~www_lesswrong_com | Bookmarks (664)

Published on October 6, 2024 5:21 PM GMTWritten by Tom Ireland & published by Asimov Press.The womb is a remarkable organ — a muscular, pear-shaped chamber that supports the transformation of a tiny cluster of dividing cells into an entirely new person. All humans begin their lives in this sturdy chamber.At least for now.Several research groups are busily developing artificial wombs to replicate the...

Published on October 6, 2024 3:22 PM GMTThis post focuses on philosophical objections to Bayesianism as an epistemology. I first explain Bayesianism and some standard objections to it, then lay out my two main objections (inspired by ideas in philosophy of science). A follow-up post will speculate about how to formalize an alternative.Degrees of beliefThe core idea of Bayesianism: we should ideally reason by...

Published on October 6, 2024 11:10 AM GMTThis is a crosspost from https://250bpm.substack.com/p/european-progress-conferenceEurope has become known as a hub of degrowth.Where are the authors of degrowth papers from?European parliament even hosted a degrowth conference. Ursula von der Leyen addressed the participants and took a conciliatory (although still a pro-growth) stance.This stuff is scary: I've seen degrowthers going so far as proposing to take lessons...

Published on October 5, 2024 8:43 PM GMTThis is a forecasting contest with cash prizes that I'm running based on 50 questions about the the 2024 election. Posting it here because I think a lot of people in this community like forecasting, prediction markets, etc. (Actually this is my first LW post after years of lurking. Am I allowed to post stuff like this?...

Published on October 5, 2024 10:28 PM GMTIf it’s worth saying, but not worth its own post, here's a place to put it.If you are new to LessWrong, here's the place to introduce yourself. Personal stories, anecdotes, or just general comments on how you found us and what you hope to get from the site and community are invited. This is also the place...

Published on October 5, 2024 8:43 PM GMTProduced by Jon Kutasov and David Steinberg as a capstone project for ARENA. Epistemic status: 5 days of hacking, and there could be bugs we haven’t caught. Thank you to the TAs that helped us out, and to Adam Karvonen (author of the paper our work was based on) for answering our questions and helping us debug...

Published on October 5, 2024 9:28 PM GMTI am actively looking for a tutor/advisor with expertise in AI x-risk, with the primary goal of collaboratively determining the most effective ways I can contribute to reducing AI existential risks (X-risk).Tutoring GoalsI suspect that I misunderstand key components of the mental models that lead some highly rational and intelligent individuals to assign a greater than 50%...

Published on October 5, 2024 8:00 PM GMTby Daniel Böttger. This was posted on ACX a few months ago but came up in a podcast of the Bayesian Conspiracy, recently.Discuss

Published on October 5, 2024 7:14 PM GMTDamon Sasi (@DaystarEld) is a mentor of mine, and he is also a therapist who claims to be very psychologically healthy. What’s his inner experience like?“Probably for an average week, maybe I'll suffer for like five minutes”“I don't think I have any prolonged internal conflict”“Self-loathing to me was a weird concept […] Like, what does it mean...

Published on October 5, 2024 7:00 PM GMTThe Chinchilla scaling law says that for a given number of FLOPs C, the optimal amount of data D to train on is proportional to (C to the power of b), that is you'll get a less intelligent model if you use either more data or less data than that while training for C FLOPs. The optimal...

Published on October 4, 2024 5:25 PM GMTIn the past couple of years, I’ve found myself roles that are defined by their lack of definition. It’s the kind of role that lets you add value in ways that don’t fit neatly into tech’s boxes, where there’s room for more undirectedness and using your curiosity as a battering ram. Depending on where you’re working, the...

Published on October 4, 2024 1:44 PM GMTTLDR; apply by October 27th to join a 13-week research programme in AI safety. You’ll write a technical paper in a team of 3-4 with supervision from an experienced researcher. The programme is full-time in London.  Apply to be a participant here. We’re also looking for a programme manager, and you can read more about the role here.London AI Safety Research (LASR)...

Published on October 3, 2024 7:11 PM GMTEpistemic status: Theorizing on topics I’m not qualified for. Trying my best to be truth-seeking instead of hyping up my idea. Not much here is original, but hopefully the combination is useful. This hypothesis deserves more time and consideration but I’m sharing this minimal version to get some feedback before sinking more time into it. “We believe there’s...

Published on October 3, 2024 6:47 PM GMTI wanted to share a new paper from the special issue on AI safety that I'm editing, which takes up the influential idea that evolutionary theory gives us some reason to think that the project of value alignment is bound to fail and (in my opinion) shows that it has serious problems. If you don't have institutional access...

Published on October 3, 2024 6:04 PM GMTThis is a re-post from our previous version that incorporates initial feedback.The preprint version of this post is available on ArXiv.We investigate whether we can bias the output of Vision-Language Models with visual stimuli that contradict the "correct answer." This phenomenon, which we term "multi-modal agreeableness", is a type of modality bias where a concept or object...

Published on October 3, 2024 3:00 PM GMTIntroduction: Better than a Podcast Andrej Karpathy continues to be a big fan of NotebookLM, especially its podcast creation feature. There is something deeply alien to me about this proposed way of consuming information, but I probably shouldn’t knock it (too much) until I try it? Others are fans as well. Carlos Perez: Google with NotebookLM may...

Published on October 3, 2024 11:31 AM GMTI just want to make sure that when I donate money to AI alignment stuff it's actually going to be used economicallyDiscuss

Published on October 3, 2024 12:01 AM GMTSummaryA previous post argued that work on Alignment Target Analysis (ATA) needs to start now in order to reduce the probability of a bad alignment target getting successfully implemented. The present post is focused on one specific scenario where starting ATA work now would reduce the probability of disaster. Different types of time crunch can lead to...

Published on October 2, 2024 10:42 PM GMTThe Ferrett isn't an official member of the Rationalist Diaspora, but he's been blogging for longer than LessWrong has existed and often has useful insights that align with what the LessWrong community likes to talk and think about, and when I find one, I link to it. The advice in here might very well be of the...

Published on October 2, 2024 5:11 PM GMTMIT FutureTech is hiring for a Head of Operations role. This is an exciting opportunity to support a rapidly growing lab who work on socially impactful AI and computing research, and rapidly develop cutting-edge skills and experience.Please apply or share as relevant.Why apply or share?Our work to understand progress in computing and artificial intelligence, and its implications,...

Published on October 2, 2024 3:21 PM GMTAI definitely poses an existential risk, in the sense that it can generate models with the hidden (possibly undetectable?) intention of competing against humanity for resources. The more intelligent the model, the higher its chance of success!The thought of an AI takeover is so scary that I won’t even try to imagine what its possible implications may...

Published on October 2, 2024 3:20 PM GMT3.1 Post summary / Table of contentsThis is the third of a series of eight blog posts, which I’m serializing over the next month or so. (Or email or DM me if you want to read the whole thing right now.)So far in the series, Post 1 established some foundations about intuitive self-models in general, and then Post 2 talked about...

Published on October 2, 2024 11:39 AM GMTHere, I will list the three main arguments without going into detail before going to meta-argument:The first argument is that AI thinks it may be in a testing simulation, and if it harms humans, it will be turned off.AI acausally trades with other branches of the multiverse. It preserves 10 planets of humans, and in some branches...