~www_lesswrong_com | Bookmarks (692)

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...

Published on November 15, 2024 3:47 PM GMTIn this post, I’ll make a technical point that comes up when thinking about risks from scheming AIs from a control perspective.In brief: Consider a deployment of an AI in a setting where it’s going to be given a sequence of tasks, and you’re worried about a safety failure that can happen suddenly. Every time the AI...

Published on November 15, 2024 1:59 PM GMTTechnological progress can excite us, politics can infuriate us, and wars can mobilize us. But faced with the risk of human extinction that the rise of artificial intelligence is causing, we have remained surprisingly passive. In part, perhaps this was because there did not seem to be a solution. This is an idea I would like to...

Published on November 14, 2024 6:39 PM GMTI spent most of my election day -- 3pm to 11pm Pacific time -- trading on Manifold Markets. That went about as well as it could have gone. I doubled the money I was trading with, jumping to 10th place on Manifold's all-time leaderboard. Spending my time trading instead of just nervously watching results come in also...

Published on November 14, 2024 4:59 PM GMTAbstractThis post summarises my findings on the effects of Non-Uniform feature sparsity on Superposition in the ReLU output model, introduced in the Toy Models of Superposition paper, the ReLU output model is a toy model which is shown to exhibit features in superposition instead of a dedicated dimension ('individual neuron') devoted to a single feature. That experiment...

Published on November 14, 2024 5:02 PM GMTScott Alexander's latest today discusses Robert Axelrod's Prisoner’s Dilemma Tournament and the morality of Christians, Quakers, and the rationalist community. I think is of general interest to LessWrong readers.This is why I’m so fascinated by the early Christians. They played the doomed COOPERATE-BOT strategy and took over the world.https://www.astralcodexten.com/p/the-early-christian-strategy Discuss

Published on November 14, 2024 2:37 PM GMT1. PROBLEM In today’s digital era, teenagers face a dual challenge: processing vast amounts of information and maintaining emotional well-being. Traditional educational models, focused on memorization and mechanical procedures, might be better suited to preparing students for complex decision-making in an increasingly uncertain world.As part of a non-profit Latín American education initiative, Jacominesp, I seek to connect with...

Published on November 14, 2024 2:10 PM GMTAs the Trump transition continues and we try to steer and anticipate its decisions on AI as best we can, there was continued discussion about one of the AI debate’s favorite questions: Are we making huge progress real soon now, or is deep learning hitting a wall? My best guess is it is kind of both, that...

Published on November 14, 2024 1:06 PM GMTTLDR:Fluent dreaming for language models is an algorithm based on the GCG method that can reliably find plain-text readable prompts for LLMs that maximize certain logits or residual stream directions by using gradients and genetic algorithms. Authors showed its use for visualizing MLP neurons. We show this method can also help interpret SAE features.We reimplement the algorithm in...

Published on November 14, 2024 7:00 AM GMTYouTube link Do language models understand the causal structure of the world, or do they merely note correlations? And what happens when you build a big AI society out of them? In this brief episode, recorded at the Bay Area Alignment Workshop, I chat with Zhijing Jin about her research on these questions. Topics we discuss: How...

Published on November 14, 2024 6:13 AM GMTFrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AIFrontierMath presents hundreds of unpublished, expert-level mathematics problems that specialists spend days solving. It offers an ongoing measure of AI complex mathematical reasoning progress.We’re introducing FrontierMath, a benchmark of hundreds of original, expert-crafted mathematics problems designed to evaluate advanced reasoning capabilities in AI systems. These problems span major...