~www_lesswrong_com | Bookmarks (657)

Published on August 18, 2024 2:10 PM GMT One of the things I like about playing for contra dances is that you have a lot of freedom about what to play. As long as you meet the minimum requirements for danceable music (108-122bpm, contra phrasing) you can do almost anything. And then if you're a bottom left corner band you might want to play...

Published on August 18, 2024 7:02 AM GMT"Since you are reluctant to provide us with the location of the Rebel base," said Grand Moff Tarkin, "I have chosen to test this station's destructive power on your home planet of Alderaan." "No. Alderaan is peaceful. We have no weapons there. It is a loyal planet under Imperial control. Striking Alderaan would destroy your own resources...

Published on August 18, 2024 5:35 AM GMT"My father didn't fight in the wars. He was a navigator on a spice freighter," said Luke. "That's what your uncle told you. Basic security protocol. You don't tell a young child sensitive information about your participation in an ongoing civil war. Which reminds me. I have here something for you. Your father wanted you to have...

Published on August 18, 2024 3:19 AM GMTIntroduction from BenZhukeepa is a LessWronger who I respect and whose views I'm interested in. In 2018 he wrote the first broadly successful explication of Paul Christiano's research ideas for AI alignment, has spent a lot of time interviewing people in AI about their perspectives, and written some more about neuroscience and agent foundations research. He came...

Published on August 18, 2024 1:36 AM GMTMy heart leaps up when I beholdA rainbow in the sky:So was it when my life began;So is it now I am a man;So be it when I shall grow old,Or let me die!The Child is father of the Man;And I could wish my days to beBound each to each by natural piety.-William WordsworthI am exquisitely attuned...

Published on August 17, 2024 11:42 PM GMTSummary: The collection of a massive first-person video dataset for use in large model pretraining is technologically & economically feasible with modest resources. Such a dataset might enable high-fidelity imitation of human behavior, with positive implications for the capabilities and safety of trained models. Such models may also enable a type of “digital immortality” and provide a...

Published on August 17, 2024 10:47 PM GMTTLDR: Through concrete scenic descriptions illustrate how I expect naive goal specifications to fail, for getting diamonds in Minecraft. Not much beyond the concrete examples is original. Also checkout the excellent Specification Gaming video by Rational Animations. The Setup I am playing Minecraft. I'd like to have an AI companion that can perform all sorts of tasks,...

Published on August 17, 2024 4:41 PM GMTI don't usually post stories on LessWrong so I'm curious to see how this is received.The first time we spoke, you asked me some questions that felt really invasive. I didn’t want that to happen again, so I avoided you the entire following year.So when you said “Hi” at a party and suggested catching up, I hesitated....

Published on August 17, 2024 3:30 PM GMTShort version It has always felt like a gift that people read things I write, and I enjoyed reciprocating that by sharing my writing for free.  Until recently I had enough income to pull that off and still cover material needs. That is no longer true, and while it is not an urgent problem, I would like...

Published on August 17, 2024 2:08 PM GMTI recently argued for Cohabitive Games, games that are designed for practicing negotiation, or for developing intuitions for applied cooperative bargaining, which is one of the names of preference aggregation.I offered the assets for P1, my prototype, to whoever was interested. About 20 people asked for them. I told most of them that I wanted to polish...

Published on August 17, 2024 11:07 AM GMTI have started a new personal blog!I intend to use it to write about more esoteric/lower confidence/epistemologically-sticky topics than elsewhere.You can already read the first post: "Mysticism 101, or: In defence of Natural Language DSLs"Discuss

Published on August 17, 2024 9:57 AM GMTThe agent-like structure problem is a question about how agents in the world are structured. I think rationalists generally have an intuition that the answer looks something like the following:We assume the world follows some evolution law, e.g. maybe deterministically like xn+1=f(xn).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%;...

Published on August 17, 2024 2:36 AM GMTCan SRAM be stacked like NAND flash? background types of memory SRAM has, for each bit, multiple transistors that connect power supplies to the gates of each other. Typically 6 transistors are used, but many variations have been proposed. DRAM uses transistors to connect capacitors to an input/output line when they're written or read. The capacitors lose...

Published on August 17, 2024 1:16 AM GMTTL;DR: We demonstrate that the decoder directions of GPT-2 SAEs are highly structured by finding a historical date direction onto which projecting non-date related features lets us read off their historical time period by comparison to year features.Calendar years are linear: there are as many years between 2000 and 2024, as there are between 1800 and 1824....

Published on August 16, 2024 8:21 PM GMTI may be completely confused about this, but my model of technological breakthroughs in history was basically this: A few guys independently connect the dots leading to a new invention, for example the telephone, approximately at the same time. One of them runs to the patent office a little faster than the others, and he gets the...

Published on August 14, 2024 11:04 PM GMTI am just getting into the field and I would really appreciate some recommended reading. I am looking for articles/papers that showcase some of the best current proposals for solving the AGI control problem. Discuss

Published on August 15, 2024 5:03 PM GMTIs there anything you avoid that exposure still hasn’t fixed?…Why is that? In my experience, people who avoid X are usually not afraid of the average X… For example, I spoke to someone who is afraid of starting conversations with women he’s attracted to. But as far as I can tell, he has no fear of how this will...

Published on August 15, 2024 12:50 PM GMTAbstractLanguage models rapidly become more capable, and both AI labs and policy makers[1][2][3] are in need of benchmarks that measure their proficiency in biology, and conducting biological research, but there are only a handful of benchmarks evaluating these capabilities[4][5], and all of them have their limitations. This paper introduces the Biological Lab Protocol benchmark (BioLP-bench) that evaluates...

Published on August 15, 2024 11:26 AM GMTEpistemic status: This post touches on bodywork, NLP, Salsa and Yoga. I went through a 4-year training in Danis Bois style of bodywork, have roughly 70 seminar days worth of NLP training, and started dancing Salsa back in 2008 and have danced it a lot since then. I don't have special expertise in Yoga, but apply general...

Published on August 15, 2024 4:22 AM GMTWe may be making important conceptual or methodological errors in prioritization between moral patients. In this sequence, I illustrate and address several:Types of subjective welfare: I review types of subjective welfare, interpersonal comparisons with them and common grounds between them.Solution to the two envelopes problem for moral weights: The welfare concepts we value directly are human-based, so...

Published on August 14, 2024 11:24 PM GMTtl;dr: For Lisa, GPT-2 does not do IOI. GPT-2 fails to perform the IOI task on a significantly nonzero fraction of names used in the original IOI paper.Code for this post can be found at https://github.com/ronakrm/ioi-enumerate.Unintentionally continuing the trend of "following up" on the IOI paper, I ran GPT-2 Small on all possible inputs that fit the...

Published on August 14, 2024 11:59 PM GMT[cross-posted from the EA Forum]Post authors: Eli Rose, Asya BergalPosting in our capacities as members of Open Philanthropy’s Global Catastrophic Risks Capacity Building team.Note: This program, together with our separate program for work that builds capacity to address risks from transformative AI, has replaced our 2021 request for proposals for outreach projects. If you have a project which was...