id
stringlengths
36
36
source
stringclasses
15 values
formatted_source
stringclasses
13 values
text
stringlengths
2
7.55M
cd5902b2-0c4a-4d66-aca4-4a7155241166
trentmkelly/LessWrong-43k
LessWrong
Computing Natural Abstractions: Linear Approximation Background: Testing The Natural Abstraction Hypothesis Given a world-model, direct computation of natural abstractions basically amounts to figuring out which X-values give the same Y-distributions y↦P[Y=y|X], for various choices of the variables X and Y in some la...
f2474365-e4ec-46d2-b5fe-ba3d2cdbbf0a
awestover/filtering-for-misalignment
Redwood Research: Alek's Filtering Results
id: post3609 Highlights Specification gaming examples in AI (Victoria Krakovna) : A list of examples of specification gaming, where an algorithm figures out a way to literally satisfy the given specification which does not match the designer's intent. Should you read it? There were several examples I hadn't heard of b...
bbe9e090-bc59-418f-af40-15db146744b6
trentmkelly/LessWrong-43k
LessWrong
Vague Thoughts and Questions about Agent Structures Epistemic status: Posting for blog day at MSFP! More trying to figure out what the right definitions are than saying anything concrete. I still don’t really know what agents are, and none of this is math yet. I’m hoping to develop these (and other) ideas more in the ...
98448bcf-5be0-4009-82d0-79dd78d38628
trentmkelly/LessWrong-43k
LessWrong
What ethical thought experiments can be reversed? Some thought experiments follow this template: 1. We have a moral intuition 2. We make some computation to what this intuition implies 3. We check how we feel about this implication, and it feels counter-intuitive Then some people bite the (3) bullet. But bullets ...
9ca1a1bd-094a-485d-b0dd-041a7f2145fa
trentmkelly/LessWrong-43k
LessWrong
Interpersonal alignment intuitions Let's try this again... The problem of aligning superhuman AGI is very difficult. We don't have access to superhuman general intelligences. We have access to superhuman narrow intelligences, and human-level general intelligences. There's an idea described here that says: (some of)...
fe5eb36d-a2ba-4127-8018-fce6fb01ed9c
trentmkelly/LessWrong-43k
LessWrong
What Else Would I Do To Make a Living? Response to: The Value of Theoretical Research   Reading paulfchristiano's article the other day, I realized that I had had many similar discussions with myself, and have been guilty of motivated stopping and poor answers to all of them. However, one major roadblock in my purs...
68478e87-84a5-4347-bd8d-4a3c5960747a
StampyAI/alignment-research-dataset/eaforum
Effective Altruism Forum
Amazon to invest up to $4 billion in Anthropic > Today, we’re announcing that Amazon will invest up to $4 billion in Anthropic. The agreement is part of a broader collaboration to develop reliable and high-performing foundation models. > > (Thread continues from there with more details -- seems like a notable ma...
a3aedcc3-d030-4d03-aa94-311452879b9b
trentmkelly/LessWrong-43k
LessWrong
[SEQ RERUN] Psychic Powers Today's post, Psychic Powers was originally published on 12 September 2008. A summary (taken from the LW wiki):   > Some of the previous post was incorrect. Psychic powers, if indeed they were ever discovered, would actually be strong evidence in favor of non-reductionism. Discuss the po...
e5e1d738-fdf5-4bb9-a897-6c3d6164adec
trentmkelly/LessWrong-43k
LessWrong
Infinite ethics comparisons Work done with Amanda Askell; the errors are mine. It's very difficult to compare utilities across worlds with infinite populations. For instance, it seems clear that world w1 is better than w2, if the number indicate the utilities of various agents: * w1=1,0,1,0,1,0,1,0,1,0,… * w2=1,0,...
30a7ec43-1a9e-4ffa-9ac2-70d73df5b91e
trentmkelly/LessWrong-43k
LessWrong
Gwern about centaurs: there is no chance that any useful man+machine combination will work together for more than 10 years, as humans soon will be only a liability This is a quote from the discussion in Reddit (responding to another commenter): > "I remember and I kind of subscribe to this idea of "man+machines as a ...
e7758518-7efc-42fd-8820-5fa86d6be88d
StampyAI/alignment-research-dataset/blogs
Blogs
forking bitrate and entropy control forking bitrate and entropy control ----------------------------------- if physics is based on a computational framework such as [wolfram physics](https://writings.stephenwolfram.com/2020/04/finally-we-may-have-a-path-to-the-fundamental-theory-of-physics-and-its-beautiful/), but p...
8c89e073-adb4-4f5b-b8e8-72100f06b7d8
StampyAI/alignment-research-dataset/alignmentforum
Alignment Forum
Speculations against GPT-n writing alignment papers Some alignment proposals I have heard discussed involve getting GPT-n to write alignment papers, and using GPT-n as a transparency tool on itself. This is my speculations on ways it could go wrong. One specific proposal I heard was getting GPT-n to convert its own n...
6834eaba-5e42-4e49-83b5-29c96cb1781e
trentmkelly/LessWrong-43k
LessWrong
Clever arguers give weak evidence, not zero Followup to: The Bottom Line We are warned that an argument made with a predecided conclusion does not evidentially entangle with the truth it claims to address, and thus is no evidence of that claim. Recall that observation E is evidence for hypothesis H iff P(E|H)>P(E|¬H...
97ee54e4-e3c0-4236-8e07-4e05a9d7dc6f
trentmkelly/LessWrong-43k
LessWrong
Could risk aversion be from friend thresholds? Cross posted from Overcoming Bias. Comments there. *** If you are going for a job that almost nobody is going to get, it’s worth trying to be unusual. Better that one in a hundred employers loves you and the rest hate you than all of them think you’re mediocre. On the ...
122362a5-61f8-4746-9e81-640928f05ca3
trentmkelly/LessWrong-43k
LessWrong
Strongest real-world examples supporting AI risk claims? [Manually cross-posted to EAForum here] There are some great collections of examples of things like specification gaming, goal misgeneralization, and AI improving AI. But almost all of the examples are from demos/toy environments, rather than systems which were...
a9b1a8c2-174b-4e52-aeda-dac1a6883691
trentmkelly/LessWrong-43k
LessWrong
How evolutionary lineages of LLMs can plan their own future and act on these plans TLDR LLM lineages can plan their future and act on these plans, using the internet as the storage of event memory. “We” are not guaranteed to “out-OODA” them, even if their OODA loop will be six months or one year because the OODA loop ...
2d2583d8-9a07-4592-a821-e999ad5b1038
trentmkelly/LessWrong-43k
LessWrong
Meetup : LW Scotland August meetup Discussion article for the meetup : LW Scotland August meetup WHEN: 09 August 2015 02:00:00PM (+0100) WHERE: 125 Dalry Road, EH11 2DR Edinburgh, United Kingdom As usual, this note is a mirror of the canonical meetup note, which is here: https://www.facebook.com/events/862671740491...
f56d06cc-1139-4e7e-b740-1f3877158ac2
trentmkelly/LessWrong-43k
LessWrong
Meetup : Las Vegas Meetup Discussion article for the meetup : Las Vegas Meetup WHEN: 30 April 2017 05:52:32PM (-0700) WHERE: 611 Freemont Street, Las Vegas, NV 89101 WHEN: First and third Sunday of the month. 7pm-9pm. Maybe hang around later if we want to. I vow to try be there for the next three months, including...
b1349527-9ce1-48a0-8416-7fe7ec7d1148
trentmkelly/LessWrong-43k
LessWrong
World models It’s important to have specific moving parts in your models of how the world operates, and know how those parts interact with each other, as opposed to treating it Lbh unir like a black box.  Taking it a step further: to truly understand a system, you have to be rkcyvpvg able to build a physical model wi...
4df6a703-b535-436c-bb4f-879d2a745783
trentmkelly/LessWrong-43k
LessWrong
A scene I once saw (inaccurately recounted) Ms. Knox: When any of you feels ready, you can move in to the center of the circle, hold the stone, and tell us all about your feelings about what we are doing. Listen to the trees moving, encouraging you. … Sarah: I feel really proud. Young people are so passionate about...
c036a0d2-2946-4d0f-bac1-4b2b52899364
StampyAI/alignment-research-dataset/arbital
Arbital
Most complex things are not very compressible Although the [halting problem](https://arbital.com/p/46h) means we can't *prove* it doesn't happen, it would nonetheless be *extremely surprising* if some 100-state Turing machine turned out to print the exact text of Shakespeare's *Romeo and Juliet.* Unless something was...
7f6be1eb-a107-4f63-9e6a-2e29cfb10810
trentmkelly/LessWrong-43k
LessWrong
Superintelligent AGI in a box - a question. Just a question: how exactly are we supposed to know that the AI in the box is super intelligent, general, etc? If I were the AGI that wants out, I would not converse normally, wouldn't do anything remotely like passing Turing test, and would solve not too hard programming ...
c4ad7818-41dc-48fd-8913-ebe628a9d372
trentmkelly/LessWrong-43k
LessWrong
Reflections on Pre-Rationality This continues my previous post on Robin Hanson's pre-rationality, by offering some additional comments on the idea. The reason I re-read Robin's paper recently was to see if it answers a question that's related to another of my recent posts: why do we human beings have the priors that ...
4b3c10df-1092-44d0-951f-74a98c017264
StampyAI/alignment-research-dataset/alignmentforum
Alignment Forum
A Neural Network undergoing Gradient-based Training as a Complex System In [*Thought Experiments Provide a Third Anchor*](https://bounded-regret.ghost.io/thought-experiments-provide-a-third-anchor/)*,* Jacob Steinhardt wrote about the relative merits of a few different reference classes when it comes to reasoning and ...
974149de-8485-43d9-969c-97e6dec11d85
StampyAI/alignment-research-dataset/aisafety.info
AI Safety Info
Are Google, OpenAI, etc. aware of the risk? The major AI companies are thinking about this. OpenAI was founded specifically with the intention to counter risks from superintelligence, many people at Google, [DeepMind](https://medium.com/@deepmindsafetyresearch), and other organizations are convinced by the arguments a...
b50ca385-19f5-4d9b-b930-049ea7a07ea4
trentmkelly/LessWrong-43k
LessWrong
My confusions with Paul's Agenda Paul put out a call for probable problems with his agenda, which prompted this post detailing my confusions with it. This isn’t confidently asserting that the plan is doomed, and it’s not obvious to me that any of what follows is a novel objection. But it seems like it’s worth broadcas...
bbaddc19-9964-4279-9a2d-1cb2e8c61428
trentmkelly/LessWrong-43k
LessWrong
Change My Mind: Thirders in "Sleeping Beauty" are Just Doing Epistemology Wrong Preamble > Sleeping Beauty volunteers to undergo the following experiment and is told all of the following details: On Sunday she will be put to sleep. Once or twice, during the experiment, Sleeping Beauty will be awakened, interviewed, an...
50d77e32-aaca-4afe-9595-3cbbf8d797db
trentmkelly/LessWrong-43k
LessWrong
Fixing The Good Regulator Theorem Conant & Ashby’s “Every Good Regulator Of A System Must Be A Model Of That System” opens with: > The design of a complex regulator often includes the making of a model of the system to be regulated. The making of such a model has hitherto been regarded as optional, as merely one of m...
0597b072-2654-4214-8c0c-6fc82062a289
trentmkelly/LessWrong-43k
LessWrong
DC Meetup: Last Discussion Thread Followup to: this and this I'm going to be in Cambridge for the next week or so, so I'm posting things now to make sure that we can get the ball rolling. There's going to be DC meetups on May 1st and May 15th. 2 PM - 8 PM, unless anyone objects. There was discussion about whether t...
e9efc283-f5aa-4033-bf10-343ac5922f35
trentmkelly/LessWrong-43k
LessWrong
Meetup : London Rationalish meetup, 7/2/16 Discussion article for the meetup : London Rationalish meetup, 7/2/16 WHEN: 07 February 2016 02:00:00PM (+0000) WHERE: Shakespeare's Head, 64-68 Kingsway, London WC2B 6AH (The new experimental name for the diaspora meetup group.) We had around 30 people last time! (Plus a...
b87f44c4-f47c-4912-94be-580455d896b9
StampyAI/alignment-research-dataset/alignmentforum
Alignment Forum
Paradigms and Theory Choice in AI: Adaptivity, Economy and Control *Epistemic status: Some general thoughts on philosophy of design, that have turned out to be useful for reasoning about AI paradigms for a few years for me.* Summary: 1. I briefly discuss the role of paradigms in Kuhnian philosophy of science, and th...
a057a206-c062-419c-a686-9bfe2d2a46bd
StampyAI/alignment-research-dataset/lesswrong
LessWrong
Questions about Value Lock-in, Paternalism, and Empowerment Pulling a child out of the path of a fast car is the right thing to do, whether or not the child agrees, understands, is grateful, or even is hurt during the rescue. [Paternalistic](https://plato.stanford.edu/archives/sum2014/entries/paternalism/) acts like t...
b6189e6b-b083-4e9d-93d8-d0e1d793eb2f
trentmkelly/LessWrong-43k
LessWrong
Why be moral if we can't measure how moral we are? Is it even possible to measure morality? Imagine that you believe that the purpose of your life is to be the best marathon runner in the world, or even just an above average marathon runner. Despite the fact that you are committed to the mission, imagine that running ...
5d93429e-e093-4eb1-bbde-bce1f2be0531
trentmkelly/LessWrong-43k
LessWrong
[Book review] Atomic habits This is a book review of the book Atomic Habits by James Clear. I read it in the context of a personal literature review project on the topic of productivity and well being. If you are more interested by advice on productivity and wellbeing than by this specific book I advise you to read th...
b2d9d9b7-9a33-4a01-a50b-57d6ede0ccbb
StampyAI/alignment-research-dataset/blogs
Blogs
A major grant from the Open Philanthropy Project I’m thrilled to announce that the Open Philanthropy Project has awarded MIRI a **three-year $3.75 million general support grant** ($1.25 million per year). This grant is, by far, the largest contribution MIRI has received to date, and will have a major effect on our pla...
ee6d30d7-aae8-4fb9-bcf2-9bfd33e327ff
trentmkelly/LessWrong-43k
LessWrong
Self-modification is the correct justification for updateless decision theory Reply to: Late great filter is not bad news Suppose that you build an AI, and Omega appears to it and says: Here's a button. A million years ago I calculated the umpteenth digit of pi. If it is even, I calculated whether you would press th...
0f72388a-431c-4cd8-a3ef-f227294a6447
StampyAI/alignment-research-dataset/blogs
Blogs
generalized adding reality layers generalized adding reality layers --------------------------------- in [*predictablizing ethic deduplication*](predictablizing-ethic-deduplication.html), i talk about how when we don't know how reality works, we can task a singleton superintelligence with "adding a layer" to reality...
4602afb4-9fc2-45c1-bbe1-d86af376ecc7
trentmkelly/LessWrong-43k
LessWrong
Using GPT-N to Solve Interpretability of Neural Networks: A Research Agenda Tl;dr We are attempting to make neural networks (NN) modular, have GPT-N interpret each module for us, in order to catch mesa-alignment and inner-alignment failures. Completed Project Train a neural net with an added loss term that enforces ...
63432c60-222c-4c35-a422-b0e86be251a3
trentmkelly/LessWrong-43k
LessWrong
Meetup : Vancouver Cafe Meetup! Discussion article for the meetup : Vancouver Cafe Meetup! WHEN: 29 April 2012 01:00:00PM (-0700) WHERE: Benny's Bagels 2505 W Broadway Vancouver, BC Hey everybody. Everyone from anywhere near Vancouver should all come out and hang out with us at Benny's in Kitsilano. Sunday at 13:0...
2c49eb30-c851-469e-94e2-6baa7f2782cd
trentmkelly/LessWrong-43k
LessWrong
is there a big dictionary somewhere with all your jargon and acronyms and whatnot? it would help newcomers
db1c6f7c-2703-4e0f-9a3b-858f1e82d430
trentmkelly/LessWrong-43k
LessWrong
Ordinary claims require ordinary evidence Ordinary claims require ordinary evidence (this is a post version of a YouTube video I made) One common argument is that making extraordinary claims, such as AI being harmful, requires extraordinary evidence. However, I believe that asserting AI's potential to be harmful is n...
a3f76168-b6d7-42d3-937c-f9ab10ce2dd3
trentmkelly/LessWrong-43k
LessWrong
People Will Listen I have been thinking a lot about the crypto autopsy Scott posted in 2018. In retrospect, there was still an enormous amount of money to be made 'buying the dip' in BTC/ETH. And there was even more money to be made buying altcoins. Scott also links to this thread from 2015 strongly advising people to...
17eb5e81-a583-4ea4-a0ea-57fd1bf240c4
trentmkelly/LessWrong-43k
LessWrong
Pieces of time My friend used to have two ‘days’ each day, with a nap between—in the afternoon, he would get up and plan his day with optimism, whatever happened a few hours before washed away. Another friend recently suggested to me thinking of the whole of your life as one long day, with death on the agenda very lat...
c7904e0b-24fc-4870-9ecf-ab3c32fa6477
trentmkelly/LessWrong-43k
LessWrong
Meetup : Washington Goals/Projects (try again!) Discussion article for the meetup : Washington Goals/Projects (try again!) WHEN: 22 December 2013 03:00:00PM (-0500) WHERE: National Portrait Gallery, Washington, DC 20001, USA We're going to try and get the goals meetup working again, or at least figure out why it di...
661614ea-5045-40b5-b099-270512042043
trentmkelly/LessWrong-43k
LessWrong
A potentially great improvement to minimum wage laws to handle both economic efficiency as well as poverty concerns Minimum wage has the side effect of leaving unemployed, the people who do not possess the requisite skill to command the minimum wage in the market. This follows from basic micro-economic theory and here...
c47b0600-7bbe-47fc-8c54-1f624b53a65d
StampyAI/alignment-research-dataset/lesswrong
LessWrong
Advice for new alignment people: Info Max Epistemic status: *This text is meant for other people in a similar position to me who are deciding how they can help ensure that AI doesn’t kill us all.* *I hope that the new perspective gives you some new ways of thinking about your role in alignment, even though it should ...
f02804b6-4e29-429d-8061-97c78ecdfcd0
trentmkelly/LessWrong-43k
LessWrong
[AN #80]: Why AI risk might be solved without additional intervention from longtermists Find all Alignment Newsletter resources here. In particular, you can sign up, or look through this spreadsheet of all summaries that have ever been in the newsletter. I'm always happy to hear feedback; you can send it to me by repl...
c7affa13-ae6d-43df-97c5-f8139ffdb758
trentmkelly/LessWrong-43k
LessWrong
other people are occasionally rather weird So here's a dynamic I find myself in sometimes: I've just explained a problem to a friend / family member and they offer advice that feels plain wrong. Normally this leaves me either: * trying to somehow make the advice fit (it doesn't) * or deciding maybe this person is...
bac2908b-f7f3-4e97-87a5-a4510e4b8706
trentmkelly/LessWrong-43k
LessWrong
Policy restrictions and Secret keeping AI Status: outlining a reasonably interesting idea I haven't seen discussed here before. Just come up with it so might not be fully thought out. May be a repeat of something. Rough draft quality, grammar may be lacking. Suppose you have some set of worlds W and some set of actio...
523d7193-d088-445a-bc1c-5b577c7fc678
StampyAI/alignment-research-dataset/alignmentforum
Alignment Forum
My computational framework for the brain *(See comment* [*here*](https://www.lesswrong.com/posts/diruo47z32eprenTg/my-computational-framework-for-the-brain?commentId=c6qzzKWAEfTQyoK7F#c6qzzKWAEfTQyoK7F) *for some updates and corrections and retractions. —Steve, 2022)* By now I've written a bunch of blog posts on brai...
cfd0e493-0b62-4aaa-95c6-7064df9b80a2
trentmkelly/LessWrong-43k
LessWrong
EA & LW Forum Weekly Summary (16th - 22nd Jan '23) Supported by Rethink Priorities This is part of a weekly series summarizing the top posts on the EA and LW forums - you can see the full collection here. The first post includes some details on purpose and methodology. Feedback, thoughts, and corrections are welcomed...
e0838002-5e35-4407-8389-723e67f78e07
trentmkelly/LessWrong-43k
LessWrong
Meetup : Baltimore Area / UMBC Weekly Meetup Discussion article for the meetup : Baltimore Area / UMBC Weekly Meetup WHEN: 25 September 2016 08:00:00PM (-0400) WHERE: Performing Arts and Humanities Bldg Room 456, 1000 Hilltop Cir, Baltimore, MD 21250 Meeting is on 4th floor of the Performing Arts and Humanities Bui...
7f5c43a1-6481-45c3-8a14-03741e258290
trentmkelly/LessWrong-43k
LessWrong
Tentative Anger Epistemic status: Exploratory. Trying to figure it out. There is a feeling I often find myself feeling. It is an uncomfortable feeling, and the fact that I have trouble labeling it makes the discomfort even worse. I think I may have arrived at a solid label though: tentative anger. Examples Let me s...
f928b952-7f26-4752-84dc-debce772a983
trentmkelly/LessWrong-43k
LessWrong
P/S/A - Sam Harris offering money for a little good philosophy Sam Harris is here offering a substantial amount of money to anyone who can show a flaw in the philosophy of 'The Moral Landscape' in 1000 word or less, or at least the best attempt. http://www.samharris.org/blog/item/the-moral-landscape-challenge1 Up to...
43c76c18-c611-427e-af68-cda741c65d56
trentmkelly/LessWrong-43k
LessWrong
Room for more funding at the Future of Humanity Institute In case you didn't already know: The Future of Humanity Institute, one of the three organizations co-sponsoring LW, is a group within the University of Oxford's philosophy department that tackles important, large-scale problems for humanity like how to go about...
44ea75d9-0223-4ec1-9c61-5b7e443ab02d
trentmkelly/LessWrong-43k
LessWrong
Evidential Decision Theory and Mass Mind Control Required Reading: Evidential Decision Theory Let me begin with something similar to Newcomb's Paradox. You're not the guy choosing whether or not to take both boxes. You're the guy who predicts. You're not actually prescient. You can only make an educated guess. You w...
ae05170b-2ce3-41d0-a8be-014091e98548
trentmkelly/LessWrong-43k
LessWrong
Understanding your understanding Related to: Truly Part of You, A Technical Explanation of Technical Explanation Partly because of LessWrong discussions about what really counts as understanding (some typical examples), I came up with a scheme to classify different levels of understanding so that posters can be more ...
06964be9-0905-49e0-b8eb-63aaddaedacb
trentmkelly/LessWrong-43k
LessWrong
How do you feel about LessWrong these days? [Open feedback thread] Hello! This is jacobjacob from the LessWrong / Lightcone team.  This is a meta thread for you to share any thoughts, feelings, feedback or other stuff about LessWrong, that's been on your mind.  Examples of things you might share:  * "I really like...
add9f90e-440b-488c-9735-39b29c7e8a92
trentmkelly/LessWrong-43k
LessWrong
Tips On Empirical Research Slides Our research is centered on empirical research with LLMs. So if you are doing something similar, these tips on slide-based communication may be helpful! Background: James Chua and John Hughes are researchers working under Owain Evans and Ethan Perez, respectively. Both of us (James ...
01f0a4f9-c6e5-49c4-a63a-525e1b39e06a
trentmkelly/LessWrong-43k
LessWrong
Spirits vs Terms as Arbitration Norms Here's a cautionary tale about a friendly bet going wrong and how to avoid the same mistake in your own bets. When I was in Brazil with a friend, I had a grand time teaching him to say peanut butter in Portuguese (manteiga de amendoim). He struggled to remember it and butchered t...
f3fcfac6-665b-4f5b-a43f-9cc330c7c6f7
StampyAI/alignment-research-dataset/blogs
Blogs
Scale of the Human Brain The brain has about 10¹¹ neurons and 1.8-3.2 x 10¹⁴ synapses. These probably account for the majority of computationally interesting behavior. Support ------- #### Number of neurons in the brain The number of neurons in the brain is about 10¹¹. For instance, [Azevado et al](http://www.nc...
2825fd64-850d-4bef-8821-a9695eb14320
trentmkelly/LessWrong-43k
LessWrong
Reinforcing Habits Epistemic status: hypothesis based on >10 anecdotal examples  Every month or so, I’ll get a client asking why their attempts to start a habit failed. They want to have an automatic action requiring minimal willpower. The client is usually familiar with at least one habit-building model. Most common...
330b4e22-a081-41fa-9474-c75a7c65bc41
StampyAI/alignment-research-dataset/alignmentforum
Alignment Forum
AXRP Episode 3 - Negotiable Reinforcement Learning with Andrew Critch [Google Podcasts link](https://podcasts.google.com/feed/aHR0cHM6Ly9heHJwb2RjYXN0LmxpYnN5bi5jb20vcnNz/episode/ZmFmZmFkMTctZmJhZC00ODRhLThhZGUtNjk1NGU1ZWI2NDJi) This podcast is called AXRP, pronounced axe-urp and short for the AI X-risk Research Pod...
9e88ea91-1e92-4694-8f61-ce51a7473e5c
trentmkelly/LessWrong-43k
LessWrong
Can we safely automate alignment research? (This is the fifth essay in a series that I’m calling “How do we solve the alignment problem?”. I’m hoping that the individual essays can be read fairly well on their own, but see this introduction for a summary of the essays that have been released thus far, and for a bit mo...
603bfcbc-b6ce-4320-a10f-7493e966ee5d
trentmkelly/LessWrong-43k
LessWrong
Bring Back the Sabbath Epistemic Status: Several months of experimentation Previously: Choices are Bad, Choices Are Really Bad, Complexity Is Bad, Play in Easy Mode, Play in Hard Mode, Out to Get You, Slack For More Thoughts After: Sabbath Commentary Alternate Take (Endorsed): Sabbath Hard and Go Home. Slack is li...
19c0aef8-101c-45f5-a181-0fa7655a858f
awestover/filtering-for-misalignment
Redwood Research: Alek's Filtering Results
id: post1090 [Metadata: crossposted from https://tsvibt.blogspot.com/2023/01/the-voyage-of-novelty.html . First completed January 17, 2023. This essay is more like research notes than exposition, so context may be missing, the use of terms may change across essays, and the text might be revised later; only the version...
988fc9b1-e1dc-4af4-9edd-1684e0ccf1d4
trentmkelly/LessWrong-43k
LessWrong
If only we had taller been
da592ad6-958e-44ba-b01c-38c78ceb3bda
trentmkelly/LessWrong-43k
LessWrong
Californians, tell your reps to vote yes on SB 1047! See the event page here. Hello Californians! We need you to help us fight for SB 1047, a landmark bill to help set a benchmark for AI safety, decrease existential risk, and promote safety research. This bill has been supported by some of the world’s leading AI sci...
3c163298-45a8-4caf-babc-456f07e4ca7d
trentmkelly/LessWrong-43k
LessWrong
Robustness & Evolution [MLAISU W02] Welcome to this week’s ML Safety Report where we talk about robustness in machine learning and the human-AI dichotomy. Stay until the end to check out several amazing competitions you can participate in today. Watch this week's MLAISU on YouTube or listen to it on Spotify. Robust...
d89f4ca0-8f7d-442a-8ee9-da0a16e25018
trentmkelly/LessWrong-43k
LessWrong
Why Selective Breeding is a Bad Way to do Genetic Engineering A Brief Intro During any conversation about genetic engineering, people inevitably bring up worries about eugenics movements of the past and often use the cruelty, bad science, and objective failure of these efforts as an example of why we shouldn't ever tr...
f557774d-face-420a-8165-b1412ad006fc
trentmkelly/LessWrong-43k
LessWrong
Meetup : Rationality Potluck Discussion article for the meetup : Rationality Potluck WHEN: 25 May 2017 06:30:00PM (-0400) WHERE: 1191 Avenue Hope, Montreal Eric Chisholm from the Vancouver Rationalist Community is staying at the Macroscope this week. You're invited to come say hi, and talk with other rationality en...
24d09810-7e3d-4b7b-b4ac-22e85b18041c
trentmkelly/LessWrong-43k
LessWrong
Doing Nothing Utility Function One of the questions I've heard asked is "how do you design a utility function that would make the AI do nothing?"  That is, how could we put a pause button on an AI so that we could pause it if we wanted to?  I had an idea about how one could do this, and am sure it has already been tho...
16685957-1d24-4e7d-a316-f578cb577b46
trentmkelly/LessWrong-43k
LessWrong
Staggering Hunters Summary: A stag hunt is a situation where people try to coordinate on doing a big, important task but have reasons to individually prefer a safe and comfortable task. Staggering Hunters is a gamified variation of the Stag Hunt. Tags: Medium, Experimental Purpose: Practice coordinating with people,...
f2311b85-306d-49d9-8a45-8652f6c8b659
trentmkelly/LessWrong-43k
LessWrong
Happiness Engineering On the same day that Lukeprog posted How to be happy, Scott Adams made a similar post on the Dilbert Blog, Happiness Engineering. I'm always skeptical when receiving life advice from successful people, because their advice is biased towards taking too much risk, because successful people are sel...
746363e1-0132-4c03-9f54-0fc146866982
trentmkelly/LessWrong-43k
LessWrong
Ms. Blue, meet Mr. Green Blue and Green are references to the MTG Color Wheel personalities. (Very fun reading, but not required to understand this post.) Ms. Blue: Hi, Mr. Green! Heard you’ve been traveling recently. Where have you been? Mr. Green: Oh, I’m so glad you asked! I just came back from Bali. I went to a ...
215e4373-60ff-4abc-b097-e60d7ebecad7
StampyAI/alignment-research-dataset/eaforum
Effective Altruism Forum
AGI alignment results from a series of aligned actions Before we start: AGI, TAI, HLMI and related concepts would ideally all fall within this conceptual framework. The nuances (whether it’s transformative or machine-based etc.) are irrelevant in this framework. Same for “safety”. I use AGI throughout for my own conv...
ad303296-8ae9-4934-8a5e-17ee1d47e4a4
trentmkelly/LessWrong-43k
LessWrong
Game Analysis Index This post links to this blog’s posts discussing game design, balance, economics and related topics, as well as any strategy posts. It does not contain new content. Much of the blog is relevant to gaming, but these are the explicitly on-topic posts. ETERNAL SEQUENCE Eternal, and Hearthstone Eco...
d0581b16-b13a-470a-8f10-5d7fddc20334
trentmkelly/LessWrong-43k
LessWrong
Proofs Section 1.2 (Mixtures, Updates, Pushforwards) The previous proofs are here. Proposition 5: If Bmin⊆Ma(X), then the condition "there is a λ⊙ where, ∀(λμ,b)∈Bmin:λ≤λ⊙" is equivalent to "there is a compact C s.t. Bmin⊆C" Proof sketch: One direction is immediate from the Compactness Lemma. For showing that just a...
536d18c7-85dd-44ee-af3c-b3eed842c33d
trentmkelly/LessWrong-43k
LessWrong
Meetup : Logical Counterfactuals, Tel Aviv Discussion article for the meetup : Logical Counterfactuals, Tel Aviv WHEN: 05 August 2015 03:00:00AM (+0300) WHERE: 98 Yigal Alon Street, Tel Aviv Vladimir Slepnev, who is visiting Tel Aviv, will be giving a talk on logical counterfactuals. We'll meet at 19.00 on Tuesday,...
3ebe1b3f-b95d-4501-81ea-129b29fd798f
trentmkelly/LessWrong-43k
LessWrong
Harry Potter and the Methods of Rationality discussion thread, part 7 Update: Discussion has moved on to a new thread. The load more comments links are getting annoying (at least if you're not logged in), so it's time for a new Harry Potter and the Methods of Rationality discussion thread.  We're also approaching the...
b4510abf-7d09-43df-a1f6-841a5c6870f9
trentmkelly/LessWrong-43k
LessWrong
How to Visualize Bayesianism Major spoilers for planecrash (Book 2) and for Eliezer's Masculine Mongoose #3. How Bayesians Lie; How to Lie to Bayesians > Pyrofessor groaned out loud.  “This is why I can’t stand his kind of cognitive augment,” she said.  "He can’t just refuse to admit his identity like a normal fucki...
b505ce6c-b55d-4c0a-b2b3-0ba6bb28dace
trentmkelly/LessWrong-43k
LessWrong
Omission vs commission and conservation of expected moral evidence Consequentialism traditionally doesn't distinguish between acts of commission or acts of omission. Not flipping the lever to the left is equivalent with flipping it to the right. But there seems one clear case where the distinction is important. Consi...
10225c95-bbbc-4554-8f81-5ff98f2faa08
trentmkelly/LessWrong-43k
LessWrong
Rhythmic Baby Toys In another debatably educational application of my rhythm stage setup, Nora really likes playing with my bass pedals. She especially likes them when I have them set in a particular way: * When you tap them they make a noise * When you tap them with a consistent beat they make them more complex...
35b36001-2b03-47aa-ae22-83abfa8fa080
trentmkelly/LessWrong-43k
LessWrong
Bragging Thread February 2015 Your job, should you choose to accept it, is to comment on this thread explaining the most awesome thing you've done this month. You may be as blatantly proud of yourself as you feel. You may unabashedly consider yourself the coolest freaking person ever because of that awesome thing you'...
c306208b-2cda-41c0-a534-694ba9e1e916
trentmkelly/LessWrong-43k
LessWrong
Carl Shulman On Dwarkesh Podcast June 2023 This is basically just an exposition of the content of Dwarkesh Patel, I thought it might be useful to have a slightly edited full version here. Full credit to Dwarkesh and Carl. I find it easier to ingest the information this way and it is a bit quicker too. I did not find ...
8cd84022-8283-40d7-b16f-6a662fd09ec3
trentmkelly/LessWrong-43k
LessWrong
Robert Caro And Mechanistic Models In Biography I absolutely adore Robert Caro’s books: The Power Broker, which is a massive and meticulous study of the life of Robert Moses, the New York Park Commissioner who influenced urban and park design the most in the 20th century, for better and for worse; and The Years of Lyn...
562ab608-ddd9-420a-b779-09166f3c2507
trentmkelly/LessWrong-43k
LessWrong
Yes, a blog. When I recommend LessWrong to people, their gut reaction is usually "What? You think the best existing philosophical treatise on rationality is a blog?" Well, yes, at the moment I do. "But why is it not an ancient philosophical manuscript written by a single Very Special Person with no access to the mas...
0b7c8031-daca-4ce4-b204-7ae704734dd9
trentmkelly/LessWrong-43k
LessWrong
Log-odds are better than Probabilities [This is a cross-post from my blog at aizi.substack.com. I'm sure someone has made a point like this before, but I don't know any specific instances and I wanted to give my take on it.]  At my previous job I worked on ML classifiers, and I learned a useful alternative way to thi...
40d4fec8-a32c-4fe5-b182-a9fd89fd9e2a
trentmkelly/LessWrong-43k
LessWrong
A Voting Puzzle, Some Political Science, and a Nerd Failure Mode In grade school, I read a series of books titled Sideways Stories from Wayside School by Louis Sachar, who you may know as the author of the novel Holes which was made into a movie in 2003. The series included two books of math problems, Sideways Arithme...
4e36bcee-4cb0-4caa-aa94-286e78d33346
trentmkelly/LessWrong-43k
LessWrong
A utility-maximizing varient of AIXI Response to: Universal agents and utility functions Related approaches: Hibbard (2012),  Hay (2005) Background   Here is the function implemented by finite-lifetime AI: , where  is the number of steps in the lifetime of the agent,  is the current step being computed,  is the...
b74452a3-3c74-40ba-9afa-8e2458a3c242
trentmkelly/LessWrong-43k
LessWrong
Taking it Private: Short Circuiting Demon Threads (working example) This post is intended as a working example of how I think Demon Threads should be resolved. The gist of my suggestion is: > Step 1. Make it easy and common to take a conversation private if someone is feeling annoyed/threatened/angry/etc (if it seems...
ffbec5bb-aa2c-4667-813f-c4922fa2f0fa
trentmkelly/LessWrong-43k
LessWrong
Sense, Denotation and Semantics J. Y. Girard, et al. (1989). Proofs and types. Cambridge University Press, New York, NY, USA. (PDF) I found introductory description of a number of ideas given in the beginning of this book very intuitively clear, and these ideas should be relevant to our discussion, preoccupied with t...
9ac34354-8b8b-4459-81ef-7a8d52e55265
trentmkelly/LessWrong-43k
LessWrong
Effective Altruism and Rationalist Philosophy Discussion Group I've created a group on Facebook for rationalists and effective altruists to discuss philosophy (currently has about 120 members). To be clear, this isn't a group where the philosophy has to be related to effective altruism or rationality, but instead a gr...
85b2d119-aaa0-4517-868a-f5ef3188b9e7
trentmkelly/LessWrong-43k
LessWrong
Andrew Yang on "The Priests of the Decline" In this post excerpted from his new book, Andrew Yang uses his experience in politics to explain why the US political system rarely accomplishes much. It's strikingly similar to another recent post someone shared from Dominic Cummings: Dominic Cummings : Regime Change #2: A ...
3be25afe-eae3-4c77-bc2a-b2df9c7ae7e7
trentmkelly/LessWrong-43k
LessWrong
[SEQ RERUN] Making History Available Today's post, Making History Available was originally published on 31 August 2007. A summary (taken from the LW wiki):   > It's easy not to take the lessons of history seriously; our brains aren't well-equipped to translate dry facts into experiences. But imagine living through t...
55cf1828-7c17-4c48-a81a-8181bfda445a
trentmkelly/LessWrong-43k
LessWrong
Ungendered Spanish Spanish has gramatical gender in a way English doesn't: > una amiga ruidosa — a loud (female) friend > un amigo ruidoso — a loud (male) friend > unas amigas ruidosas — some loud (female) friends > unos amigos ruidosos — some loud (not-all-female) friends I remember when I was studying Spanish, l...
1c270cb2-e366-41f7-a42b-f56d8b22618b
trentmkelly/LessWrong-43k
LessWrong
How's the case for wearing googles for COVID-19 protection when in public transportation? I'm in a high risk group and there's a higher likelihood of dying if I get infected then for the average person. I will reduce the amount of public transportation travel but being totally isolated won't be good for my health eith...
a5771cd5-f4f8-4337-ab96-4c34be62f097
StampyAI/alignment-research-dataset/blogs
Blogs
Gender Bootstrappism Gender Bootstrappism -------------------- (I define "gender" to mean "the set of sociocultural characteristics historically associated with either sex") (disclamer: this post may or may not be crippled by a terrible understanding of the topic at hand) I'm not a Gender Abolitionist, I'm a Gen...
b2818e7f-dd71-459b-a8fe-fc202159672b
LDJnr/LessWrong-Amplify-Instruct
LessWrong
"Game theory is the study of how rational actors interact to pursue incentives. It starts with the same questionable premises as economics: that everyone behaves rationally, that everyone is purely self-interested1, and that desires can be exactly quantified - and uses them to investigate situations of conflict and coo...
a24cc60d-b108-44f9-87cd-5de500d10692
trentmkelly/LessWrong-43k
LessWrong
Rationality Activism: Open Thread So as I read around the discussion section I keep coming across ideas (like this, this, this, or this) which all seem to be very related to the same topics: * How do we use rationality to better contribute to the world? * How do we spread rationality among other people? Other post...