AI, and there’s a lot of politicking during the process...
<|im_start|>user "Related to: Is That Your True Rejection? "If you’re interested in being on the right side of disputes, you will refute your opponents’ arguments. But if you’re interested in producing truth, you will fix your opponents’ arguments for them. To win, you must fight not only the creature you encounter; yo...
<|im_start|>user "David Chapman criticizes "pop Bayesianism" as just common-sense rationality dressed up as intimidating math[1]: Bayesianism boils down to “don’t be so sure of your beliefs; be less sure when you see contradictory evidence.” Now that is just common sense. Why does anyone need to be told this? And how d...
<|im_start|>user "This article is an attempt to summarize basic material, and thus probably won't have anything new for the hard core posting crowd. It'd be interesting to know whether you think there's anything essential I missed, though. You've probably seen the word 'Bayesian' used a lot on this site, but may be a b...
<|im_start|>user "There are many ways you might approach being less wrong.A popular one is to make fewer wrong statements; to say fewer wrong things.Naively it would seem this is a recipe for success, since you just say more things that are true and right and fewer things that are false and wrong. But if Goodhart has a...
<|im_start|>user "The more complex an explanation is, the more evidence you need just to find it in belief-space. (In Traditional Rationality this is often phrased misleadingly, as “The more complex a proposition is, the more evidence is required to argue for it.”) How can we measure the complexity of an explanation? H...