id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
75704571-64c5-4f97-b76e-0e725c5842fd | trentmkelly/LessWrong-43k | LessWrong | Preparing for Power Outages in Disasters
Author: Finan Adamson
Last Updated: 03/2022
Overview
This doc goes into details on how to maintain electricity if it’s important to your survival and flourishing even when the power goes out. It may not be necessary to do anything here if you don’t depend on electricity t... |
34cfa112-d530-4a7b-8a6a-cd52703c098a | trentmkelly/LessWrong-43k | LessWrong | RFC: COVID-19 Statistical Guilt
(Updated 2020/08/08; appended to the bottom. New BLUF: "What's the expected total number of further C19 infections recursively resulting from a single infection, in the current USA environment?")
(Original post: )
BLUF: How many days of life would I be statistically costing others by ... |
bfb26e73-ccb3-41c5-920f-d178a33a9abc | trentmkelly/LessWrong-43k | LessWrong | How do you notice when you're procrastinating?
I'm going to steal Anna's idea and change it to the instrumental side of rationality. In Luke's algorithm for beating procrastination, Step 1 is to Notice You Are Procrastinating. I'm not so sure this is easy. For me, the knowledge sort of fades in and out without being e... |
64b9cd3b-3af9-4729-8f2a-f98cac01af0e | trentmkelly/LessWrong-43k | LessWrong | TDT for Humans
This is part 19 of 30 of Hammertime. Click here for the intro.
As is Hammertime tradition, I’m making a slight change of plans right around the scheduled time for Planning. My excuse this time:
Several commenters pointed out serious gaps in my knowledge of Focusing. I will postpone Internal Double Cru... |
b9e5562f-23fe-44ac-96bf-351dbbb7b809 | trentmkelly/LessWrong-43k | LessWrong | Grandpa Has Different Rules
It's very common that there are multiple adults in a child's life who parent differently. These can be explicit differences in rules (I allow jumping on the furniture, you don't), or more subtle differences in approach (I'm fine with kids trying to persuade me something should be ok, not ev... |
e00f8bae-35ef-4bd6-8e59-1579987cb085 | trentmkelly/LessWrong-43k | LessWrong | Metaculus Introduces AI-Powered Community Insights to Reveal Factors Driving User Forecasts
Forecast Consumers Can More Quickly, More Deeply Understand Aggregate Forecasts Without Reading Hundreds of User Comments
Forecast questions sometimes feature hundreds of comments offering analyses, rationales, arguments, and... |
a077dd04-ed93-4020-9fcf-fdadc60ad4d9 | trentmkelly/LessWrong-43k | LessWrong | Hierarchical planning: context agents
If you end up applying this post, please do it in the name of safety research.
I - intro
Suppose I need groceries. When I make a plan to get more groceries, what I don't do is fully model the world (e.g. as a Markov process), find a policy that leads to me getting groceries, and... |
9deb9944-81e8-4971-826a-62f57d8cd0b2 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Does agent foundations cover all future ML systems?
Epistemic Status: *Wondering over meta approaches to reasoning about agent foundations*
In mathematics, we can find general principles for mathematical objects with a particular set of axioms. For example, if a language follows first-order logic, we can assume that ... |
f4a375b2-7b5f-4495-9e28-7aaf38b447c7 | trentmkelly/LessWrong-43k | LessWrong | Goal Factoring
This is part 18 of 30 of Hammertime. Click here for the intro.
Up until today, Hammertime focused on improving one’s ability to achieve one’s goals. The next two techniques, Goal Factoring and Internal Double Crux, are designed to figure out what goals to pursue. For the largest goals in life, you shou... |
39af5d23-d84c-4265-9703-ce66891d3fe3 | trentmkelly/LessWrong-43k | LessWrong | SAEBench: A Comprehensive Benchmark for Sparse Autoencoders
Adam Karvonen*, Can Rager*, Johnny Lin*, Curt Tigges*, Joseph Bloom*, David Chanin, Yeu-Tong Lau, Eoin Farrell, Arthur Conmy, Callum McDougall, Kola Ayonrinde, Matthew Wearden, Samuel Marks, Neel Nanda *equal contribution
TL;DR
* We are releasing SAE Bench... |
a9fbc2d0-5062-48e8-9dcb-667b20f9f99e | trentmkelly/LessWrong-43k | LessWrong | Help: Building Awesome Personal Organization Systems
Related to: Rationality Power Tools
I'm looking to use (or make) something that helps me achieve god-like productivity. In particular, I'm interested in any information about systems that are:
* Flexible: They can be extended or customized to accommodate new work... |
a707f8f8-1938-4e2c-bc79-571c5f203d91 | trentmkelly/LessWrong-43k | LessWrong | nostalgebraist - bayes: a kinda-sorta masterpost
Extended criticism of "Bayesianism" as discussed on LW. An excerpt from the first section of the post:
> Like most terms ending in -ism, [Bayesianism] can mean a number of different things. In its most limited sense, “Bayesianism” is a collection of technical/mathemat... |
406e07bb-2e18-4a07-8e41-bcde1251c3a2 | trentmkelly/LessWrong-43k | LessWrong | The Shallow Bench
Cross posting from my personal blog: https://spiralprogress.com/2024/10/28/the-shallow-bench/
Spoilers for "Project Hail Mary", stop reading here if you don't want to be spoiled.
Project Hail Mary follows Ryland Grace, a disgraced academic turned high school biology teacher who gets selected as par... |
0944400f-28cc-41de-9b35-d9e78d37bd33 | trentmkelly/LessWrong-43k | LessWrong | Running With a Backpack
In the comments on my running by default post, one of the more common responses was that people often have backpacks and a bouncing backpack is somewhere between "annoying" and "painful, risking bruising".
There was some discussion on how to set up your backpack to reduce bouncing. Tips:
*... |
28547061-9fec-4c15-9a3c-22f890ffc677 | trentmkelly/LessWrong-43k | LessWrong | UC Berkeley course on LLMs and ML Safety
The UC Berkeley course I co-taught now has lecture videos available: https://www.youtube.com/playlist?list=PLJ66BAXN6D8H_gRQJGjmbnS5qCWoxJNfe
Course site: Understanding LLMs: Foundations and Safety
Unrelatedly, a more conceptual AI safety course has its content available at h... |
b1a97f39-bd48-40b2-b1e8-215c2ad3aba2 | trentmkelly/LessWrong-43k | LessWrong | Meetup : San Francisco: Effective Altruism
Discussion article for the meetup : San Francisco: Effective Altruism
WHEN: 27 June 2013 07:00:00PM (-0700)
WHERE: 170 Saint Germain Ave, San Francisco
Our first salon, about Effective Altruism groups in Oxford.
The current effective altruist movements seem to be spread b... |
a201e23b-09ed-40f7-91f3-4b53c6f4e3e8 | trentmkelly/LessWrong-43k | LessWrong | Cryo: Legal fees of $2500
I have just received a message from my lawyer, regarding the preparations of my cryo-based will, power of attorney, and related papers. The most significant quote reads as follows:
Due to the complex nature of your wishes and the undeveloped area of the law surrounding cryogenics and the tr... |
2bad3731-0b77-4f1c-8e1c-f24ff7d02ed1 | StampyAI/alignment-research-dataset/blogs | Blogs | Lyle Ungar on forecasting
 [Dr. Lyle Ungar](http://www.cis.upenn.edu/~ungar/home.html) is a Professor of Computer and Information Science at the University of Pennsylvania, where he also holds appointments in multiple departments... |
73d80fd4-b9b6-4660-88ec-189b088fb950 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Intuitions on Universal Behavior of Information at a Distance
What’s special about [information at a distance](https://www.lesswrong.com/s/ehnG4mseKF6xALmQy/p/TTNS3tk5McHqrJCbR)? Some examples of what I mean:
* What information about a little patch of pixels in a photo is relevant to another little patch of pixels fa... |
e06f25e1-0140-4e74-a274-221359186997 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | AI and Value Alignment | Jaan Tallinn
[Music]
has been my work over the last 10 years
trying to bring these communities
together to have this open discussions
about topics that have been taboos and
yeah thanks for that I grew to have been
able to create such a positive
atmosphere I see like a lot of smiles
around me i... |
b0b0991d-1e44-4d4d-8a67-3d133ce26a08 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Against GDP as a metric for timelines and takeoff speeds
Or: Why AI Takeover Might Happen Before GDP Accelerates, and Other Thoughts On What Matters for Timelines and Takeoff Speeds
============================================================================================================================
*[Epistemic... |
f79847ad-57e3-4be9-83ba-fb7621e1edc8 | trentmkelly/LessWrong-43k | LessWrong | OpenAI now has an RL API which is broadly accessible
About 1 month ago, OpenAI made their RL fine-tuning API accessible to anyone. While this API has some important limitations, I still think it might be quite useful for AI safety/alignment work so people should consider taking advantage of it.
To use the RL fine-tun... |
a02c0067-b992-45fb-9ffc-e355625b71a3 | trentmkelly/LessWrong-43k | LessWrong | Evaluating the truth of statements in a world of ambiguous language.
If I say "the store is 500 meters away," is this strictly true? Strictly false? Either strictly true or strictly false, with probabilies of true or false summing to one? Fuzzily true, because the store is 500.1 meters away? My thesis is that it's str... |
6487c59e-abdf-4ed1-bf2b-b4b5a6a18eef | trentmkelly/LessWrong-43k | LessWrong | Overview article on FAI in a popular science magazine (Hebrew)
A new article which I wrote just appeared in Hebrew in Galileo, Israel's top popular science magazine, in hardcopy.
It is titled "Superhuman Intelligence, Unhuman Intelligence" (Super- and un- are homophones in Hebrew, a bit of wordplay.)
You can read it ... |
96c854b3-df2b-4a9e-a6ab-a2f14eec75f1 | trentmkelly/LessWrong-43k | LessWrong | Progress links and short notes, 2024-12-27: Clinical trial abundance, grid-scale fusion, permitting vs. compliance, crossword mania, and more
Much of this content originated on social media. To follow news and announcements in a more timely fashion, follow me on Twitter, Threads, Bluesky, or Farcaster.
Contents
* M... |
c40c34e2-af30-4feb-bbad-351a41713cc0 | trentmkelly/LessWrong-43k | LessWrong | Does the US nuclear policy still target cities?
The history of nuclear strategic bombing
Daniel Ellsberg’s The Doomsday Machine brought my attention to a horrifying fact about early US nuclear targeting policy. In 1961, the US had only one nuclear war plan, and it called for the destruction of every major Soviet city ... |
b40a2662-e2e5-4aca-a627-82987646cc67 | trentmkelly/LessWrong-43k | LessWrong | Easy money: Find me a new job, get $1000
I normally post under a different name, which you can find by looking at my posting history, specifically, this thread. I need to keep the search somewhat secret, so I'm adding a trivial barrier to identifying me.
Anyway, I haven't been very good at job searches, and I have s... |
a4ae6512-3888-4952-a38b-9012e7339468 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | A strong mind continues its trajectory of creativity
*[Metadata: crossposted from <https://tsvibt.blogspot.com/2023/01/a-strong-mind-continues-its-trajectory.html>. First completed January 29, 2023.]*
A very strong mind is produced by a trajectory of creativity. A trajectory of creativity that produces a very strong... |
f95b3853-8b0a-4820-b128-05d0d0186406 | trentmkelly/LessWrong-43k | LessWrong | The Hidden Origins of Ideas
It is well known that people tend to inherit their world view toghether with their genes. Buddhists are born to the Buddhists, Muslims are born to the Muslims and Republicans are born to the Republicans. While rejecting Predestination, a XVI century catholic could be fairly certain that... |
ae29f351-aa64-4016-8f86-6d574b133936 | trentmkelly/LessWrong-43k | LessWrong | Joy in Discovery
> "Newton was the greatest genius who ever lived, and the most fortunate; for we cannot find more than once a system of the world to establish."
> —Lagrange
I have more fun discovering things for myself than reading about them in textbooks. This is right and proper, and only to be expected.
... |
f1dfb214-d3a2-4f93-be0a-3aab45401ee7 | trentmkelly/LessWrong-43k | LessWrong | New Member
Hello. I'm new to LW. I was wondering if there's a forum to ask questions and talk about HPMOR? |
bf1e8e88-682f-445a-96c2-a7ad143cb88e | trentmkelly/LessWrong-43k | LessWrong | Advice On Getting A Software Job
(Note to LWers: This post was written for a general audience at my blog, but I think it's particularly applicable to Less Wrong, as many here are already interested in programming. Programming is also an important route into two of the main paths to get rich, entrepreneurship and angel... |
0af36f2a-6361-4838-b87b-18007829074b | StampyAI/alignment-research-dataset/arxiv | Arxiv | The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
Future of
Humanity
InstituteUniversity
of OxfordCentre for
the Study of
Existential
RiskUniversity of
CambridgeCenter for a
New American
SecurityElectronic
Frontier
FoundationOpenAI
February 2018The Malicious Use
of Art... |
6af354f5-f27a-4afa-aeda-b2aae737e653 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Why one-box?
I have sympathy with both one-boxers and two-boxers in Newcomb's problem. Contrary to this, however, many people on Less Wrong seem to be staunch and confident one-boxers. So I'm turning to you guys to ask for help figuring out whether I should be a staunch one-boxer too. Below is an imaginary dialogue se... |
cd1aad48-9b3a-4066-8a68-dd9633f14285 | trentmkelly/LessWrong-43k | LessWrong | No, Seriously. Just Try It: TAPs
This next semester (I'm in university, so that's how I measure time) I'm working on developing my ability to better integrate arbitrary habits into my behavior. Trigger-action-planning (a more detailed explanation as well) is LW's most concrete strategy for doing such a thing, so I've ... |
376f454f-0bb7-4e05-a1db-742cc62c86b7 | trentmkelly/LessWrong-43k | LessWrong | Fort Collins, Colorado Meetup Wednesday June 15 7pm
At the Bean Cycle, downtown. I'll have a Less Wrong sign.
Let's exchange anti-akrasia tips. |
3a4b7fe7-5863-4186-a294-a73001cc4c72 | trentmkelly/LessWrong-43k | LessWrong | Meetup : London social meetup - New venue
Discussion article for the meetup : London social meetup - New venue
WHEN: 17 November 2013 02:00:00PM (+0000)
WHERE: London W6 8BS
LW London is experimenting with switching to weekly meetups, and also experimenting with a new venue! You should come along and complain about... |
c7703adf-6759-4cd4-838f-ad3e1c5df01f | StampyAI/alignment-research-dataset/arxiv | Arxiv | Adaptive Mechanism Design: Learning to Promote Cooperation
1 Introduction
---------------
Social dilemmas highlight conflicts between individual and collective interests. Cooperation allows for better outcomes for all participants, but individual participants are tempted to increase their own payoff at the expense ... |
db7175c3-e262-4147-85c4-03a112b166e1 | trentmkelly/LessWrong-43k | LessWrong | Counterarguments to Core AI X-Risk Stories?
I've added a tag for object-level AI risk skepticism arguments. I've included my own post about deceptive alignment and Katja Grace's post about AI X-risk counterarguments. What other arguments should be tagged? |
674e7ee2-cc6d-4bc1-b5af-a37ca5d27c67 | trentmkelly/LessWrong-43k | LessWrong | The Best Way to Align an LLM: Is Inner Alignment Now a Solved Problem?
This is a link-post for a new paper I read: Safety Pretraining: Toward the Next Generation of Safe AI by Pratyush Maini, Sachin Goyal, et al.
For a couple of years I (and others) have been proposing an approach to alignment: what the authors of th... |
530c4904-4087-4af2-98d3-37418ec51428 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Counterfactual Fairness
1 Introduction
---------------
Machine learning has spread to fields as diverse as credit scoring Khandani et al. ([2010](#bib.bib15)), crime prediction Brennan et al. ([2009](#bib.bib3)), and loan assessment Mahoney & Mohen ([2007](#bib.bib18)). As
machine learning enters these new areas it... |
9eb6a056-d142-471a-8897-803a75916110 | trentmkelly/LessWrong-43k | LessWrong | [link] Interview with Anders Sandberg on how to make a difference through research and how to choose a research topic
Here. Some excerpts:
> What do you think are some good heuristics for doing high impact research?
>
> One idea is to go for under-researched fields. Progress in a field is typically a very convex lea... |
84bf2a5f-11a0-47f6-aaa6-8cb2e8f4b1d5 | trentmkelly/LessWrong-43k | LessWrong | A 2011 summary of modern intelligence tests
...and the theories of intelligence they use to measure 'intelligence'. Here, from the new (and very good) Cambridge Handbook of Intelligence.
Bonus fun fact from chapter 3: "Persons with higher IQs apparently are also likely to be taller and have more body symmetry than pe... |
978172d2-eaa3-46ae-a816-a303d82d3849 | trentmkelly/LessWrong-43k | LessWrong | Meetup Notes: Community Building
Review of our fifth LessWrong Meetup - Report from Berlin
Summary
We had visitors fank1 and just_existing from the Bielefeld/Paderborn Meetup. The meetup was great. It was a continuously lively discussion with everybody contributing personal and/or insightful and/or relevant pieces.... |
cbbdadab-5858-4824-af7e-6b01c82a48e4 | trentmkelly/LessWrong-43k | LessWrong | You don't get to know what you're fighting for
A number of my recent posts may have given you the impression that I know exactly what I'm fighting for. If someone were to ask you, "hey, what's that Nate guy trying so hard to do," you might answer something like "increase the chance of human survival," or "put an end t... |
fd8ddebb-fdba-4ae4-b7ba-419c847342d2 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Sydney Pub meetup - February
Discussion article for the meetup : Sydney Pub meetup - February
WHEN: 23 February 2017 06:30:00PM (+1100)
WHERE: 565 george st, sydney
https://www.meetup.com/lesswrong-Sydney0/events/237546781/
https://www.facebook.com/events/1816134538644351/
Find us at the big table outsi... |
7ab663da-5689-4bd7-9d2e-df253e08ab42 | trentmkelly/LessWrong-43k | LessWrong | Apple Cider Syrup
We bought some apple cider when we went apple picking a few weeks ago, and while it's tasty stuff it seems it's not what people wanted to be spending their sweet budget on: we still had 2/3 of it left three weeks later. I decided to reduce it and make syrup, partly so that it would keep longer but mo... |
0efaaf64-947d-40f1-b2c8-777645be07c3 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Recursive Quantilizers II
I originally introduced the recursive quantilizers idea [here](https://www.lesswrong.com/s/SBfqYgHf2zvxyKDtB/p/bEa4FuLS4r7hExoty), but didn't provide a formal model until my recent [Learning Normativity](https://www.lesswrong.com/posts/2JGu9yxiJkoGdQR4s/learning-normativity-a-research-agenda)... |
8384479e-55b9-4a27-98ff-4a68fab323a9 | trentmkelly/LessWrong-43k | LessWrong | Boredom vs. Scope Insensitivity
How much would you pay to see a typical movie? How much would you pay to see it 100 times?
How much would you pay to save a random stranger’s life? How much would you pay to save 100 strangers?
If you are like a typical human being, your answers to both sets of questions probably exhi... |
94c182f0-794c-401a-9112-1bb47a86361c | trentmkelly/LessWrong-43k | LessWrong | Cognitive Biases in Large Language Models
> Humans, one might say, are the cyanobacteria of AI: we constantly emit large amounts of structured data, which implicitly rely on logic, causality, object permanence, history—all of that good stuff. All of that is implicit and encoded into our writings and videos and ‘data e... |
369cc0a9-22df-42dd-a2fa-b8a9a3ab31dd | trentmkelly/LessWrong-43k | LessWrong | LLM in-context learning as (approximating) Solomonoff induction
Epistemic status: One week empirical project from a theoretical computer scientist. My analysis and presentation were both a little rushed; some information that would be interesting is missing from plots because I simply did not have time to include it. ... |
62845201-426c-4496-9d99-f6d45e2204c5 | trentmkelly/LessWrong-43k | LessWrong | An overview of some promising work by junior alignment researchers
We’re all familiar with ELK, natural abstractions, and toy models of superposition.
But there’s also a new cohort of alignment researchers. Many of them got involved (or produced their first major pieces of work) in the last year.
I’ve been impresse... |
4f1b5313-9138-4b30-94b1-15bf0c6a26e3 | trentmkelly/LessWrong-43k | LessWrong | The Case For Gods
[this is a repost from my personal blog explanationing.wordpress.com. Look there for posts explaining my priors.]
I’ve been playing with belief in God since I was a child.
During my adolescent years, when I started really digging the catchphrases of pseudo-rational-types like Terry Goodkind, I beca... |
1c771794-d04a-4f14-8c7f-4435d3b87474 | trentmkelly/LessWrong-43k | LessWrong | Epistea Summer Experiment (ESE)
Remark: This post was written collectively by the organizing team of the Epistea Summer Experiment.
Cross-posted to the EA Forum here.
Epistea Summer Experiment (ESE, /ˈiːzi/) was an experimental summer workshop in Prague combining elements of applied rationality and experiential educ... |
9e852c7c-db93-4c8a-b1ad-1876aa59f035 | trentmkelly/LessWrong-43k | LessWrong | Multi-agent predictive minds and AI alignment
Abstract: An attempt to map a best-guess model of how human values and motivations work to several more technical research questions. The mind-model is inspired by predictive processing / active inference framework and multi-agent models of the mind.
The text has slightly... |
d2e2acf2-8e9d-4b23-975d-06dabf3b1335 | trentmkelly/LessWrong-43k | LessWrong | Human errors, human values
The trolley problem
In 2009, a pair of computer scientists published a paper enabling computers to behave like humans on the trolley problem (PDF here). They developed a logic that a computer could use to justify not pushing one person onto the tracks in order to save five other people. Th... |
fcc1de32-0120-4d0d-9686-5b60263771d6 | trentmkelly/LessWrong-43k | LessWrong | How fast can we perform a forward pass?
Thanks to Hao Zhang, Kayvon Fatahalian, and Jean-Stanislas Denain for helpful discussions and comments.
Over the last month, I’ve spent a lot of time trying to answer the following question:
> How quickly can we perform one forward pass in a transformer model?
By a transforme... |
f260c78c-8631-4ac5-a9a0-a596fbc5887b | trentmkelly/LessWrong-43k | LessWrong | Taking Ideas Seriously
I, the author, no longer endorse this post.
----------------------------------------
Abstrummary: I describe a central technique of epistemic rationality that bears directly on instrumental rationality, and that I do not believe has been explicitly discussed on Less Wrong before. The te... |
2b2eba0a-0555-4b69-8e59-7a0c08b8ec43 | trentmkelly/LessWrong-43k | LessWrong | Make learning a reality
The following passage comes from What Do You Care What Other People Think? by Richard Feynman. It's a collection of stories from his life and curious adventures.
> We had the Encyclopedia Britannica at home. When I was a small boy he [Feynman's father] used to sit me on his lap and read to me ... |
8799d519-d08b-465c-84fd-a3e71bab4e6a | trentmkelly/LessWrong-43k | LessWrong | Help re:Less Wrong Meetup please?
Hi Everyone,
I've been conducting a LW meetup in West Sydney. had 3 somewhat succesful sessions. Covered the following topics:
1. What is rationality? Who uses it? Why be less wrong?
2. Map and Territroy
3. Belief: functions, proper and imporper and other things pertaining.
I'm w... |
82ff2782-307e-4b90-bcd6-b59b5263ebdb | StampyAI/alignment-research-dataset/arxiv | Arxiv | Estimating the Brittleness of AI: Safety Integrity Levels and the Need for Testing Out-Of-Distribution Performance
1 Introduction
---------------
Test, Evaluation, Verification, and Validation (TEVV) for Artificial Intelligence (AI) is a central challenge that threatens to limit the economic and societal rewards th... |
5dd2d268-ffde-4e0f-b87c-66587f59cd0d | trentmkelly/LessWrong-43k | LessWrong | Model-building and scapegoating
When talking about undesirable traits, we may want to use simple labels. On one hand, simple labels have the virtue of efficiently pointing to an important cluster of behavioral predictions. On the other, they tend to focus attention on the question of whether the person so described is... |
70802b4d-c3d7-4113-b647-15baa506e891 | trentmkelly/LessWrong-43k | LessWrong | What readings did you consider best for the happy parts of the secular solstice?
I'm currently thinking about creating a new rationalist ritual day that focuses just on happiness. I'm thinking about reusing some elements that worked well at the solstice. Which readings did you enjoy very much during the happy parts of... |
3fd973ea-1965-4055-8d90-8c6a7e70e585 | trentmkelly/LessWrong-43k | LessWrong | Fermenting Form
Application forms are hard to write. Questions like: “Tell us about yourself” or “What are your strengths and weaknesses?” are tiring to address usefully in 200 words. Getting stuck on a bad application question rewriting paragraphs is fermenting your brain. You don’t become a better applicant with mor... |
8df09246-d106-49d2-a915-5d0cbbbd96ba | trentmkelly/LessWrong-43k | LessWrong | Anki with Uncertainty: Turn any flashcard deck into a calibration training tool
We've developed an Anki addon that lets you do calibration training on numerical flashcards!
Find information on how it works and how to use it on Quantified Intuitions.
Thanks to @Beth Barnes for supporting the development and giving fe... |
8e18506b-4393-48c5-9cd0-b07fdedbcb63 | StampyAI/alignment-research-dataset/arxiv | Arxiv | DETERRENT: Detecting Trojans using Reinforcement Learning
1. Introduction
----------------
Reinforcement learning (RL) helps a computing system (a.k.a. agent) to learn by its own experience through exploring and exploiting the underlying environment.
Over time, the agent takes optimal actions in sequence, even with... |
891205bf-e919-4a10-8cde-8c1673671b9f | trentmkelly/LessWrong-43k | LessWrong | On Measuring Intellectual Performance - personal experience and several thoughts
A very interesting problem is measuring something like general intelligence. I’m not going to delve deeply into this topic but simply want to draw attention to an idea that is often implied, though rarely expressed, in the framing of such... |
934c1713-c367-4078-9fa2-9945efe94a08 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Pessimistic Shard Theory
It is often said that a partial alignment solution will bring about an S-risk, as your agent cares enough about humans to keep them around, but not enough about them to allow them to flourish. This is usually not worried about because the thought is that we are currently very far away from eve... |
6889c389-68d2-4062-8117-7ef44f3d59ec | trentmkelly/LessWrong-43k | LessWrong | The Absent-Minded Driver
This post examines an attempt by professional decision theorists to treat an example of time inconsistency, and asks why they failed to reach the solution (i.e., TDT/UDT) that this community has more or less converged upon. (Another aim is to introduce this example, which some of us may not be... |
0d82c33b-02e6-4317-9356-fc55b9080183 | trentmkelly/LessWrong-43k | LessWrong | Q&A with experts on risks from AI #4
[Click here to see a list of all interviews]
Professor Michael G. Dyer is an author of over 100 publications, including In-Depth Understanding, MIT Press, 1983. He serves on the editorial board of the journals: Applied Intelligence, Connection Science, Knowledge-Based Systems, Int... |
0185f9f9-a40c-4a58-a71a-a72b1cc79684 | trentmkelly/LessWrong-43k | LessWrong | How to use ChatGPT to get better book & movie recommendations
I find ChatGPT gives me better movie recommendations than Netflix when I do the following:
1) Keep a list of books/movies that you like and why you like them
2) Use the prompt "Recommend X movies/books that [CRITERIA]. Here's a list of things I like and ... |
ec20e4b4-79fd-4c84-b45b-500ee27dcc07 | trentmkelly/LessWrong-43k | LessWrong | Challenge: know everything that the best go bot knows about go
On a few different views, understanding the computation done by neural networks is crucial to building neural networks that constitute human-level artificial intelligence that doesn’t destroy all value in the universe. Given that many people are trying to ... |
b6e9d045-6592-4600-acf4-f4381eea9060 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | When does technical work to reduce AGI conflict make a difference?: Introduction
*This is a pared-down version of a longer draft report. We went with a more concise version to get it out faster, so it ended up being more of an overview of definitions and concepts, and is thin on concrete examples and details. Hopefull... |
9ea7a935-7227-426c-a5f4-0757a62751d5 | trentmkelly/LessWrong-43k | LessWrong | n=3 AI Risk Quick Math and Reasoning
Epistemic status: n=3, more about building a culture of sharing and reasoning through numbers than any given particular estimates.
I've been somewhat surprised by how substantially different the probability estimates of on AI risk are from smart people who are well-informed, even ... |
166ee038-de38-414c-86a4-4c28b3cd5f2a | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Animal Advocacy in the Age of AI
This post calls on animal advocates to take seriously how the future will be transformed by AI. It lays out how technological revolutions of the past have enabled th... |
05ce07b9-e92a-45fe-8497-bdca4ff9c56e | trentmkelly/LessWrong-43k | LessWrong | time is event based
After college I worked for a high frequency trading firm where the basic unit of time was the microsecond. A single blink—about 250,000 µs—was long enough for our algorithms to open and close thousands of positions, each trade born and buried long before a human observer would have even noticed the... |
f5a06683-98a9-4364-8175-1c889f7a8b13 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Informers and Persuaders
Today's post, Informers and Persuaders was originally published on 10 February 2009. A summary (taken from the LW wiki):
> A purely hypothetical scenario about a world containing some authors trying to persuade people of a particular theory, and some authors simply trying to sh... |
03983fd8-c736-49c6-a559-57e8f4c00540 | StampyAI/alignment-research-dataset/arxiv | Arxiv | AI safety via debate
1 Introduction
---------------
Learning to align an agent’s actions with the values and preferences of humans is a key challenge in ensuring that advanced AI systems remain safe [Russell et al., [2016](#bib.bib1)]. Subtle problems in alignment can lead to unexpected and potentially unsafe behav... |
0d1a7a1b-d7e9-4137-83f8-33fa2126b32b | trentmkelly/LessWrong-43k | LessWrong | Wanna bet?
For our November meetup, the Chicago Rationality group is focusing on predictions markets, and more generally on the practice of betting on beliefs. As part of this, we have a "homework assignment" for the meetup: each of us is trying to make at least one bet before the meetup happens. This turns out to be... |
38cca289-4b77-4be0-8c75-ef39123d4612 | trentmkelly/LessWrong-43k | LessWrong | Do we automatically accept propositions?
Epistemic Status: Exploratory (I'm searching for an expert or someone who has studied and rigorously investigated these claims/essays, as I intend to, but time doesn't permit me now)
16 years ago, Eliezer asked "Do we Believe Everything we're told?"
This was with respect to ... |
b98c5e0c-c141-46cf-a809-fe8c78d41933 | trentmkelly/LessWrong-43k | LessWrong | Optimizing your Social Network
From Crowdsourcing The Availabiliy Hueristic:
> There are people who already utilize their social network to the utmost, and who expand it strategically, adding people just to enhance the diversity of available viewpoints. But I will take a chance, and state that most of us probably don... |
e5e311cf-fc7f-4da1-a3b2-d1476acebf55 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Updating my AI timelines
Earlier this year [I offered to bet people who had short AI timelines](https://www.lesswrong.com/posts/X3p8mxE5dHYDZNxCm/a-concrete-bet-offer-to-those-with-short-ai-timelines).
While it wasn't my intention to be known as "a long AI timelines guy", I have begun feeling that was how people perc... |
9280ec03-46db-43ce-8ead-a5c8cac1fab9 | trentmkelly/LessWrong-43k | LessWrong | The algorithm isn't doing X, it's just doing Y.
Introduction
Mutual reduction implies equivalence
Here's my most load-bearing intuition —
> If two tasks reduce to one another, then it is meaningless to ask if a machine is 'really doing' one task versus the other.
Moreover —
* This intuition grounds my perspectiv... |
0a0fb777-5bb5-4b9e-b904-b5124c89a760 | trentmkelly/LessWrong-43k | LessWrong | Acausal trade barriers
A putative new idea for AI control; index here.
Many of the ideas presented here require AIs to be antagonistic towards each other - or at least hypothetically antagonistic towards hypothetical other AIs. This can fail if the AIs engage in acausal trade, so it would be useful if we could preven... |
e293427a-9772-42ef-bba0-414eedf02c82 | trentmkelly/LessWrong-43k | LessWrong | How easy/fast is it for a AGI to hack computers/a human brain?
If an AGI had to create and hack a computer or a human brain, how easy and how fast would they be able to do it so that it does what the AI wants? |
92fa264a-51a5-4e02-89ed-085e45be8395 | trentmkelly/LessWrong-43k | LessWrong | Key questions about artificial sentience: an opinionated guide
[crossposted at EA Forum and Experience Machines; twitter thread summary]
What is it like to be DALL-E 2? Are today’s AI systems consciously experiencing anything as they generate pictures of teddy bears on the moon, explain jokes, and suggest terrifying ... |
28cd7931-0e32-4997-bdea-1b74ed890179 | trentmkelly/LessWrong-43k | LessWrong | Philosophy by Paul Graham Link
I don't know why this doesn't have link post: http://www.paulgraham.com/philosophy.html It's look like a brilliant explanation which science philosophy has to become. |
ebd00c59-a799-4778-9220-601cad0a0f6c | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Bad at Arithmetic, Promising at Math
n.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%; font-size-adjust: none; letter-spacing: normal; word-wrap: normal; word-spacing: normal; white-space: nowrap; float:... |
c5e97313-a2c4-40a4-9188-b93e1d06e734 | trentmkelly/LessWrong-43k | LessWrong | DC Meetup: Sunday May 1st, 1 PM
Sunday May 1st, 1 PM - 5 PM
Chipotle Mexican Grill
7600 Old Georgetown Road
Bethesda, MD 20814
Hey DC LWers, its about time we started meeting up! (Lurkers welcome)
Goals:
Basically, get to know each other and establish a regularly meeting (and thoroughly awesome) meetup group. I have... |
e55f073e-b389-4a21-96fb-347753f8c697 | trentmkelly/LessWrong-43k | LessWrong | Anthropics and Biased Models
The Fine-tuned Universe Theory, according to Wikipedia is the belief that, "our universe is remarkably well suited for life, to a degree unlikely to happen by mere chance". It is typically used to argue that our universe must therefore be the result of Intelligent Design.
One of the most ... |
8c08a495-c5b9-4700-b3ce-e527e3189eae | trentmkelly/LessWrong-43k | LessWrong | Not for the Sake of Pleasure Alone
Related: Not for the Sake of Happiness (Alone), Value is Fragile, Fake Fake Utility Functions, You cannot be mistaken about (not) wanting to wirehead, Utilons vs. Hedons, Are wireheads happy?
When someone tells me that all human action is motivated by the desire for pleasure, or tha... |
5ae84787-4e4b-464d-aeba-bcd2ff75a3fa | StampyAI/alignment-research-dataset/lesswrong | LessWrong | High-level interpretability: detecting an AI's objectives
*Thanks to Monte MacDiarmid (for discussions, feedback, and experiment infrastructure) and to the Shard Theory team for their prior work and exploratory infrastructure.*
*Thanks to Joseph Bloom, John Wentworth, Alexander Gietelink Oldenziel, Johannes Treuitle... |
26601832-fe20-4345-b8a4-3b6c298157e7 | trentmkelly/LessWrong-43k | LessWrong | Implications of a feelings-first metaphysics?
What would be the implications on decision-making, beliefs, and actions of a metaphysics that is structured as follows?:
1. All beliefs, ideas, actions, etc. are driven by feelings.
2. Reasons are descriptions of feelings.
3. Language fails to fully capture the sensati... |
c40ad696-8451-48a8-8e87-b371b24cfeeb | trentmkelly/LessWrong-43k | LessWrong | Two arguments for not thinking about ethics (too much)
I used to spend a lot of time thinking about formal ethics, trying to figure out whether I was leaning more towards positive or negative utilitarianism, about the best courses of action in light of the ethical theories that I currently considered the most correct,... |
d498e1c7-a63d-4a2e-a451-65a0f7266e06 | trentmkelly/LessWrong-43k | LessWrong | AI community building: EliezerKart
Having good relations between the various factions of AI research is key to achieving our common goal of a good future. Therefore, I proposal an event to help bring us all together: EliezerKart! It is a go karting competition between three factions: AI capabilities researchers, AI ex... |
d096cf6b-e43a-42d0-a1e8-3ed1c8836dd9 | trentmkelly/LessWrong-43k | LessWrong | Parliaments without the Parties
Epistemic status: butterfly idea
Parliaments might be great, but they suffer from a number of problems. For example, in Israel the opposition is refusing to vote for bills they almost unanimously support, in the hope it will bring down the current government.[1] Meanwhile members of al... |
82ccbf9d-8d20-4c91-92de-40d73eff50f1 | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | How doomed is humanity?
The opinions from experts are all over the place, according to [this 2021 survey](https://www.alignmentforum.org/posts/QvwSr5LsxyDeaPK5s/existential-risk-from-ai-survey-results). Michael Aird has collected a [database of existential risk estimates](https://docs.google.com/spreadsheets/d/1W10B... |
995a12bc-2cdb-4617-b767-8396140042af | trentmkelly/LessWrong-43k | LessWrong | Contra Dance Contact Tracing
Many contra dances require everyone to provide their emails for contact tracing. The idea is, if anyone later tests positive for covid everyone can be notified after. While I think this is good to offer, I don't think it should be mandatory.
People have a wide range of ways they're handli... |
09cb863f-eed5-472c-9839-685e37f75ee8 | StampyAI/alignment-research-dataset/special_docs | Other | Sufficient Conditions for Causality to be Transitive.
Sufficient Conditions for Causality to be
Transitive
Joseph Y . Halpern
Cornell University
Computer Science Department
Ithaca, NY 14853
halpern@cs.cornell.edu
http://www.cs.cornell.edu/home/halpern
Abstract
Natural conditions are provided that are sufficient to ensu... |
02b00064-dd2e-4cb5-8984-673a2f25458d | StampyAI/alignment-research-dataset/arxiv | Arxiv | TuringAdvice: A Generative and Dynamic Evaluation of Language Use
1 Introduction
---------------
Language models today are getting ever-larger, and are being trained on ever-increasing quantities of text. For an immense compute cost, these models like T5 Raffel et al. ([2019](#bib.bib39)) and GPT3 Brown et al. ([20... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.