~www_lesswrong_com | Bookmarks (664)

Published on August 16, 2024 8:21 PM GMTI may be completely confused about this, but my model of technological breakthroughs in history was basically this: A few guys independently connect the dots leading to a new invention, for example the telephone, approximately at the same time. One of them runs to the patent office a little faster than the others, and he gets the...

Published on August 14, 2024 11:04 PM GMTI am just getting into the field and I would really appreciate some recommended reading. I am looking for articles/papers that showcase some of the best current proposals for solving the AGI control problem. Discuss

Published on August 15, 2024 5:03 PM GMTIs there anything you avoid that exposure still hasn’t fixed?…Why is that? In my experience, people who avoid X are usually not afraid of the average X… For example, I spoke to someone who is afraid of starting conversations with women he’s attracted to. But as far as I can tell, he has no fear of how this will...

Published on August 15, 2024 12:50 PM GMTAbstractLanguage models rapidly become more capable, and both AI labs and policy makers[1][2][3] are in need of benchmarks that measure their proficiency in biology, and conducting biological research, but there are only a handful of benchmarks evaluating these capabilities[4][5], and all of them have their limitations. This paper introduces the Biological Lab Protocol benchmark (BioLP-bench) that evaluates...

Published on August 15, 2024 11:26 AM GMTEpistemic status: This post touches on bodywork, NLP, Salsa and Yoga. I went through a 4-year training in Danis Bois style of bodywork, have roughly 70 seminar days worth of NLP training, and started dancing Salsa back in 2008 and have danced it a lot since then. I don't have special expertise in Yoga, but apply general...

Published on August 15, 2024 4:22 AM GMTWe may be making important conceptual or methodological errors in prioritization between moral patients. In this sequence, I illustrate and address several:Types of subjective welfare: I review types of subjective welfare, interpersonal comparisons with them and common grounds between them.Solution to the two envelopes problem for moral weights: The welfare concepts we value directly are human-based, so...

Published on August 14, 2024 11:24 PM GMTtl;dr: For Lisa, GPT-2 does not do IOI. GPT-2 fails to perform the IOI task on a significantly nonzero fraction of names used in the original IOI paper.Code for this post can be found at https://github.com/ronakrm/ioi-enumerate.Unintentionally continuing the trend of "following up" on the IOI paper, I ran GPT-2 Small on all possible inputs that fit the...

Published on August 14, 2024 11:59 PM GMT[cross-posted from the EA Forum]Post authors: Eli Rose, Asya BergalPosting in our capacities as members of Open Philanthropy’s Global Catastrophic Risks Capacity Building team.Note: This program, together with our separate program for work that builds capacity to address risks from transformative AI, has replaced our 2021 request for proposals for outreach projects. If you have a project which was...

Published on August 14, 2024 11:52 PM GMT[cross-posted from the EA Forum]Post authors: Eli Rose, Asya BergalPosting in our capacities as members of Open Philanthropy’s Global Catastrophic Risks Capacity Building team.This program, together with our separate program for programs and events on global catastrophic risk, effective altruism, and other topics, has replaced our 2021 request for proposals for outreach projects. If you have a project which...

Published on August 14, 2024 8:46 PM GMTGiveWell, and the EA community at large, often emphasize the "cost of saving a life" as a key metric, $5,000 being the most commonly cited approximation. At first glance, GiveWell might seem to be in the business of finding the cheapest lives that can be saved, and then saving them. More precisely, GiveWell is in the business...

Published on August 14, 2024 1:21 PM GMTEpistemic status: Fun speculation. I'm a dilettante in physics and encryption so some mistakes might be expected.The metaphysical claim:Imagine an external universe that seeks to encrypt or hash an enormous amount of data to defend against a powerful adversary. For this purpose, it has built an extremely sophisticated and self-contained encryption machine. I suggest that our universe...

Published on August 14, 2024 12:28 PM GMTI was thinking about what would it mean for a sequence of bits to be "anti-inductive". It probably is a concept that is already known (as a rule of thumb, if I can think about it, someone probably already wrote a paper on it 50 years ago), but I haven't heard about it.*Some sequences are predictable and...

Published on August 14, 2024 5:40 AM GMTQuick psychology experimentRight now, if I offered you a bet that was a fair coin flip, on tails you give me $100, heads I give you $110, would you take it?Got an answer? Good.Hover over the spoiler to see what other people think:About 90% of undergrads will reject this bet[1].Second part now, if I offered you a...

Published on August 14, 2024 12:18 AM GMTEpistemic status: Solider mindset. These are not (necessarily) our actual positions, these are positions we were randomly assigned, and for which we searched for the strongest arguments we could find, over the course of ~1 hr 45 mins.Sides: Ben was assigned to argue that it's ethical to work for an AI capabilities company, and Lawrence was assigned...

Published on August 13, 2024 11:08 PM GMTIs AI takeover like a nuclear meltdown? A coup? A plane crash?My day job is thinking about safety measures that aim to reduce catastrophic risks from AI (especially risks from egregious misalignment). The two main themes of this work are the design of such measures (what’s the space of techniques we might expect to be affordable and...

Published on August 13, 2024 10:35 PM GMTThis is a polemic to the ten arguments post. I'm not a regular LW poster, but I'm an AI researcher and mild-AI-worrier.I believe that AI progress, and the risks associated with it, is one of the most important things to figure out as humanity in the current year. And yet, in most discussions about x-risk, I find...

Published on August 13, 2024 8:39 PM GMTThis post is also available on my Substack.In the previous post, I discussed the possibility of doing ordinal comparison between different entities. Yet usually when we think about measurement, we think of it as involving putting numbers to things, not just ranking them.There are quite a few methods to convert rankings into numbers, such as Elo scores...

Published on August 13, 2024 7:35 PM GMTThe following is an argument for a weak form of the many-worlds hypothesis. The weak form I mean is that there are many observers in different branches of the wave function. The other branches "actually exist" for anthropic purposes; some observers are observing them. I've written before about difficulties with deriving discrete branches and observers from the...

Published on August 13, 2024 5:00 PM GMT #kv6N55hWbJ4HdwA8w .comments-node .InlineReactSelectionWrapper-root { flex: 1 1 70%; } #kv6N55hWbJ4HdwA8w .comments-node .CommentsItemDate-root { display: none; } #kv6N55hWbJ4HdwA8w .comments-node .AgreementVoteAxis-agreementSection { display: none; } #kv6N55hWbJ4HdwA8w .comments-node .CommentsItem-body { display: flex; } #kv6N55hWbJ4HdwA8w .comments-node .CommentsItemMeta-root { order: 2; margin-left: auto; margin-right: 0px; flex-wrap: wrap; } #kv6N55hWbJ4HdwA8w .comments-node .CommentsItemMeta-rightSection { position: inherit; top: 0px; right: 0px; display: none; }...

Published on August 12, 2024 6:27 PM GMTA Defense of Open-Minded Updatelessness.This work owes a great debt to many conversations with Sahil, Martín Soto, and Scott Garrabrant.Sahil and I will have a public discussion about this this Wednesday (August 14) at 11am EDT; join via this link.You can support my work on Patreon.Iterated Counterfactual Mugging On a Single CoinflipIterated counterfactual mugging on a single...

Published on August 12, 2024 6:10 PM GMTToby Ord recently published a nice piece On the Value of Advancing Progress about mathematical projections of far-future outcomes given different rates of progress and risk levels. The problem with that and many arguments for caution is that people usually barely care about possibilities even twenty years out. We could talk about sharp discounting curves in decision-making studies,...