~www_lesswrong_com | Bookmarks (667)

Published on August 30, 2024 10:18 PM GMTBook review: On the Edge: The Art of Risking Everything, by Nate Silver. Nate Silver's latest work straddles the line between journalistic inquiry and subject matter expertise. "On the Edge" offers a valuable lens through which to understand analytical risk-takers. The River versus The Village Silver divides the interesting parts of the world into two tribes. On...

Published on August 30, 2024 8:00 PM GMTThanks to Jesse Hoogland and George Wang for feedback on these exercises. In learning singular learning theory (SLT), I found it was often much easier to understand by working through examples, rather than try to work through the (fairly technical) theorems in their full generality. These exercises are an attempt to collect the sorts of examples that I...

Published on August 30, 2024 6:00 PM GMTAI for biotech, particularly with drug discovery applications, has been used for more than a decade, with ambiguous success. But in the era of foundation models we may have experienced a step change in what’s possible.I used to work on AI-for-drug-discovery years ago, at Recursion, where we sought to identify phenotypes of genetic diseases visible in microscopic...

Published on August 30, 2024 3:43 PM GMTSummary: The AI safety research community should adopt standardized terms for probability ranges, especially in public-facing communication and especially when discussing risk estimates. The terms used by the IPCC are a reasonable default. Science communication is notoriously hard. It's hard for a lot of reasons, but one is that laypeople aren't used to thinking in numerical probabilities or...

Published on August 30, 2024 3:12 PM GMTThis question is kind of self-explanatory, but for people who are physicists, if a time reversible rule of physics/cellular automaton exists in a world, does this automatically imply the first law of thermodynamics, that is energy may not be created or destroyed? Note I'm not talking about time-symmetry or the 2nd law of thermodynamics, which states that...

Published on August 30, 2024 2:29 PM GMTCrossposted from https://williamrsaunders.substack.com/p/principles-for-the-agi-raceWhy form principles for the AGI Race?I worked at OpenAI for 3 years, on the Alignment and Superalignment teams. Our goal was to prepare for the possibility that OpenAI succeeded in its stated mission of building AGI (Artificial General Intelligence, roughly able to do most things a human can do), and then proceed on to...

Published on August 30, 2024 1:32 PM GMTYou’ve probably seen the Nancy Pelosi Stock Tracker on X or else a collection of articles and books exposing the secret and lucrative world of congressional insider trading.The underlying claim behind these stories is intuitive and compelling. Regulations, taxes, and subsidies can make or break entire industries and congresspeople can get information on these rules before anyone...

Published on August 30, 2024 9:04 AM GMTI've read the abstract of this paper, How Organisms Come to Know the World: Fundamental Limits on Artificial General Intelligence. It says: A general example of an affordance is the use of an object in the hands of an agent. We show that it is impossible to predefine a list of such uses. Therefore, they cannot be treated...

Published on August 30, 2024 3:14 AM GMTI am unsure, but I disagree with one argument that they aren’t.There’s a joke about how humans have gotten so good at thinking that they tricked rocks into thinking for them. But it’s a joke, in part because it’s funny to say that computers work by “tricking rocks into thinking,” and in part because what computers do...

Published on August 30, 2024 2:25 AM GMTIf you ask the internet if breastfeeding is good, you will soon learn that YOU MUST BREASTFEED because BREAST MILK = OPTIMAL FOOD FOR BABY. But if you look for evidence, you’ll discover two disturbing facts.First, there’s no consensus about why breastfeeding is good. I’ve seen experts suggest at least eight possible mechanisms:Formula can’t fully reproduce the...

Published on August 29, 2024 10:42 PM GMT.mjx-chtml {display: inline-block; line-height: 0; text-indent: 0; text-align: left; text-transform: none; font-style: normal; font-weight: normal; font-size: 100%; font-size-adjust: none; letter-spacing: normal; word-wrap: normal; word-spacing: normal; white-space: nowrap; float: none; direction: ltr; max-width: none; max-height: none; min-width: 0; min-height: 0; border: 0; margin: 0; padding: 1px 0} .MJXc-display {display: block; text-align: center; margin: 1em 0; padding: 0} .mjx-chtml[tabindex]:focus,...

Published on August 29, 2024 6:43 PM GMTThis year's Fall ACX Meetup everywhere in Bellevue-Redmond. Location: TBD: I want to reserve a library room but room reservations have to be made one month in advance max – https://plus.codes/84VVJVC9+R6 Contact: cedar.ren@gmail.com Discuss

Published on August 28, 2024 6:13 PM GMTPsyllium husk is a non-fermenting (no gas or bloating) soluble dietary fiber that improves both constipation and diarrhea (such as with IBS), normalizes blood sugar, reduces LDL ("bad") cholesterol, and can help with weight loss. Each type of dietary fiber has different effects, and a "high fiber" diet in general won't necessarily provide the same benefits.I'm sharing...

Published on August 28, 2024 5:19 PM GMTThis post is spoiler-freeI just finished Project Lawful, a really long, really weird book by Eliezer Yudkowsky.The book's protagonist is a knowledgable and perceptive target. A conspiracy forms around the target to learn from him while keeping him from finding out that helping them is not in the target's best interests. The book is written from the...

Published on August 28, 2024 4:42 PM GMTSummaryI’ve been working on a project aimed at finding goal representations in a small RL agent. I designed a setup where I train an agent, rapidly alternating between two very similar objectives. I was able to consistently (across alternations and across different random seeds) get high average returns on both objectives, which I think suggests the agent contains...

Published on August 28, 2024 1:46 PM GMTPaging Gwern or anyone else who can shed light on the current state of the AI market—I have several questions.Since the release of ChatGPT, at least 17 companies, according to the LMSYS Chatbot Arena Leaderboard, have developed AI models that outperform it. These companies include Anthropic, NexusFlow, Microsoft, Mistral, Alibaba, Hugging Face, Google, Reka AI, Cohere, Meta,...

Published on August 28, 2024 10:38 AM GMTAuthors: Zirui Chen, Michael F. Bonner.Quick take: this seems among the strongest evidence yet for the Natural Abstration Hypothesis.Abstract:Do neural network models of vision learn brain-aligned representations because they share architectural constraints and task objectives with biological vision or because they learn universal features of natural image processing? We characterized the universality of hundreds of thousands of...

Published on August 28, 2024 9:21 AM GMTWhat are ways to prevent development of dangerous AI? When I started on this question two years ago, I expected that passing laws to ban dangerous architectures was the way to go. Then I learned about many new ways from other concerned communities. It was overwhelming.  Here’s a four-level framework I found helpful for maintaining an overview.Four things need...

Published on August 28, 2024 8:12 AM GMTTLDR: Select candidates heterogeneously, then give them all a very hard test, only continue with candidates that do very well (accept that you lose some good ones), then briefly judge on interviews/whatever. I'm no expert but I've made some recommendations that turned out pretty well -- maybe like 5 ever. This post would probably be better if...

Published on August 28, 2024 1:57 AM GMTThe bottom of the coffee table is not the ceilingNot long ago, Andrew Ng posted one of the most fascinating tweets I've read in quite some time. It's a longer post, but the main introduction is worthy jumping off from, as it inadvertently answers a question many current AI-skeptics raise about the nature of LLMs.https://twitter.com/AndrewYNg/status/1770897666702233815Today, we mostly...

Published on August 27, 2024 11:17 PM GMTIn a 2016 blog post, Paul Christiano argued that the universal prior (hereafter "UP") may be "malign."  His argument has received a lot of follow-up discussion, e.g. inMark Xu's The Solomonoff Prior is MalignCharlie Steiner's The Solomonoff prior is malign. It's not a big deal.among other posts.This argument never made sense to me.  The reason it doesn't...

Published on August 27, 2024 6:30 PM GMTLarge bureaucratic organizations have long seemed… strange to me, on an intuitive level. Why do they exist? Like, in a world where the median person is John Wentworth (“Wentworld”), I’m pretty sure there just aren’t large organizations of the sort our world has. Nobody would ever build such an organization, because they’re so obviously wildly inefficient and misaligned....

Published on August 27, 2024 6:26 PM GMTHi. About an hour ago, someone posted here a thing to the effect of "LLMs writte prefectly boring, hears my deliberatyle mispelled manifesto". It had a mixed reaction on both the karma and comment respects, yet I believe it had some real and original aesthetic value.The author has since deleted the post. I'd love to have a...

Published on August 27, 2024 5:58 PM GMTIt seems to me that when normal people are concerned about AI destroying their life, they are mostly worried about technological unemployment, whereas rationalists think that it is a bigger risk that the AI might murder us all, and that automation gives humans more wealth and free time and is therefore good.I'm not entirely unsympathetic to the...