id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
8c47f0b0-7424-45cb-bbf9-5e9a8c9f1d4f | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post472
[Thanks to Aryan Bhatt, Ansh Radhakrishnan, Adam Kaufman, Vivek Hebbar, Hanna Gabor, Justis Mills, Aaron Scher, Max Nadeau, Ryan Greenblatt, Peter Barnett, Fabien Roger, and various people at a presentation of these arguments for comments. These ideas aren’t very original to me; many of the examples of thr... |
b332b52d-de88-4dad-99a5-c457930a9680 | trentmkelly/LessWrong-43k | LessWrong | Covid 3/4: Declare Victory and Leave Home
Health officials look on in horror as individuals both vaccinated and unvaccinated, and state and local governments, realize life exists and people can choose to live it.
This is exactly what I was worried about back in December when I wrote We’re F***ed, It’s Over. The cont... |
0b711462-4891-49de-ad0c-7b41fc42997b | trentmkelly/LessWrong-43k | LessWrong | Announcing: The great bridge
Original post: http://bearlamp.com.au/announcing-the-great-bridge-between-communities/
----------------------------------------
In the deep dark lurks of the internet, several proactive lesswrong and diaspora leaders have been meeting each day. If we could have cloaks and silly hats; we... |
d3858a66-bb76-4eb1-b7f4-0c0e62b8beb1 | trentmkelly/LessWrong-43k | LessWrong | How bad is chlorinated water?
chlorine disinfection
Today, most water distributed to people for drinking is chlorinated. Bleach is also widely used for disinfection of surfaces.
The exact ways chlorine kills microbes aren't fully understood, but the main reasons are believed to be:
* oxidation of thiols of enzymes
... |
cee815eb-eead-4395-9dbb-a409ba492153 | trentmkelly/LessWrong-43k | LessWrong | Evolved Bayesians will be biased
I have a small theory which strongly implies that getting less biased is likely to make "winning" more difficult.
Imagine some sort of evolving agents that follow vaguely Bayesianish logic. They don't have infinite resources, so they use a lot of heuristics, not direct Bayes rule with... |
d8594891-26aa-443c-9139-df98953d56b4 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Measuring Non-Probabilistic Uncertainty: A cognitive, logical and computational assessment of known and unknown unknowns
MEASUR ING NON -PROBABILISTIC UNCERTAINTY
A cognitive, logical and computational assessment of known and unknown unknowns
Florian Ellsaesser
Frankfurt School of Finance & Management... |
dc3de97a-931b-4fec-b10d-831452fbb432 | trentmkelly/LessWrong-43k | LessWrong | Evidence For Simulation
The recent article on overcomingbias suggesting the Fermi paradox might be evidence our universe is indeed a simulation prompted me to wonder how one would go about gathering evidence for or against the hypothesis that we are living in a simulation. The Fermi paradox isn't very good evidence b... |
14c51974-0632-4e69-a2e7-a77cd98f9619 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Providing Actionable Feedback in Hiring Marketplaces using Generative Adversarial Networks
1 Introduction
---------------
The prevalence of machine learning (ML) based predictive models has increased throughout various industries including recruitment platforms and marketplaces. Providing model interpretability and... |
f363a927-3912-431e-8fcc-ee5367505bda | trentmkelly/LessWrong-43k | LessWrong | Invisible Choices, Made by Default
There are two popular language learning software platforms: Anki and Duolingo. Anki is hard, free and effective. Duolingo is easy, commercial and ineffective.
The number of Duolingo users far outstrips the number of Anki users. Duolingo has 8 million downloads on the Play Store. Ank... |
a55776dd-cdc1-4a14-8dd5-802ce5f15e60 | trentmkelly/LessWrong-43k | LessWrong | A Return to Discussion
Epistemic Status: Casual
It’s taken me a long time to fully acknowledge this, but people who “come from the internet” are no longer a minority subculture. Senators tweet and suburban moms post Minion memes. Which means that talking about trends in how people socialize on the internet is not a ... |
068f17f3-44b0-482e-8118-23d7d63ba510 | trentmkelly/LessWrong-43k | LessWrong | Concrete benefits of making predictions
Your mind is a prediction machine, constantly trying to anticipate the world around you and altering its forecasts based on new information. It’s always doing this as a background process. But what would happen if you deliberately trained this skill? Could you get better at pred... |
3d6090ba-59e1-4e1c-ab53-dc958137e900 | trentmkelly/LessWrong-43k | LessWrong | Why I Believe LLMs Do Not Have Human-like Emotions
[EDIT: I don't know exactly why this received so many downvotes - whether it was my tone or arguments or both - but I accept that this was not, in the end, a strong post. I am a new writer here and I am still figuring out how to improve my argumentation.
That said, i... |
3d5a406a-a472-4af6-916e-6c783af0240f | trentmkelly/LessWrong-43k | LessWrong | A total life checklist
I came up with an idea today: I think it would be useful to have a list of everything that a typical person ought to do. After all, there is quite a lot of stuff that a typical person ought to do; how else is a person supposed to remember it all?
Here's what I've come up with so far:
Health
... |
ce099aa4-e6c9-4808-82fa-8ae1edbf3a3e | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Estimating the Current and Future Number of AI Safety Researchers
Summary
=======
I estimate that there are about **300** full-time technical AI safety researchers, **100** full-time non-technical AI safety researchers, and **400** AI safety researchers in total today. I also show that the number of technical AI safe... |
50727eec-9225-4cba-9d0e-96fd17686f57 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "LessWrong is looking to hire an additional programmer. Ideally, someone with 5+ years experience who is up for a CTO role, or seems like a strong candidate to grow into such a role.We're looking for someone excited about our longterm vision. Over the next several years, we want to build a platform for intellectual pro... |
95212583-4877-40c4-959a-c78714e6aef7 | trentmkelly/LessWrong-43k | LessWrong | Book review: The Importance of What We Care About (Harry G. Frankfurt)
This is more of a summary or paraphrase than a review, really. The Importance of What We Care About is 13 essays by philosopher Harry G. Frankfurt. These are my one-paragraph summaries of each:
1. If you do something because you willed yourself t... |
02e24e9e-ecb4-44cf-b923-11536c715ea1 | trentmkelly/LessWrong-43k | LessWrong | A brief review of China's AI industry and regulations
China has enacted three sets of AI regulations since 2021. I haven’t seen a concise breakdown of their content in one place, and I’ve been researching the legislation for a governance project at Convergence Analysis, so here is my concise summary of what I found. I... |
f2a7ce05-d5d9-4889-a28c-c3a572de6e41 | trentmkelly/LessWrong-43k | LessWrong | Observations about writing and commenting on the internet
I’m not famous or successful, so why should you care what I think? Well, I have some observations about the dynamics of writing on the internet that I think my (even more non-famous and non-successful) self would have benefited from when I started.
Human expe... |
00396d36-d408-4625-97ee-cffaccd9e0a1 | trentmkelly/LessWrong-43k | LessWrong | Leaving beta: Voting on moving to LessWrong.com
It took longer than we hoped, but LessWrong 2.0 is finally ready to come out of beta. As discussed in the original announcement, we’re going to have a vote on whether or not to migrate the new site to the lesswrong.com URL. The vote will be open to people who had 1,000 o... |
ae8f5642-2bfe-4852-957c-56b57a1b35f1 | StampyAI/alignment-research-dataset/blogs | Blogs | Welcome to Intelligence.org
Welcome to the new home for the Machine Intelligence Research Institute (MIRI), formerly called “The Singularity Institute.”
The new design (from Katie Hartman, who also designed the new site for [CFAR](http://appliedrationality.org/)) reflects our recent [shift in focus](https://intellig... |
619c0d51-70f5-4bbf-8b35-7574d56cbb54 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Washington, D.C.: Mini Talks
Discussion article for the meetup : Washington, D.C.: Mini Talks
WHEN: 26 March 2017 03:30:00PM (-0400)
WHERE: Donald W. Reynolds Center for American Art and Portraiture
This week, we will be taking turns delivering short lectures on random topics.
Upcoming meetups:
* Apr. 2... |
3ad7a358-b7a6-4128-9717-e9d993ae88f3 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Towards solving the 7-in-a-row game
I Introduction
---------------
Our paper explores how Proof Number Search (PNS) can be adapted to prove the infinite 7-in-a row game, whose game theoretic value has long been open. This game belongs to the family of (m,n,k)–games – a generalisation of Gomoku and Tic-tac-toe. In t... |
e0a00aea-48d2-4055-8c18-c722b3d65b3c | StampyAI/alignment-research-dataset/lesswrong | LessWrong | AI Takeover Scenario with Scaled LLMs
Introduction
============
In this AI takeover scenario, I tried to start from a few technical assumptions and imagine a specific takeover scenario from human-level AI.
I found this exercise very useful to identify new insights on safety. For instance, I hadn't clearly in mind h... |
32d2629c-47b1-4ca8-bb3c-0a6af718e8d2 | trentmkelly/LessWrong-43k | LessWrong | How not to sort by a complicated frequentist formula
In How Not To Sort By Average Rating, Evan Miller gives two wrong ways to generate an aggregate rating from a collection of positive and negative votes, and one method he thinks is correct. But the "correct" method is complicated, poorly motivated, insufficiently pa... |
3a39f347-5223-4d1a-90eb-8a4ad6ab12f2 | trentmkelly/LessWrong-43k | LessWrong | Alignment allows "nonrobust" decision-influences and doesn't require robust grading
Definition. On how I use words, values are decision-influences (also known as shards). “I value doing well at school” is a short sentence for “in a range of contexts, there exists an influence on my decision-making which upweights acti... |
d09a74c4-efb4-4cf2-b486-57a287679423 | trentmkelly/LessWrong-43k | LessWrong | General v. Specific Planning
Epistemic Status: Everyone already knows about it?
I've been thinking a bit about two different manners of pursuing a goal.
I haven't come up with a catchy jargon for them, and I don't know of any existing catchy jargon for them either. General v. specific planning is pretty bad, but at ... |
7a9abade-f81a-4267-b274-ffbea2cde2bd | trentmkelly/LessWrong-43k | LessWrong | DeepMind’s generalist AI, Gato: A non-technical explainer
Summary
DeepMind’s recent paper, A Generalist Agent, catalyzed a wave of discourse regarding the speed at which current artificial intelligence systems are improving and the risks posed by these increasingly advanced systems. We aim to make Gato accessible to n... |
f2a275ea-cc5c-4c9b-bc94-4d644b9efdc0 | trentmkelly/LessWrong-43k | LessWrong | Stop trying to have "interesting" friends
Originally published on substack: https://eliqian.substack.com/p/stop-trying-to-have-interesting-friends
Within the tech and tech-adjacent circles I’m part of on the internet, a number of essays and tweets have been making the rounds about what makes someone a person you want... |
d67f37e7-8458-4b3f-831d-58882a2b38d9 | StampyAI/alignment-research-dataset/blogs | Blogs | 2013 Summer Matching Challenge!
Thanks to the generosity of several major donors,† every donation to the Machine Intelligence Research Institute made from now until August 15th, 2013 will be matched dollar-for-dollar, up to a total of $200,000!
**[Donate Now!](https://intelligence.org/donate/#donation-methods)**... |
3c0fa6f3-03fc-4999-8b1a-b252cbfba5f3 | trentmkelly/LessWrong-43k | LessWrong | Intelligence–Agency Equivalence ≈ Mass–Energy Equivalence: On Static Nature of Intelligence & Physicalization of Ethics
> Imagine a place that grants any wish, but there is no catch, it shows you all the outcomes, too.
(This is the result of three years of thinking and modeling hyper‑futuristic and current ethical s... |
fa4d4feb-fbe5-4ccf-b1c2-4bffc4282d68 | trentmkelly/LessWrong-43k | LessWrong | What on Earth is a Series I savings bond?
crossposted from: https://blog.rossry.net/series-i/
(Not investment advice, of course.)
Summary: The Series I savings bond is a US government bond offered to US citizens, with purchases limited to $10k per person per year. It pays interest set by a formula based on the offic... |
f92b5940-aa8f-4da8-9207-ebc7617ac527 | trentmkelly/LessWrong-43k | LessWrong | Doomsday, Sampling Assumptions, and Bayes
Overview/TLDR
We discuss the doomsday argument, and look at various approaches taken to analyze observation selection effects, namely SSA and SIA. We conclude that the SSA is unsatisfying, and show that the SIA is isomorphic to a version of bayesianism.
An entity undergoing a... |
e65b66dc-cb5c-4e11-aa6d-b00e3573a50b | trentmkelly/LessWrong-43k | LessWrong | The Paris AI Anti-Safety Summit
It doesn’t look good.
What used to be the AI Safety Summits were perhaps the most promising thing happening towards international coordination for AI Safety.
This one was centrally coordination against AI Safety.
In November 2023, the UK Bletchley Summit on AI Safety set out to let n... |
294c37c2-e479-43ab-bef7-f3e3ad9427c0 | trentmkelly/LessWrong-43k | LessWrong | AIs in virtual worlds: discounted mixed utility/reward
A putative new idea for AI control; index here.
In a previous post on AIs in virtual worlds, I described the idea of a utility function that motivates the AI to do operate in a virtual world with certain goals in mind, but to shutdown immediately if it detects th... |
36320af8-0a8a-4537-a439-fc5a0b56b09f | trentmkelly/LessWrong-43k | LessWrong | Be More Katja
Katja is widely respected amongst the rationalists and, according to Hive, she is one of the most followed/respected EA accounts[1]. But she doesn't give off the same vibe as many impact olympians. She doesn’t have iron self-will, nor does she manage a huge team. She's hasn't got all the facts at her fin... |
9f9a9e54-acd6-4521-a0c0-7c575ea555c7 | trentmkelly/LessWrong-43k | LessWrong | Ideas to Improve LessWrong
This article is something that has been in my head for a while. I hadn't planned on doing a write-up so soon. I wanted to take the time to a) refine my ideas and b) figure out how to express them clearly before posting. But the recent post Less Wrong lacks direction made me change my mind. M... |
90d0a428-33de-464f-891b-5a7c6f5f9fb7 | trentmkelly/LessWrong-43k | LessWrong | Is AI risk assessment too anthropocentric?
Hi everyone,
I've recently discovered lesswrong and love it! So first, let me thank you all for fostering such a wonderful community.
I've been reading a lot of the AI material and I find myself asking a question you all have surely considered, so I wanted to pose it.
If ... |
f84aea55-f09f-49d5-933b-a92819c26d5f | trentmkelly/LessWrong-43k | LessWrong | Bay Area Solstice 2015
The winter solstice marks the darkest day of the year, a time to reflect on the past, present, and future. For several years and in many cities, Rationalists, Humanists, and Transhumanists have celebrated the solstice as a community, forming bonds to aid our work in the world.
Last year, more t... |
a2b78503-48f5-4e6b-a9a9-5a1fc32b36c3 | trentmkelly/LessWrong-43k | LessWrong | [Rough notes, BAIS] Human values and cyclical preferences
epistemic status: Working notes of three different people on the same question, likely useless/incomprehensible to anyone else
The question
How to find the right abstraction level of human values
Problems in over- or underfitting human values:
We can learn ... |
5d499922-4ec2-451a-befa-624643e25523 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Related to: Self-Improvement or Shiny Distraction: Why Less Wrong is anti-Instrumental Rationality
We’ve had a lot of good criticism of Less Wrong lately (including Patri’s post above, which contains a number of useful points). But to prevent those posts from confusing newcomers, this may be a good time to review what... |
502875aa-69f6-40e9-b8a0-33766cdcd737 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Real-world Newcomb-like Problems
**Elaboration of:** A [point](/lw/3mn/discussion_for_eliezer_yudkowskys_paper_timeless/3ase) I’ve made before.
**Summary:** I phrase a variety of realistic dilemmas so as to show how they’re similar to Newcomb’s problem.
**Problem:** Many LW readers don't understand why we... |
5120770d-00da-4609-89a8-5764c45637ff | trentmkelly/LessWrong-43k | LessWrong | Bayesian Methods Reading List
I'm reading this for fun -- tutorials and book recommendations on the Bayesian methods toolboox with a cognitive science/machine learning slant. Comes from the Computational Cognitive Science Lab at Berkeley. I recommend the general 2008 tutorial.
Useful stuff included in tutorial:
... |
91149855-46c3-4231-9946-f2ece762bc1a | trentmkelly/LessWrong-43k | LessWrong | Legality as a Career Harm Assessment Heuristic
A question many people in the effective altruism movement have struggled with around earning to give is how to handle potentially harmful careers. It's obviously self-defeating if you cause more harm in earning your money than the good it does when you donate it, but we w... |
dc050eec-a2bb-4f49-a948-3877e81da451 | StampyAI/alignment-research-dataset/blogs | Blogs | less quantum immortality? • carado.moe
*less* quantum immortality?
---------------------------
if the set of nested universes [really does](what-happens-when-you-die.html) look like a funny graph of bubbles, i think there are two likely possibilities: either the set of bubbles rapidly dries up, or it grows towards ... |
0cd4fab3-f61f-45aa-998b-d508da7d818a | trentmkelly/LessWrong-43k | LessWrong | Larry King: I want to be frozen
I know celebrities cryocrastinate just as much as anyone else, but King seems like the kind of guy to go through with it.
http://www.cnn.com/2011/12/02/showbiz/larry-king-i-want-to-be-frozen/index.html?hpt=hp_t3 |
1666795b-cfd9-4f3e-801c-cec4d3d68e64 | trentmkelly/LessWrong-43k | LessWrong | AI Prejudices: Practical Implications
I see widespread dismissal of AI capabilities. This slows down the productivity gains from AI, and is a major contributor to disagreements about the risks of AI.
It reminds me of prejudice against various types of biological minds.
I will try to minimize the moralizing about fai... |
6ec8a81f-7554-498f-ac70-d14963bc51e6 | trentmkelly/LessWrong-43k | LessWrong | Charisma is a Force Multiplier
Sometimes, people talk about charisma as just a positive -- for instance, a lot of generic self-help or business advice assumes that charisma is generally good. On the other hand, you sometimes see people, often from "nerdier" communities, who say charisma is bad, an arbitary and unfair ... |
21742338-9a50-4f4c-b18c-10a2901963cd | trentmkelly/LessWrong-43k | LessWrong | On ‘Responsible Scaling Policies’ (RSPs)
This post was originally intended to come out directly after the UK AI Safety Summit, to give the topic its own deserved focus. One thing led to another, and I am only doubling back to it now.
RESPONSIBLE DEPLOYMENT POLICIES
At the AI Safety Summit, all the major Western play... |
59e62f7f-1be3-402b-8e8d-5e972026b87a | trentmkelly/LessWrong-43k | LessWrong | How to Live on 24 Hours a Day
I can think of no better way to spend my karma than on encouraging people to read this 19th century self-help book. It's free and online in full.
The guidelines on what makes an appropriate front-page article be damned, or, if necessary, enforced by official censorship.
Thanks to User:s... |
a49b7429-f215-45c2-abdf-77b23eb5dcb0 | trentmkelly/LessWrong-43k | LessWrong | Forecasting Transformative AI, Part 1: What Kind of AI?
PASTA: Process for Automating Scientific and Technological Advancement.
Audio also available by searching Stitcher, Spotify, Google Podcasts, etc. for "Cold Takes Audio"
This is the first of four posts summarizing hundreds of pages of technical reports focused a... |
1aac70b2-1ad3-40ab-9920-b422e4aab1c4 | trentmkelly/LessWrong-43k | LessWrong | Ukraine and the Crimea Question
When the United States invaded Iraq, they were hoping to be greeted as liberators. In a similar vein, the current discourse suggests that if Ukraine uses its military to successfully liberate Crimea, Crimeans will greet Ukrainians as liberators. The West that currently supports Ukraine ... |
7aca5187-ce2c-481f-bb04-0e564ac5f59b | trentmkelly/LessWrong-43k | LessWrong | Weighting the probability of being a mind by the quantity of the matter composing the computer that calculates that mind
TL;DR by lavalamp: Treating "computers running minds" as discrete objects might cause a paradox in probability calculations that involve self-location. "The probability of being a certain mind" is p... |
25e67292-e16f-408b-961e-26a5d8fcf57d | trentmkelly/LessWrong-43k | LessWrong | Steven Pinker on ChatGPT and AGI (Feb 2023)
While I disagreed with a lot of Robin Hanson's latest take on AI risk, I am glad he came out with an updated position. I think with everything that's happened in the past 6-12 months, it's a good time for public intellectuals and prominent people who have previously commente... |
086890df-d207-4b13-ad1d-408c15e05622 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Critique of some recent philosophy of LLMs’ minds
I structure this post as a critique of some recent papers on the philosophy of mind in application to LLMs, concretely, on whether we can say that LLMs *think*, *reason*, *understand language*, *refer to the real world when producing language*, *have goals and intents*... |
6b0419d9-2c5c-46f3-9795-c6d071b765dc | trentmkelly/LessWrong-43k | LessWrong | Meetup : Meetup, Champaign IL,
Discussion article for the meetup : Meetup, Champaign IL,
WHEN: 14 November 2012 07:00:00PM (-0600)
WHERE: Cafe Paradiso, 801 South Lincoln Avenue Urbana, IL 61801
Let's get together on Wednesday the 14th of November at 7pm at Cafe Paradiso.
Last time we talked about wanting to disc... |
d8059aab-d960-4018-968e-ac05478fc991 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Redwood's Technique-Focused Epistemic Strategy
Imagine you’re part of a team of ML engineers and research scientists, and you want to help with alignment. Everyone is ready to jump in the fray; there’s only one problem — how are you supposed to do applied research when you don’t really know how AGI will be built, what... |
2953880e-43de-4d3c-b9d8-37dc9f78dcea | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | What do XPT forecasts tell us about AI timelines?
*This post was co-authored by the Forecasting Research Institute and Rose Hadshar. Thanks to Josh Rosenberg for managing this work, Zachary Jacobs and Molly Hickman for the underlying data analysis, Adam Kuzee and Bridget Williams for fact-checking and copy-editing, th... |
e663f87e-3a60-4ac2-9bd8-1f73862578db | trentmkelly/LessWrong-43k | LessWrong | Host Keys and SSHing to EC2
I do a lot of work on EC2, where I ssh into a few instances I use for specific purposes. Each time I did this I'd get a prompt like:
$ ssh_ec2nf
The authenticity of host 'ec2-54-224-39-217.compute-1.amazonaws.com
(54.224.39.217)' can't be established.
ED25519 key fingerprint is SHA256:..... |
feae37d9-6e4f-434a-b940-8b59bb5ce1d8 | trentmkelly/LessWrong-43k | LessWrong | Explanations: Ignorance vs. Confusion
When people notice that they don't understand something, they want an explanation. Normally this works out okay, and we can either find an explanation or gracefully admit our ignorance. To use Richard Feynman's example, suppose someone asks why their Aunt Minnie is in the hospita... |
153ac8f3-f375-4d29-9e89-a7e919c727ca | trentmkelly/LessWrong-43k | LessWrong | Agent membranes and causal distance
For the goal of maintaining the safety and autonomy of particular agents (and potential moral patients), there seems to be something important about maintaining the membranes and boundaries of those agents. A few examples:
A bacterium uses its membrane to protect its internal proce... |
7b4d4c47-ed6f-44d8-b677-cfc1238ec1ff | trentmkelly/LessWrong-43k | LessWrong | Arbital postmortem
Disclaimer 1: These views are my own and don’t necessarily reflect the views of anyone else (Eric, Steph, or Eliezer).
Disclaimer 2: Most of the events happened at least a year ago. My memory is not particularly great, so the dates are fuzzy and a few things might be slightly out of order. But this... |
4248b74d-7bb4-4003-8713-d2bbb018d943 | trentmkelly/LessWrong-43k | LessWrong | Verbal Overshadowing and The Art of Rationality
To begin, here are some Fun Psychology Facts:
People who were asked to describe a face after seeing it are worse at recognizing the same face later.
People who are asked to describe a wine after drinking it are worse at recognizing the same wine later.
People who ar... |
d1a54b55-f08f-4ed7-80f4-a2a6f4e17a9e | trentmkelly/LessWrong-43k | LessWrong | Good Fortune and Many Worlds
Summary: The Many-Worlds interpretation of quantum mechanics can help us respond virtuously to improbably good circumstances. Contemplating the less lucky branches of the quantum multiverse can be seen as a beneficial 'negative visualisation' practise comparable to those in Stoicism and so... |
2e917187-a24c-4c9c-8808-bbf9346c0ea4 | trentmkelly/LessWrong-43k | LessWrong | Launching Forecast, a community for crowdsourced predictions from Facebook
Greetings! By way of brief introduction, I’m a long time lurker on LessWrong and a member of the team building Forecast, a crowdsourced prediction and discussion community. Full disclosure: we're part of a labs group, NPE, inside of Facebook.
... |
752f1491-30d2-4a53-b413-8719448c6072 | StampyAI/alignment-research-dataset/distill | Distill Scientific Journal | High-Low Frequency Detectors
This article is part of the [Circuits thread](/2020/circuits/), an experimental format collecting invited short articles and critical commentary delving into the inner workings of neural networks.
[Naturally Occurring Equivariance in Neural Networks](/2... |
c1a5b344-cddc-4fc3-8106-7023df965683 | StampyAI/alignment-research-dataset/special_docs | Other | Why companies should be leading on AI governance _ Jade Leung _ EA Global - London 2018-by Centre for Effective Altruism-video_id AVDIQvJVhso-date 20190207
# Jade Leung Why companies should be leading on AI governance - EA Forum
\_Are companies better-suited than governments to solve collective action problems around... |
c7da5387-2583-439c-af94-1cb4495b7d5e | trentmkelly/LessWrong-43k | LessWrong | I'm Sorry Fluttershy
I could have been a hero in another world.
I will call the friend of mine who commissioned that picture Fluttershy. They posted it shortly before they killed themselves in early March. They weren't the easiest person to help, but I should have done more than I did. By the end, they were pretty iso... |
a96f4092-5633-4b8e-9a13-f7eb19ec35ba | trentmkelly/LessWrong-43k | LessWrong | Expansion of "Cached thought" wiki entry
"Cached Thought" wiki entry has been copied below for you connivance.
>
>
> A cached thought is an answer that was arrived at by recalling the old conclusion, rather than performing the reasoning from scratch. Cached thoughts can result in the maintenance of a position when... |
3169fe77-9e9a-4d47-983e-2c8eacbd5659 | trentmkelly/LessWrong-43k | LessWrong | Are the bacteria/parasites in your gut affecting your thinking?
There is a variety of science going on, mostly in mice, about how intestinal microbiota (bacteria/parasites/fungi?) can affect behavior, emotion, and mental development (Review paper: The micro-biome gut-brain axis, 2011. Review paper 2009). Does any of i... |
16c3cd4b-da67-419a-bdff-b3fb26cfbcca | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | What are some AI governance exercises and projects I can try?
This list is largely focused on projects within [AI policy](https://80000hours.org/career-reviews/ai-policy-and-strategy/) rather than other career paths like [AI safety technical research](https://80000hours.org/career-reviews/ai-safety-researcher/). See [... |
076a5fa4-376e-47c1-bdf2-1faaa69788c5 | trentmkelly/LessWrong-43k | LessWrong | Interlude with the Confessor (4/8)
(Part 4 of 8 in "Three Worlds Collide")
The two of them were alone now, in the Conference Chair's Privilege, the huge private room of luxury more suited to a planet than to space. The Privilege was tiled wall-to-wall and floor-to-ceiling with a most excellent holo of the space surr... |
98d1d14a-f984-4b11-bf64-42556dc56839 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Paper: Constitutional AI: Harmlessness from AI Feedback (Anthropic)
The authors propose a method for training a harmless AI assistant that can supervise other AIs, using only a list of rules (a "constitution") as human oversight. The method involves two phases: first, the AI improves itself by generating and revising ... |
1225ec78-8e8e-43da-803e-d0ec9e43326b | trentmkelly/LessWrong-43k | LessWrong | What I learned at the AI Safety Europe Retreat
From the 30th March - 2nd April 2023, I attended the Artificial Intelligence Safety Europe Retreat (AISER) in Berlin, Germany. There were around 70 attendees from all over Europe. Most attendees were actively working on technical AI Safety (e.g SERI-MATS scholars, indepen... |
d4ef5c7c-d320-40f2-9c4a-28ea3d2fa586 | trentmkelly/LessWrong-43k | LessWrong | Parfit's Escape (Filk)
To the tune of "Escape" (The Piña Colada Song), with apologies to Rupert Holmes.
I was lost in the desert, hopelessly dying of thirst
And I thought to myself, this can't get any worse
I heard the roar of an engine, surely it was my hearse
But then a tall shadow cooled me, it spoke and I heard
... |
e5daa05e-c90a-4a6c-a99f-bf5deae9da26 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Urbana-Champaign: Recreation
Discussion article for the meetup : Urbana-Champaign: Recreation
WHEN: 11 May 2014 01:00:00PM (-0500)
WHERE: 40.1112,-88.2274
Since the weather is nice, let's meet outside, on the benches south of the engineering quad. I'll bring kites - coincidentally, the engineering quad is ... |
397c3894-c7e8-40c9-8120-67edfcf55724 | trentmkelly/LessWrong-43k | LessWrong | Arch-anarchy:Theory and practice
This article aims to expand on some of the ideas in the text " arch-anarchy"(See my previous post) republished from Extropy magazine. First of all, I believe that the nation-state is doomed to fall in a few years to the decentralization of the economy, and distributed computing network... |
01dd5490-4f21-455c-b06e-04013592faa9 | trentmkelly/LessWrong-43k | LessWrong | AI Alignment [progress] this Week (11/12/2023)
It’s hard to deny the fact that most of the oxygen in the room this week was taken up by the OpenAI Dev Day. If you want, feel free to check out my choose-your-own-adventure GPT. I think the jury is out on whether GPTs represent an actual use-case or if like plugins they ... |
5aaf760e-d59f-4e42-86a6-cd5009b15163 | trentmkelly/LessWrong-43k | LessWrong | Leaky Generalizations
Are apples good to eat? Usually, but some apples are rotten.
Do humans have ten fingers? Most of us do, but plenty of people have lost a finger and nonetheless qualify as "human".
Unless you descend to a level of description far below any macroscopic object - below societies, below people, be... |
a77be972-b8ab-425c-a536-08991417c17a | trentmkelly/LessWrong-43k | LessWrong | What do you think of my reading list?
(I am slightly anxious about making my first discussion post! If there is anything about this that should not have been done, or done differently, please let me know!)
I'm new to this rationalist stuff. I want to improve my grasp on many topics. I want a richer vocabulary and se... |
b0ba1edd-09cb-44bb-923e-5f00fc497779 | trentmkelly/LessWrong-43k | LessWrong | Problematic Problems for TDT
A key goal of Less Wrong's "advanced" decision theories (like TDT, UDT and ADT) is that they should out-perform standard decision theories (such as CDT) in contexts where another agent has access to the decider's code, or can otherwise predict the decider's behaviour. In particular, agents... |
4b989a1b-51d0-4a3d-ae51-bc582c885db5 | trentmkelly/LessWrong-43k | LessWrong | What Would It Cost to Build a World-Class Dredging Vessel in America?
I'm doing some research into questions surrounding the Foreign Dredge Act of 1906, and thought I'd experiment by throwing this out there.
For context, the 31 biggest dredging vessels were not built in America, and thus cannot be used in America by ... |
33afb6df-65fe-4d1f-927e-8997f54f15fe | trentmkelly/LessWrong-43k | LessWrong | Hierarchy and wings
(Note for LessWrong: This is more overtly about partisan politics than the norm, but I think it's not more about that than The Two-Party Swindle, from the Sequences, and it proposes a structural model that doesn't require people to be as stupid.)
There are a few points I didn't make in my post on ... |
48216cca-f998-488f-8d77-7e1ffcedca72 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | [Congressional Hearing] Oversight of A.I.: Legislating on Artificial Intelligence
This is a selection of quotes from the Senate Subcommittee Hearing "**Oversight of A.I.: Legislating on Artificial Intelligence"** held on 9/12/23. It's the third in a series of hearings, the first a hearing on [rules for AI](https://ww... |
05949846-e0d7-4109-89cd-e86a283bafe0 | trentmkelly/LessWrong-43k | LessWrong | Quantilal control for finite MDPs
We introduce a variant of the concept of a "quantilizer" for the setting of choosing a policy for a finite Markov decision process (MDP), where the generic unknown cost is replaced by an unknown penalty term in the reward function. This is essentially a generalization of quantilizatio... |
272aebce-090e-4037-bd77-3b21a22cf7b7 | trentmkelly/LessWrong-43k | LessWrong | Bad names make you open the box
Think of a function as a black box. It takes an input, and spits back out an output.
For getPromotedPosts, you can feed it a list of blog posts and it will spit back out the ones that have been promoted.
But I probably didn't need to explain that to you, did I? Why not? Well, becau... |
b0fa7433-8f67-47e5-80e3-911e6436925e | trentmkelly/LessWrong-43k | LessWrong | What if the front page…
What if the front page looked a little more like this?
(Please assume that I'm trying to help. If you're polite and constructive (even if you hate this design) Omega will send you bundles of love in the post. If you're rude, I'll personally fund ninja assassins to hunt you down.) |
04bfbf1a-102f-4cdc-8bb3-0cfd421af369 | trentmkelly/LessWrong-43k | LessWrong | Do the 'unlucky' systematically underestimate high-variance strategies?
From the UK Telegraph:
> A decade ago, I set out to investigate luck. I wanted to examine the impact on people's lives of chance opportunities, lucky breaks and being in the right place at the right time. After many experiments, I believe that I ... |
80ff5c66-52b9-4187-ac1a-d2ce529d6322 | trentmkelly/LessWrong-43k | LessWrong | SETI Predictions
I enjoyed reading through people's views of the AGI Predictions. I know only a little about AI and a little bit more about SETI (Search for Extraterrestrial Intelligence), so I decided to make a similar poll.
The First Contact scenario with extraterrestrial intelligence shares certain similarities w... |
26a184b7-7e1d-4f82-9cd6-950a40d3963f | trentmkelly/LessWrong-43k | LessWrong | Formalizing Space-Faring Civilizations Saturation concepts and metrics
Crossposted on the EA Forum.
Displacement of other Space-Faring Civilizations (SFCs) may have macrostrategic impact for longtermists as hinted in a previous post. For example, our causal impact depends on how much value we produce relative to how ... |
efbc0ceb-64f1-4bb6-833c-19b73fadbbff | trentmkelly/LessWrong-43k | LessWrong | Kallipolis, USA
This is a very tongue-in-cheek term paper I wrote for my philosophy class on Plato in fall of 2016. I had a lot of fun with it & still like to talk about it sometimes when I get tipsy. I'm putting it up here because why not. Comments welcome.
Abstract:
> Reading Plato’s Republic, you may have had rea... |
25687bab-e932-4a26-948b-68929152b9c6 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | (retired article) AGI With Internet Access: Why we won't stuff the genie back in its bottle.
Disclaimer: This post is largely based on my long response to someone asking why it would be hard to stop or remove an AI that has escaped into the internet. It includes a list of obvious strategies such an agent could employ.... |
d2a796b6-f21d-4234-b3ef-9e253b54052c | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Related to: Rationalization, Meditation on curiosity, Original Seeing.
Why aren’t you learning faster?
For me, one answer is: because I’m not asking questions. I blunder through conversations trying to “do my job”, or to look good, or elaborating my own theories, or allowing cached replies to come out of my mouth on a... |
6141a0b9-a805-413d-b52d-f7434e092cf6 | trentmkelly/LessWrong-43k | LessWrong | Things philosophers have debated
Straight from Wikipedia.
I just had to stare at this a while. We can have papers published about this, we really ought to be able to get papers published about Friendly AI subproblems.
My favorite part is at the very end.
----------------------------------------
Trivialism i... |
0eb9caa2-7c87-4b07-8eaf-944172573c69 | trentmkelly/LessWrong-43k | LessWrong | A sketch of a value-learning sovereign
In the previous post, I discussed three preference frameworks for goal-directed agents. In this post, I will discuss the value-learning sovereign in more detail.
----------------------------------------
From the Arbital article on genies:
> Eliezer Yudkowsky has suggested that... |
ae3426c1-f4fe-4321-b1f7-ff6a10147d6a | StampyAI/alignment-research-dataset/lesswrong | LessWrong | What Does AI Alignment Success Look Like?
Suppose you are put in stasis and wake up 10 years after the FOOM. You are trying to figure out if the AI Alignment project succeeded or not. How can you tell? Not vaguely, concretely. What metrics indicate success, and what metrics indicate failure? The following are potentia... |
254c2f61-0e40-4685-8c68-cb2b1b64bec4 | StampyAI/alignment-research-dataset/arbital | Arbital | Why is log like length?
If a number $x$ is $n$ digits long (in [https://arbital.com/p/-decimal_notation](https://arbital.com/p/-decimal_notation)), then its logarithm (base 10) is between $n-1$ and $n$. This follows directly from the [definition of the logarithm](https://arbital.com/p/40j): $\log_{10}(x)$ is the numbe... |
22550806-0338-4908-af06-271441f12a83 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Investigations of Performance and Bias in Human-AI Teamwork in Hiring
Introduction
------------
As AI-powered decision tools are increasingly deployed in real-world domains, a central challenge remains understanding how best to design models to assist humans kleinberg2018human. Ergo, a growing body of literature ha... |
cd3c09db-3569-49b7-ab17-a4835b292c70 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Cambridge (MA) Meetup
Discussion article for the meetup : Cambridge (MA) Meetup
WHEN: 05 August 2012 02:00:00PM (-0400)
WHERE: 25 Ames St, Cambridge, MA 02139
Cambridge/Boston-area Less Wrong meetups on the first and third Sunday of every month, 2pm at the MIT Landau Building [25 Ames St, Bldg 66], room 14... |
fc635d18-8927-46ba-b174-ba08656079a6 | trentmkelly/LessWrong-43k | LessWrong | Give praise
The dominant model about status in LW seems to be one of relative influence. Necessarily, it's zero-sum. So we throw up our hands and accept that half the community is just going to run a deficit.
Here's a different take: status in the sense of worth. Here's a set of things we like, or here's a set of pro... |
c8bdb645-a736-4571-9433-d3ab405a4b5e | trentmkelly/LessWrong-43k | LessWrong | Kingfisher Summer Tour 2024
Kingfisher is going on tour again:
Thr 2024-06-27 Rochester NY Fri 2024-06-28 Pittsburgh PA Sat 2024-06-29 Bloomington IN Sun 2024-06-30 St Louis MO Mon 2024-07-01 Cincinnati OH Tue 2024-07-02 Indianapolis IN
Cecilia made a flyer:
Harris will be calling, and we'll be driving toget... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.