~www_lesswrong_com | Bookmarks (667)

Published on September 13, 2024 3:40 PM GMTMidjourney, “Fourth Industrial Revolution Digital Transformation”This is a little rant I like to give, because it’s something I learned on the job that I’ve never seen written up explicitly.There are a bunch of buzzwords floating around regarding computer technology in an industrial or manufacturing context: “digital transformation”, “the Fourth Industrial Revolution”, “Industrial Internet of Things”.What do those...

Published on September 13, 2024 2:13 PM GMTI see "AGI" used for everything from existing LLMs to superintelligence, and massive resulting confusion and illusory disagreements. I finally thought of a term I like for what I mean by AGI. It's an acronym that's also somewhat intuitive without reading the definition:Reasoning, Reflective Entities with Autonomy and Learningmight be called "(R)REAL AGI" or "real AGI".  See...

Published on September 13, 2024 2:00 PM GMTPeople thinking about the future of AI sometimes talk about a single project ‘getting there first’ — achieving AGI, and leveraging this into a decisive strategic advantage over the rest of the world.I claim we should be worried about this scenario. That doesn’t necessarily mean we should try to stop it. Maybe it’s inevitable; or maybe it’s...

Published on September 13, 2024 11:59 AM GMTIntroductionThere is a new paper and lesswrong post about "learned look-ahead in a chess-playing neural network". This has long been a research interest of mine for reasons that are well-stated in the paper: Can neural networks learn to use algorithms such as look-ahead or search internally? Or are they better thought of as vast collections of simple heuristics...

Published on September 13, 2024 11:37 AM GMTCrossposting from my blogI did a major career review during 2023. I’m sharing it now because:I think it’s a good case study for iterated depth decision-making in general and reevaluating your career in particular, and I want to let you know about my exciting plans! I’m doing the Tarbell Fellowship for early-career journalists for the next nine months....

Published on September 12, 2024 6:10 PM GMT[Conflict of interest disclaimer: We are FutureSearch, a company working on AI-powered forecasting and other types of quantitative reasoning. If thin LLM wrappers could achieve superhuman forecasting performance, this would obsolete a lot of our work.]Widespread, misleading claims about AI forecastingRecently we have seen a number of papers – (Schoenegger et al., 2024, Halawi et al., 2024, Phan...

Published on September 11, 2024 6:36 PM GMTI first learned about cryonics when I read Eliezer and Robin's posts about it on Overcoming Bias years ago. I got cryopilled. Somewhat amazingly to me, I'm now a researcher in this field. So I thought this community might be interested to know that I was one of several co-authors on a paper just published in Frontiers...

Published on September 11, 2024 3:09 PM GMTTL;DR I need help finding/developing a mech that can reliably elicit honest and effortful risk-estimates from labs regarding their models, risk-estimates to be used in risk-priced premiums that labs then pay the government (i.e. a "Pigouvian tax for x-risk"). Current best guess: Bayesian Truth Serum.Stretch-goal: find/develop a mech for incenting optimal production of public safety research. Current best...

Published on September 11, 2024 9:53 AM GMTHave you ever wondered what the world would be like if you hadn’t been born? Would an entirely different person have taken your place? How about if humans had never emerged? Could another species have evolved higher levels of intelligence instead of us? What if life, as we know it, didn’t emerge-could some life-form, based on entirely...

Published on September 11, 2024 4:41 AM GMTPeople often attack frontier AI labs for "hypocrisy" when the labs admit publicly that AI is an extinction threat to humanity.  Often these attacks ignore the difference between various kinds of hypocrisy, some of which are good, including what I'll call "reformative hypocrisy". Attacking good kinds of hypocrisy can be actively harmful for humanity's ability to survive,...

Published on September 10, 2024 9:33 PM GMTSummary: Consider a Membrane that is supposed to protect Steve. An AI wants to hurt Steve but does not want to pierce Steve's Membrane. The Membrane ensures that there is zero effect on predictions of things inside the membrane. The AI will never take any action that has any effect on what Steve does or experience. The...

Published on September 10, 2024 7:22 PM GMTFormalizing the InformalOne way to view MIRI's Agent Foundations research is that it saw the biggest problem in AI safety as "human preferences are informal, but we need to somehow get formal guarantees about them" -- and so, in response, it set out to make a formal-informal bridge.Recently, I’ve been thinking about how we might formally represent...

Published on September 10, 2024 5:50 PM GMT(This was supposed to be on Thursday but I forgot to cross-post) Will AI ever make art? Fully do your coding? Take all the jobs? Kill all the humans? Most of the time, the question comes down to a general disagreement about AI capabilities. How high on a ‘technological richter scale’ will AI go? If you feel...

Published on September 10, 2024 5:34 PM GMTEpistemic status: these are my own opinions on AI risk communication, based primarily on my own instincts on the subject and discussions with people less involved with rationality than myself. Communication is highly subjective and I have not rigorously A/B tested messaging. I am even less confident in the quality of my responses than in the correctness...

Published on September 10, 2024 1:50 PM GMTI am posting this now largely because it is the right place to get in discussion of unrealized capital gains taxes and other campaign proposals, but also there is always plenty of other stuff going on. As always, remember that there are plenty of really stupid proposals always coming from all sides. I’m not spending as much...

Published on September 10, 2024 7:11 AM GMTCross post from: https://invertedpassion.com/what-bootstraps-intelligence/A musing on how intelligence comes to be.The bedrock of intelligence is abstractions – the thing we do when we throw away a lot of information and just emphasise on a subset of it (e.g. calling that thing an apple instead of describing all its atoms and their x, y, z positions).But where does...

Published on September 9, 2024 6:38 PM GMTI recently decided to sign a letter of support for SB 1047. Before deciding whether to do so, I felt it was important for me to develop an independent opinion on whether the bill was good, as opposed to deferring to the opinions of those around me, so I read through the full text of SB 1047....

Published on September 9, 2024 5:10 PM GMTReason for Writing: I want to gather information for a friend who is a professional in the behavioral sciences.Epistemic Status: Less than 2 hours googling how to build a forum, and a couple youtube videosRequirements:AestheticInexpensivePrivateEasily SetupThe goal is to create a small, private forum for discussions. I've looked into discourse, not sure if that's the best option.Discuss

Published on September 9, 2024 3:33 AM GMTThis was an up-skilling project I worked on throughout the past months. Even though I don't think it is anything fancy or highly relevant to the research around SAEs, I find it valuable since I learned a lot and refined my understanding of how mechinterp fits in the holistic, bigger picture of AI Safety.In the mid-term future...

Published on September 8, 2024 4:13 PM GMTTo be clear from the outset: I don't believe Eliezer Yudkowsky would make any of the mistakes I describe in this post when playing 2-4-6-alike games. I've performed well in novel pattern-finding challenges, but not necessarily better than I imagine Yudkowsky would. I'm confident he correctly understands and would emphatically agree with everything I'm about to say....

Published on September 9, 2024 1:36 AM GMTI'm sorry if this question is a bit fuzzy, maybe my understanding of a "passion" isn't the most coherent. But, I'd like to know if anyone has made a successful effort to get themselves to be passionate about doing X where they were not passionate about X before. I suppose you could call that "creating drive."For context:...

Published on September 8, 2024 10:10 PM GMT Pew recently commissioned Gallup to run a poll in Israel on attitudes to social media censorship. They found high support for banning various kinds of speech: The fourth question, especially, is disturbing: 59% want to ban publicly expressing sympathy for civilians in Gaza? Since the polling was conducted in Hebrew and Arabic, however, this got me...

Published on September 8, 2024 4:09 PM GMTAttachment theory is a psychological theory that has gained an important place in child development literature, especially since the mid-20th century. First developed by British psychiatrist John Bowlby, the theory suggests that the emotional bonds that children form with their primary caregivers deeply affect their social, emotional and cognitive development in later life. According to John Bowlby,...

Published on September 8, 2024 4:09 PM GMTSummary In this article, Erik Erikson's theory of psychosocial development is discussed in depth and the critical impact of the parenting role at each stage and the long-term psychosocial consequences of childhood are analysed. The article discusses how the theory is supported by current research, how deficiencies experienced in childhood can lead to problems in adulthood, and how...