~www_lesswrong_com | Bookmarks (667)

Published on November 20, 2024 11:48 AM GMTAuthors: Anonymous (I'm not one of them).Abstract:Most analysis of transformer expressivity treats the depth (number of layers) of a model as a fixed constant, and analyzes the kinds of problems such models can solve across inputs of unbounded length. In practice, however, the context length of a trained transformer model is bounded. Thus, a more pragmatic question...

Published on November 20, 2024 11:04 AM GMTCurrently, it looks like Robert F. Kennedy Jr. will become HHS secretary and change a lot of things at the HHS. There will likely be both good and bad changes.It's a time when the ideas that lay around matter. What changes do you think should be made? What clever policy ideas should be adopted?Discuss

Published on November 20, 2024 10:13 AM GMTSummary thread: https://x.com/GarrisonLovely/status/1859022323799699474. An influential congressional commission is calling for a militarized race to build superintelligent AI based on threadbare evidenceDiscuss

Published on November 20, 2024 6:04 AM GMTI run a weekly sequences-reading meetup with some friends, and I want to add a film-component, where we watch films that have some tie-in to what we've read.I got to talking with friends about what good rationality films there are. We had some ideas but I wanted to turn it to LessWrong to find out.So please, submit...

Published on November 20, 2024 1:37 AM GMTAs I relayed in my last post, in "Theory of Games and Economic Behavior", von Neumann and Morgenstern defended the validity of using utility to predict economic outcomes despite the fact that cross-individual utility cannot apparently be measured or apprehended directly: "The [ . . . ] difficulties of the notion of utility, and particularly of the...

Published on November 20, 2024 12:57 AM GMTI work in a niche company in a niche industry mostly with a nearly-obsolete programming language. I have worked for the same company for an extremely long time by programmer standards, basically right out of high-school. I have not looked for work in a very long time.Reading HackerNews lately, the market looks pretty grim. I am reading...

Published on November 18, 2024 6:25 PM GMTWe wanted to run an event where controversial opinions could be shared without restraint: “a safe space for what you can't say in ‘safe spaces’”So a mechanism was devised:https://x.com/tobi/status/1795619548579918222Examples of what may or may have been on the slips:“Only white men can save us.”“Intelligent people are worth more.”“Bestiality is good, actually.” We also advertised the event so only...

Published on November 18, 2024 4:00 PM GMTWhat kinds of ethical implications should we expect from the Many-Worlds Interpretation of Quantum Mechanics (MWI)? I’ll argue that we shouldn’t expect decision-making to change. The implications are more about how we should think or feel about events in our lives, and the virtues of taking a cosmic perspective.According the many-worlds interpretation (MWI) of quantum mechanics, the universe...

Published on November 18, 2024 2:25 PM GMTGreat. Another crucial consideration I missed. I was convinced that working on reducing the existential risk for humanity should be a global priority.Upholding our potential and ensuring that we can create a truly just future seems so wonderful.Well, recently I was introduced to the idea that this might actually not be the case. The argument is rooted in...

Published on November 18, 2024 4:58 PM GMTPeople often ask me this. It’s a good question. It seems potentially important for anyone who doesn’t want to die, or doesn’t want other people to have to die. I don’t feel like I have a good answer, which is one reason I want to do more research. But recently I think my answer has gotten a...

Published on November 18, 2024 4:05 PM GMT(thanks to Alex Mallen, Cody Rushing, Zach Stein-Perlman, Hoagy Cunningham, Vlad Mikulik, and Fabien Roger for comments)Sometimes I hear people argue against AI control as follows: if your control measures rely on getting good judgments from "trusted" AI models, you're doomed because AI models aren't adversarially robust. I agree that better adversarial robustness would definitely help with...

Published on November 18, 2024 1:20 PM GMTThis is your monthly roundup. Let’s get right to it. Young People are Young and Stupid As a reminder that yes college students are often young and stupid and wrong about everything, remember the time they were behind a ban on paid public toilets? This is a central case of the kind of logic that often gets...

Published on November 18, 2024 12:45 PM GMTThis post was written during the agent foundations fellowship with Alex Altair funded by the LTFF. Thanks to Alex, Jose, Daniel, Cole, and Einar for reading and commenting on a draft.The Good Regulator Theorem, as published by Conant and Ashby in their 1970 paper (cited over 1700 times!) claims to show that 'every good regulator of a...

Published on November 18, 2024 12:30 PM GMTOn the emergence of history's reinsOne general law, leading to the advancement of all organic beings, namely, multiply, vary, let the strongest live and the weakest die.― Charles DarwinWe are a way for the universe to know itself.— Carl SaganIf you don’t know where you are going, you’ll end up someplace else.— Yogi BerraImagine you were trying...

Published on November 18, 2024 4:21 AM GMTFertility rates in the developed world are too low and that's bad, blah blah.Here's my proposal to raise fertility rates (coming from a current uni student):Promote parenthood in universities via student run clubs. Reading groups about different parenting styles, or more subtle pro-fertility clubs like knitting groups where students make clothes for sick kids (very un-EA, I...

Published on November 18, 2024 2:13 AM GMTNote: I would have done this as a Quick Take, but it doesn't allow images.In the spirit of How I got 4.2M YouTube views without making a single video, I improved a diagram on the wikipedia page for Pareto Efficiency.ORIGINAL VERSIONNEW VERSION Based on the text, I don't think the author understood that Cooperate/Cooperate isn't the only Pareto...

Published on November 16, 2024 2:31 PM GMTAt every turn there was a Gwern, Within this dream I couldn't discern If to Heaven I did rise Or in Satan's pit - my soul's demise. Creatures short and stout and keen of mind Wrote and wrote, words flowed like wine. "Good sir," I said, "how did you come to be In this place with him....

Published on November 16, 2024 2:24 PM GMTI want to make a serious effort to create a bigger evals field. I’m very interested in which resources you think would be most helpful. I’m also looking for others to contribute and potentially some funding. Which resources would be most helpful? Suggestions include:Open Problems in Evals list: A long list of open relevant problems & projects in...

Published on November 16, 2024 6:38 AM GMTAs part of the court case between Elon Musk and Sam Altman, a substantial number of emails between Elon, Sam Altman, Ilya Sutskever, and Greg Brockman have been released. I have found reading through these really valuable, and I haven't found an online source that compiles all of them in an easy to read format. So I made...

Published on November 16, 2024 4:29 AM GMTRob Miles has released a new video, this time on control!Youtube Transcript (Very rough)0:00hi so this channel is about AI safety a lot of people when they hear AI safety0:05the first thing that comes to mind is they think it's about how to keep potentially dangerous AI systems under control that we're trying to answer0:11questions like what...

Published on November 16, 2024 2:59 AM GMTEpistemic status: Toy model. Oversimplified, but has been anecdotally useful to at least a couple people, and I like it as a metaphor.IntroductionI’d like to share a toy model of willpower: your psyche’s conscious verbal planner “earns” willpower (earns trust with the rest of your psyche) by choosing actions that nourish your fundamental, bottom-up processes in the...

Published on November 16, 2024 12:57 AM GMTI wrote a whole book! What's next?I'm currently doing an edit pass on the entire book. I need to rewrite some of the early sections, fix some consistency issues, and generally look with fresh eyes on words I wrote months or years ago. Many of you provided helpful comments, and I'm using those to make the second...

Published on November 15, 2024 6:55 PM GMTTrump and the Republican party will yield broad governmental control during what will almost certainly be a critical period for AGI development. In this post, we want to briefly share various frames and ideas we’ve been thinking through and actively pitching to Republican lawmakers over the past months in preparation for the possibility of a Trump win.Why...