id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
cdb2c982-9700-424a-b8f8-cc6605ebb17a | trentmkelly/LessWrong-43k | LessWrong | Endogenous Epinephrine for Anaphylaxis?
Content warning: discussion of allergy attacks.
Epistemic warning: I know very little and this is total speculation. Don't do anything in this post unless this becomes the recommended way of dealing with allergy attacks.
Imagine you're walking in a remote area with someone who... |
030185ac-63f1-4b20-af28-42f025492ae8 | trentmkelly/LessWrong-43k | LessWrong | Google lends further legitimacy to Bitcoin
Though not yet an "official" project, Google has released a Bitcoin client. As you may remember, there were concerns here about what the government/legal reaction to Bitcoin [1] will be, and the significance of certain groups lending their support to it. EFF and SIAI accept ... |
16a2989f-4f0a-4ea3-85fe-13b48e2ec6a0 | StampyAI/alignment-research-dataset/arbital | Arbital | Symmetric group
The notion that group theory captures the idea of "symmetry" derives from the notion of the symmetric group, and the very important theorem due to Cayley that every group is a subgroup of a symmetric group.
# Definition
Let $X$ be a [https://arbital.com/p/-3jz](https://arbital.com/p/-3jz). A [bijecti... |
d2c5e066-370b-4393-8f0d-2d91b99b92d7 | trentmkelly/LessWrong-43k | LessWrong | Proposal: Anti-Akrasia Alliance
*Related to: [Kicking Akrasia: now or never](http://lesswrong.com/r/discussion/lw/3ko/kicking_akrasia_now_or_never/); [Tsuyoku Naritai](http://lesswrong.com/lw/h8/tsuyoku_naritai_i_want_to_become_stronger/)*
# The situation
I am greatly afficted by akrasia, and in all probabilit... |
439656d9-f356-4356-a3ea-a4393433fed6 | trentmkelly/LessWrong-43k | LessWrong | Good Research Takes are Not Sufficient for Good Strategic Takes
TL;DR Having a good research track record is some evidence of good big-picture takes, but it's weak evidence. Strategic thinking is hard, and requires different skills. But people often conflate these skills, leading to excessive deference to researchers ... |
96949d2c-b023-4ea8-9918-52eee1653098 | trentmkelly/LessWrong-43k | LessWrong | Marsh et al. "Serotonin Transporter Genotype (5-HTTLPR) Predicts Utilitarian Moral Judgments"
The whole paper is here. In short, they found a genotype that predicts people's response to the original trolley problem:
> A trolley (i.e. in British English a tram) is running out of control down a track. In its path are ... |
d08f5897-1c43-4602-afcc-bc33e5ae5da2 | trentmkelly/LessWrong-43k | LessWrong | The case for aligning narrowly superhuman models
I wrote this post to get people’s takes on a type of work that seems exciting to me personally; I’m not speaking for Open Phil as a whole. Institutionally, we are very uncertain whether to prioritize this (and if we do where it should be housed and how our giving should... |
18e9b5b3-769f-442c-8599-d97d9b8476a0 | trentmkelly/LessWrong-43k | LessWrong | Book Review: All I Want To Know Is Where I'm Going To Die So I'll Never Go There
Introduction
The pope asked Michelangelo: "Tell me the secret of your genius".
How have you created the statues of David, the masterpiece of all masterpieces?
Michelangelo's answer: " It is simple. I removed everything that is not David... |
6f8e3146-015d-4dfd-b2ca-55bfb1c3bae3 | trentmkelly/LessWrong-43k | LessWrong | Jaynesian interpretation - How does “estimating probabilities” make sense?
In Professor Jaynes’ theory of probability, probability is the degree of plausibility about a thing given some knowledge and not an physical property of that thing.
However, I see people treating the probability of heads in a coin flip as a pa... |
fd534c77-3e00-473a-8bde-96ea84a3f83b | trentmkelly/LessWrong-43k | LessWrong | Two easy things that maybe Just Work to improve AI discourse
So, it seems AI discourse on X / Twitter is getting polarised. This is bad. Especially bad is how some engage in deliberate weaponization of discourse, for political ends.
At the same time, I observe: AI Twitter is still a small space. There are often impo... |
4047dc1f-fb30-40ba-9058-f8b027e00f36 | trentmkelly/LessWrong-43k | LessWrong | Status quo bias is usually justified
Generally, we know more about the status quo then about anything else.
* We know that we can live in the current climate, we don’t know that about any other climate.
* We know that society functions with current laws and norms, we don’t know that about any other set of laws.
Of... |
c1fee948-1b67-4082-8a6d-fe6a41aad530 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | What can we learn from Lex Fridman’s interview with Sam Altman?
These are my personal thougths [about this interview](https://www.youtube.com/watch?v=L_Guz73e6fw).
*Epistemic status: I neither consider myself a machine-learning expert, nor am I an alignment expert.* [*My focus*](https://docs.google.com/document/d/1P... |
1f9ca408-9460-495b-afb0-b90b91c15b76 | trentmkelly/LessWrong-43k | LessWrong | Clarifying what ELK is trying to achieve
(Basic familiarity with ELK required.)
I noticed that some people who haven’t thought that much about ELK yet (including my former self) are confused about (1) why the ELK setup is structured how it is structured and what we want to achieve, and relatedly (2) what's the underl... |
4af68460-aa5a-4915-b2c1-625aa066ee75 | trentmkelly/LessWrong-43k | LessWrong | Would a scope-insensitive AGI be less likely to incapacitate humanity?
I was listening to Anders Sandberg talk about "humble futures" (i.e., futures that may be considered good in a sober non-"let's tile the universe with X" way), and started wondering whether training (not yet proven safe) AIs to have such "humble" s... |
3d1e395b-d75d-4e28-81c6-e3ddea10e14b | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Bayesian Judo
Today's post, Bayesian Judo, was originally published on 31 July 2007. A summary (taken from the LW wiki):
> You can have some fun with people whose anticipations get out of sync with what they believe they believe. This post recounts a conversation in which a theist had to backpedal when he... |
065e1f1b-c208-43cf-b445-a3364146ea8f | trentmkelly/LessWrong-43k | LessWrong | Ngo's view on alignment difficulty
This post features a write-up by Richard Ngo on his views, with inline comments.
Color key:
Chat Google Doc content Inline comments
13. Follow-ups to the Ngo/Yudkowsky conversation
13.1. Alignment difficulty debate: Richard Ngo's case
[Ngo][9:31] (Sep. ... |
e3dd6520-bf50-44b6-9ceb-79f6826b47d5 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Human priors, features and models, languages, and Solmonoff induction
This post was originally inspired by Robin Hanson's publication "[Uncommon Priors Require Origin Disputes](https://www.researchgate.net/publication/5158932_Uncommon_Priors_Require_Origin_Disputes), but it took a left turn and brought in Solmonoff in... |
f5250e5a-0cfd-44cd-b219-a9b3d0e676b2 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Related to: Shane Legg on Prospect Theory and Computational FinanceThis post is on prospect theory partly because it fits the theme of replacing simple utility functions with complicated reward functions, but mostly because somehow Less Wrong doesn't have any posts on prospect theory yet and that needs to change.Kahne... |
918fee98-cf4f-4481-9d76-f56e0e526abd | trentmkelly/LessWrong-43k | LessWrong | Two hemispheres - I do not think it means what you think it means
I am going to address some misconceptions about brain hemispheres -- in popular culture, and in Zizian theory. The latter, because the madness must stop. The former, because it provided a foundation for the latter.
*
Two hemispheres in popular cultur... |
ec6191ec-3209-4072-828e-e8fc1ddc42d9 | trentmkelly/LessWrong-43k | LessWrong | How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
This post is a copy of the introduction of this paper on lie detection in LLMs. The Twitter Thread is here.
Authors: Lorenzo Pacchiardi, Alex J. Chan, Sören Mindermann, Ilan Moscovitz, Alexa Y. Pan, Yarin Gal, Owain Evans, Jan Brau... |
025584d6-37fc-476f-86fb-d6c65e4d9253 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Moscow: rational review, bias busters, Kolmogorov and Jayes probability
Discussion article for the meetup : Moscow: rational review, bias busters, Kolmogorov and Jayes probability
WHEN: 09 October 2016 02:00:00PM (+0300)
WHERE: Москва, ул. Большая Дорогомиловская, д.5к2
Note: most our members join meetups ... |
6c295787-9111-46ee-a5c9-d3e96fa403c9 | trentmkelly/LessWrong-43k | LessWrong | An interactive introduction to grokking and mechanistic interpretability
Our write up largely agrees with @Quintin Pope's summary, with the addition of training trajectory visualizations and an explanation of the MLP construction that solves modular addition.
A meta note that didn't make it into the article — with ... |
4018a7d2-09c1-4d94-ae91-d0ef848f90f0 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Leveraging Legal Informatics to Align AI
We already face significant challenges communicating our goals and values in a way that reliably directs AI behavior – even without additional technological advancements, which could compound the difficulty with more autonomous systems. Specifying the desirability (*value*) of ... |
893b57d1-6431-4bfa-b57f-961f11df6516 | trentmkelly/LessWrong-43k | LessWrong | Apply to be a mentor in SPAR!
Mentor applications are now open for the Fall 2025 round of the Supervised Program for Alignment Research (SPAR), running from September 15 to December 20, 2025.
Apply as a mentor
SPAR is a remote-first part-time program that connects mentors and mentees for three-month AI safety and gov... |
d5f73b77-940f-4770-9d8f-3b11657866bf | trentmkelly/LessWrong-43k | LessWrong | How Humanity Lost Control and Humans Lost Liberty: From Our Brave New World to Analogia (Sequence Introduction)
In this sequence of posts, we will examine how our global civilization has found itself wandering, staggering, and rocketing through, and now beyond Our Brave New World.
Superintelligences exist and they a... |
f90217df-4226-4712-a7b1-49c23f1aed25 | trentmkelly/LessWrong-43k | LessWrong | The Decreasing Value of Chain of Thought in Prompting
> This is the second in a series of short reports that seek to help business, education, and policy leaders understand the technical details of working with AI through rigorous testing. In this report, we investigate Chain-of-Thought (CoT) prompting, a technique th... |
18b1a688-9070-402b-82d9-51b6920f249b | trentmkelly/LessWrong-43k | LessWrong | Using the Quantified Self paradigma for COVID-19
Petri Hollmén traveled to Tyrol on the 5th of March. He had a bottle of hand sanitizer with him, used it a lot and washed his hands like never before.
Sunday, the 8th he returned home to hear a day afterwards that Tyrol was declared a COVID-19 epidemic area. He decided... |
b9bf05e3-0f23-4603-b00d-a49dc6dd53a6 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | 222. Robot Responsibilities
uh welcome to
the ai safety reading group number 222
this week we're reading artificial
intelligence and robot responsibilities
uh innovating
beyond rights by uttan ash rafiyaan
hutan ash rafiyan is
works at the imperial college of
medicine i believe
uh in the uk and um
uh works as a as a s... |
fa8d1a9b-79fc-42a0-9d02-1a8877d36f08 | trentmkelly/LessWrong-43k | LessWrong | Perverse Independence Incentives
In writing about parenting, I don't write enough about what didn't work: this might give the impression that everything I try works, which is not the case! Here's an example of something that didn't, and which I might have caught before trying if I'd thought a bit more.
Brief recap: I... |
2c2bc913-f4e1-4656-8570-f75229df840b | trentmkelly/LessWrong-43k | LessWrong | Quintin's alignment papers roundup - week 2
Introduction
Last week's paper roundup (more or less by accident) focused mostly on path dependence of deep learning and the order of feature learning. Going forwards, I've decided to have an explicit focus for each week's roundup. This week's focus is on the structure/redun... |
e7456774-3373-4fd2-bf21-5f6e8aae05c0 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Tel Aviv Game Night
Discussion article for the meetup : Tel Aviv Game Night
WHEN: 08 December 2015 07:00:00PM (+0200)
WHERE: Yigal Alon 118, Tel Aviv
We will play board games and have fascinating discussions, as always. Bring your own board games!
If you have trouble finding the place or have other questi... |
8ce998ea-cd0e-4ca2-ad0e-2ed772b0cdd6 | trentmkelly/LessWrong-43k | LessWrong | It's time for a self-reproducing machine
I've wanted to build a self-reproducing machine since I was 17. It's forty-five years later, and it has finally become feasible. (I've done a few other things along the way.) I'm going to describe one such device, and speculate as to its larger implications. It's a pretty de... |
6db099b9-1b23-4bef-81d8-1ad77a7cc58a | StampyAI/alignment-research-dataset/arbital | Arbital | Axiom
An **axiom** of a [theory](https://arbital.com/p/theory_mathematics) $T$ is a [well-formed](https://arbital.com/p/well_formed) [sentence](https://arbital.com/p/sentence_mathematics) in the [language](https://arbital.com/p/language_mathematics) of the theory that we assume to be true without a formal justificatio... |
ebd2439c-59e3-49e7-97c1-0e993e86015c | StampyAI/alignment-research-dataset/arxiv | Arxiv | The Social Cost of Strategic Classification
1 Introduction
---------------
As machine learning increasingly supports consequential decision making, its
vulnerability to manipulation and gaming is of growing concern. When individuals
learn to adapt their behavior to the specifics of a statistical decision rule,
its ... |
bbe1f644-d9b8-4980-bce7-053dad19a677 | trentmkelly/LessWrong-43k | LessWrong | Tsuyoku Naritai
This is the fourth speech in the wedding ceremony of Ruby & Miranda. See the Sequence introduction for more info. The speech was given by Ruby.
----------------------------------------
Riva descends from podium.
Brienne: We have spoken of the horrors that exist, the threats that loom, and the good w... |
0912f769-8c91-415b-b4e7-34078c35bf53 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Intuition
In the [previous post](https://www.lesswrong.com/posts/eCWkJrFff7oMLwjEp/clarifying-factored-cognition), I've said,
>
> [...] in both schemes, Factored Cognition includes a step that is by definition non-decomposable. In Ideal Debate, this is step is judging the final statement. In HCH, it is solving a p... |
6906f93f-a689-408c-8fdf-683e2f928204 | trentmkelly/LessWrong-43k | LessWrong | ELCK might require nontrivial scalable alignment progress, and seems tractable enough to try
Written quickly rather than not at all, I was thinking about this a couple of days ago, and decided to commit to writing something by today rather than adding this idea to my list of a million things to write up.
This post de... |
1951f20f-330d-4575-bce0-3eb5a95460d1 | trentmkelly/LessWrong-43k | LessWrong | Inseparably Right; or, Joy in the Merely Good
Followup to: The Meaning of Right
I fear that in my drive for full explanation, I may have obscured the punchline from my theory of metaethics. Here then is an attempted rephrase:
There is no pure ghostly essence of goodness apart from things like truth, happiness and ... |
94cdf7a0-14ca-4c16-9ae8-b1652c69f54d | trentmkelly/LessWrong-43k | LessWrong | US Presidential Election: Tractability, Importance, and Urgency
Disclaimer: To avoid harmful polarization of important topics, this post is written in a non-partisan manner, and I’d encourage comments to be written with this in mind.
US presidential elections are surprisingly tractable
1. US presidential election... |
38881f56-2e93-4364-833a-4a485763809e | trentmkelly/LessWrong-43k | LessWrong | Effective Altruism 80,000 hours workshop materials & outline (and Feb 10 '19 KC meetup notes)
Intro & overview
This is a brief overview of an "Introduction to 80,000 Hours" workshop written by fellow LessWronger Bae's Theorem. It's to the point - a set of slides & an outline going over 80k hours' key points and core a... |
8d0199d1-1424-494d-8682-e8a128bbd1b8 | trentmkelly/LessWrong-43k | LessWrong | Guidelines for productive discussions
I enjoyed reading Duncan_Sabien's post, Basics of Rationalist Discourse, as well as the response posts and comments. The guidelines probably wouldn't have made sense to my beginner-self though, so I wanted to try creating a list that is more targeted at beginners. In that sense, t... |
65e80d20-c57d-4dbb-9361-aa7280f87fb2 | trentmkelly/LessWrong-43k | LessWrong | Testing the Efficacy of Disagreement Resolution Techniques (and a Proposal for Testing Double Crux)
Introduction
I will describe a procedure for testing the efficacy of disagreement resolution techniques (DRTs) together with methodologies for inducing their use (induction methods). DRTs are structured games (in the lo... |
8362a10a-4fa5-4e68-a8e2-825a9f249415 | trentmkelly/LessWrong-43k | LessWrong | How important are model sizes to your timeline predictions?
I'm thinking of doing a paper for GovAI on model sizes if they matter. Any or all of the following would be helpful:
1) If you found out that the largest published neural net model sizes (by # of parameters) will grow by 10000x in the next 6 years, would tha... |
89e84aa7-f7d3-4158-b0fd-f87815094c15 | trentmkelly/LessWrong-43k | LessWrong | Transferring credence without transferring evidence?
Agent X has evidence for proposition P that agent Y does not have, and X wants to convince Y that P is true (or more precisely, increase Y's credence in P as well). However, there are the following unfortunate conditions:
1) Y doesn't trust X, meaning that X just te... |
41cae1e3-cc1f-4480-af82-e4f9e32af576 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | My Central Alignment Priority (2 July 2023)
*Epistemic status: The further you scroll, the more-important the points are.*
I continue my deconfusion from my [alignment timeline](https://www.lesswrong.com/posts/RTjE6KN2WGepGL6m9/my-alignment-timeline) post. Goal: figure out which sub-problem to work on *first* in AI ... |
b3a94d47-58c8-4575-9eeb-317a4e56595d | trentmkelly/LessWrong-43k | LessWrong | Quick Nate/Eliezer comments on discontinuity
This isn't a proper response to Paul Christiano or Katja Grace's recent writings about takeoff speed, but I wanted to cross-post Eliezer's first quick comments on Katja's piece someplace more linkable than Twitter:
> There's a lot of steps in this argument that need to be ... |
d06c74e6-ae74-4d03-b422-203b1fcd61eb | trentmkelly/LessWrong-43k | LessWrong | On Juvenile Fiction
Follow-up To: On the Care and Feeding of Young Rationalists
Related on OB: Formative Youth
Eliezer suspects he may have chosen an altruistic life because of Thundercats.
Nominull thinks his path to truth-seeking might have been lit by Asimov's Robot stories.
PhilGoetz suggests that Ender's Game... |
ba8fefbb-94d1-4e52-bb32-a1c5ebdde16b | StampyAI/alignment-research-dataset/blogs | Blogs | Superintelligence reading group
Nick Bostrom’s eagerly awaited [*Superintelligence*](http://smile.amazon.com/Superintelligence-Dangers-Strategies-Nick-Bostrom/dp/0199678111/) comes out in the US this week. To help you get the most out of it, MIRI is running an online reading group where you can join with others to ask... |
6f1adf82-6e88-43df-819c-98b6064dc3b9 | trentmkelly/LessWrong-43k | LessWrong | May 2017 Media Thread
This is the monthly thread for posting media of various types that you've found that you enjoy. Post what you're reading, listening to, watching, and your opinion of it. Post recommendations to blogs. Post whatever media you feel like discussing! To see previous recommendations, check out the old... |
6a6958ea-75ad-4824-869f-606143b4cf66 | trentmkelly/LessWrong-43k | LessWrong | Rising rents and appropriate responses
I was recently involved in a discussion related to real estate and rising rents. A friend proposed this policy: "We should limit the extent to which the city can expand, and we should have rent caps so that the prices don't go up." I responded: "That means that purchase prices wi... |
39efc418-df93-48d9-bb04-7a6b5deeba5c | trentmkelly/LessWrong-43k | LessWrong | Watching Myself Program
Michael Malis described an interesting technique for improving his software development workflow:
> One incredibly useful exercise I’ve found is to watch myself program. Throughout the week, I have a program running in the background that records my screen. At the end of the week, I’ll watch a... |
0bb9631c-8e3e-4a5a-8cc5-5c80b2b01290 | trentmkelly/LessWrong-43k | LessWrong | The Doomsday Argument and Self-Sampling Assumption are wrong, but induction is alive and well.
Since the Doomsday Argument still is discussed often on Less Wrong, I would like to call attention to my new, short, self-published e-book, The Longevity Argument, which is a much-revised and much-expanded work that began wi... |
c87137a1-e6fe-4676-8181-d460d123c963 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Think Like Reality
Today's post, Think Like Reality was originally published on May 2, 2007. A summary (from the LW wiki):
> "Quantum physics is not "weird". You are weird. You have the absolutely bizarre idea that reality ought to consist of little billiard balls bopping around, when in fact reality is a... |
93ed0a25-de0b-4325-a882-6a5d2857a15f | trentmkelly/LessWrong-43k | LessWrong | All AGI safety questions welcome (especially basic ones) [Sept 2022]
tl;dr: Ask questions about AGI Safety as comments on this post, including ones you might otherwise worry seem dumb!
Asking beginner-level questions can be intimidating, but everyone starts out not knowing anything. If we want more people in the worl... |
cb9655be-55dd-49e3-9eda-8bacd5dad07c | trentmkelly/LessWrong-43k | LessWrong | A letter on optimism about human progress
This open letter was originally posted on Letter.wiki and is part of a longer conversation with Andrew Glover about sustainability and progress.
Dear Andrew,
Thanks for a thoughtful reply. Reading over it, it seems the biggest difference between us is in our expectations for... |
b750bc5d-420c-4622-bcef-0237521b33c1 | trentmkelly/LessWrong-43k | LessWrong | [Video] Presentation on metacognition contains good intro to basic LW ideas
I attended a talk yesterday given under the auspices of the Ottawa Skeptics on the subject of "metacognition" or thinking about thinking -- basically, it was about core rationality concepts. It was designed to appeal to a broad group of lay p... |
e5418a18-0fbf-4bda-a714-9180fc28e3ab | trentmkelly/LessWrong-43k | LessWrong | Model Thinking class [link]
As part of the expansion of Stanford's effort to open up some of their courseware Scott Page is giving Model Thinking course, which I suspect a lot of people here might like. There is quite a bit of Schelling-type modeling applied to a wide range of problems. The course is live, but it's no... |
e09df34a-7523-4eb3-acae-dcddfa7f475e | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Deontology and Tool AI
Please forgive me for being awkward on my first post, I just wanted to get these ideas out there to facilitate discussion on the topic. I also am sorry if I use any newly-discovered terminology incorrectly, but I am doing my best.
Introduction: Utilitarianism is Unaligned
---------------------... |
2275b8ad-b37d-4b28-a781-8759c2905dff | trentmkelly/LessWrong-43k | LessWrong | The Samurai and the Daimyo: A Useful Dynamic?
The post Slack Club by The Last Rationalist describes a problem in the rationalist community where there is an overabundance of Ender Wiggins: people trying to be clever as a way of avoiding having to do work. HPMOR and other rationalist media lionizes this sort of behavi... |
47ab4bfd-d3b3-494b-8639-80d82ccc4d93 | trentmkelly/LessWrong-43k | LessWrong | What past highly-upvoted posts are overrated today?
I've noticed the quality of LW posts varies greatly, even among top posts. Some of this is subjective or comes from what I want out of LW, but I suspect some posts are not nearly as useful or fun to readers in 2020 as their karma makes them appear.
Answers should be... |
bbd05d45-1e79-43b2-a23b-c6f781bf052a | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Please help me sense-check my assumptions about the needs of the AI Safety community and related career plans
For background and context, see my related series of postson [an approach for AI Safety Movement Building](https://forum.effectivealtruism.org/s/RwtygELTfbRJzcvwD). This is a quick and concise rewrite of the m... |
61ebaad5-ed09-4083-878c-1e2111b70d6f | trentmkelly/LessWrong-43k | LessWrong | Integrity and accountability are core parts of rationality
Epistemic Status: Pointing at early stage concepts, but with high confidence that something real is here. Hopefully not the final version of this post.
When I started studying rationality and philosophy, I had the perspective that people who were in positions... |
33a5abb9-cdc7-48f3-87f3-c54b0c4cc3ca | trentmkelly/LessWrong-43k | LessWrong | The fast takeoff motte/bailey
|
3a080580-aef7-451c-a48d-bb28de4e0844 | trentmkelly/LessWrong-43k | LessWrong | We have the technology required to build 3D body scanners for consumer prices
Apple's iPhone 7 Plus decided to add another lense to be able to make better pictures. Meanwhile Walabot who started with wanting to build a breast cancer detection technology released a 600$ device that can look 10cm into walls. Thermal ima... |
3c355a86-10f4-4f4a-ac8f-b68d9a76e62f | trentmkelly/LessWrong-43k | LessWrong | My version of Simulacra Levels
> People act as if there are four truth-values: True, False, Cringe, and Based.
--David Udell (paraphrase)
This post lays out my own version of the Simulacra Levels idea. Be warned, apparently it is importantly different from the original.
TRUTHTEAMSDeontologicalLevel 1: “Is it true?... |
498a67e8-0bd8-441d-b572-f1cdc209ac12 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Role Architectures: Applying LLMs to consequential tasks
**TL;DR:**
Strong problem-solving systems can be built from AI systems that play diverse roles, LLMs can readily play diverse roles in role architectures, and AI systems based on role architectures can be practical, safe, and effective in undertaking complex a... |
f6de9141-f2ac-4a3f-a427-372b5fc43cdc | trentmkelly/LessWrong-43k | LessWrong | Principles for the AGI Race
Crossposted from https://williamrsaunders.substack.com/p/principles-for-the-agi-race
Why form principles for the AGI Race?
I worked at OpenAI for 3 years, on the Alignment and Superalignment teams. Our goal was to prepare for the possibility that OpenAI succeeded in its stated mission of ... |
23d31175-5a4d-4af1-89c4-b2da336a79e0 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Montreal - How to Actually Change your Mind
Discussion article for the meetup : Montreal - How to Actually Change your Mind
WHEN: 07 January 2014 07:00:00PM (-0500)
WHERE: 459 rue McTavish Montreal Quebec Canada
Montreal Less Wrong won't be meeting officially over the holidays due to several of us having b... |
b330ddf2-1407-41d8-96d2-b5640e4efc06 | trentmkelly/LessWrong-43k | LessWrong | [LINK] Motivational Versus Metabolic Effects of Carbohydrates on Self-Control
> Self-control is critical for achievement and well-being. However, people’s capacity for self-control is limited and becomes depleted through use. One prominent explanation for this depletion posits that self-control consumes energy through... |
5806b5b7-e302-4535-b842-f23c2be3c527 | trentmkelly/LessWrong-43k | LessWrong | Non-poisonous cake: anthropic updates are normal
I am on a quest to show that anthropics probability are normal, at least in the absence of exact duplicates.
So consider this simple example: a coin is tossed. This coin is either fair, is 3/4 biased to heads, or 3/4 biased to tails; the three options are equally likel... |
343d1854-8561-4e5e-9fc7-140a5b1daf18 | trentmkelly/LessWrong-43k | LessWrong | Bayesian Nights (Rationalist Story Time)
Tell us a story. A tall tale for King Solamona, a yarn for the folk of Bensalem, a little nugget of wisdom, finely folded into a parable for the pages.
The game is simple:
1. Choose a bias, a fallacy, some common error of thought.
2. Write a short, hopefully entertaining... |
eeb5de8b-e6eb-4cbb-b9a3-aec2c2281e5c | trentmkelly/LessWrong-43k | LessWrong | Hardened Problems Make Brittle Models
Consider a simple decision problem: you arrange a date with someone, you arrive on time, your partner isn't there. How long do you wait before giving up?
Humans naturally respond to this problem by acting outside the box. Wait a little then send a text message. If that option is ... |
452c3f49-21f5-4a2c-9c7b-63eafdf7c3d1 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Interacting with a Boxed AI
A BOXED AI
==========
So, a thought experiment.
We have an AI-in-a-box. By this I mean:
* The AI can interact with the world only through a single communication channel.
* We control that communication channel.:
+ We can communicate with the AI at will, it can communicate with us only ... |
10b5a62c-f1a9-47e6-a3e8-57aeb96105c9 | trentmkelly/LessWrong-43k | LessWrong | "The Bitter Lesson", an article about compute vs human knowledge in AI
The Bitter Lesson Rich Sutton
The biggest lesson that can be read from 70 years of AI research is that general methods that leverage computation are ultimately the most effective, and by a large margin. The ultimate reason for this is Moore's law,... |
d0497e04-c58c-4107-aa84-24f8de423024 | trentmkelly/LessWrong-43k | LessWrong | Chapter 6: How does it Work?
Finding a path in the Knowledge Graph - that's what this part about.
How works the machine that will provide our signal across the network?
We have only objects activations, connections strengths, and the rule "fire together - wire together." It seems like we need a hint.
I guessed that t... |
76afce59-196b-4bc5-9f48-226db34e9a1e | trentmkelly/LessWrong-43k | LessWrong | Podcast with Oli Habryka on LessWrong / Lightcone Infrastructure
OK sorry to over-advertise but it seemed like this one would be of interest to the LessWrong and EA communities. Episode description below, audio is here, or search for "The Filan Cabinet Habryka" wherever you listen to podcasts.
-----------------------... |
9cc6e06a-e99e-4f65-9838-2fbff8a7feed | trentmkelly/LessWrong-43k | LessWrong | Celiefs
We have "aliefs" and "beliefs" - let me introduce "celiefs": something that we worry *has a high chance of being true*, but aren't quite convinced of.
Often this is something that society/experts/someone you admire says is true, but you don't see the reasoning behind.
We may look for evidence that might conv... |
fc720d43-468f-4459-81b4-c4f97f5b4082 | trentmkelly/LessWrong-43k | LessWrong | INTERVIEW: StakeOut.AI w/ Dr. Peter Park
Hey everyone! This week's episode of the Into AI Safety podcast is an interview with Dr. Peter Park. Along with Harry Luk and one other cofounder, he started StakeOut.AI, a non-profit with the goal of making AI go well, for humans.
Unfortunately, due to funding pressures, the... |
8b822bf8-d4cb-44e9-820f-cd14580692ef | trentmkelly/LessWrong-43k | LessWrong | Frankenstein: A Modern AGI
Epistemic Status: Hopelessly Naïve
Prose: Purple as a bruise
I. A Possible Future
You blink - metaphorically, you don't have eyelids - you don't have eyes either, for all the streams of data that can be decoded into coherent timestamped images flowing through you. You are somewhat shaky ... |
b82dcb7a-98a4-404d-b4c5-10387cb4062c | trentmkelly/LessWrong-43k | LessWrong | 96 Bad Links in the Sequences [fixed]
Follow-up to: 96 Bad Links in the Sequences
Just to let everyone know:
I followed up on my promise to fix all the broken links Alexandros found in the Sequences.
|
8e6fb0f8-a111-41e1-aa4d-3998273af2e7 | trentmkelly/LessWrong-43k | LessWrong | Separation of Concerns
Separation of concerns is a principle in computer science which says that distinct concerns should be addressed by distinct subsystems, so that you can optimize for them separately. We can also apply the idea in many other places, including human rationality. This idea has been written about bef... |
34ac90da-d66e-43ef-a957-8acafeeb01e1 | trentmkelly/LessWrong-43k | LessWrong | A Roadmap to a Post-Scarcity Economy
Background Reading (optional for the discussion)
https://lorenzopieri.com/post_scarcity/
Summary
A post-scarcity society can be defined as a society in which all the basic needs of the population are met and provided for free. A common belief is that moving to such a desirable ... |
ab9ac721-ac3f-4494-94c9-de38ea43868a | trentmkelly/LessWrong-43k | LessWrong | The Most Dangerous Idea
Previously: Epistemic Hell, The Journal of Dangerous Ideas
Scott Mutter
We may safely predict that it will be the timidity of our hypotheses, and not their extravagance, which will provoke the derision of posterity. (H. H. Price)
Introduction
Jeffrey Kripal has written extensively in recent ... |
9dc7cf2d-24d9-44db-a598-8a128e49a2ce | StampyAI/alignment-research-dataset/blogs | Blogs | generalized values: testing for patterns in computation
generalized values: testing for patterns in computation
-------------------------------------------------------
i believe the [True Name](https://www.alignmentforum.org/posts/FWvzwCDRgcjb9sigb/why-agent-foundations-an-overly-abstract-explanation) for our [forma... |
10a234c0-de69-4b75-b7d8-cc01dd6aa58f | StampyAI/alignment-research-dataset/lesswrong | LessWrong | On decision-prediction fixed points
.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: n... |
f9e5f9ab-3312-487c-b144-ef86d038e8b4 | trentmkelly/LessWrong-43k | LessWrong | Review AI Alignment posts to help figure out how to make a proper AI Alignment review
I've had many conversations over the last few years about the health of the AI Alignment field and one of the things that has come up most frequently (including in conversations with Rohin, Buck and various Open Phil people) is that ... |
f701e85f-3e06-4feb-9e77-43e2ad839506 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Discussion article for the meetup : Melbourne, practical rationality
Discussion article for the meetup : Discussion article for the meetup : Melbourne, practical rationality
WHEN: 06 July 2012 07:00:00PM (+1000)
WHERE: Carlton VIC 3053, Australia
WHEN: 06 July 2012 07:00:00PM (+1000)
WHERE: Bens House : S... |
46c81faf-3ea7-46df-b598-22acfb6024aa | trentmkelly/LessWrong-43k | LessWrong | Why we love unimportant things
Consider all the things humans have ever invented. On average, the ones that have been adopted by the most people should be the most useful ones. This seems to be roughly what has happened.
Now consider the ones we get really excited about, and identify with, and celebrate. These are th... |
0fcd97e4-5199-42eb-a0bd-db8a6e836519 | trentmkelly/LessWrong-43k | LessWrong | [Linkpost] Automated Design of Agentic Systems
Authors: Shengran Hu, Cong Lu, Jeff Clune.
Brief summary: proof of concept of automated LM scaffolding design, with state-of-the-art performance on several tasks.
Website: https://www.shengranhu.com/ADAS/.
X/twitter summary thread: https://x.com/jeffclune/status/1825... |
d1df7cdd-2095-4929-9e30-da7f8df5b98c | trentmkelly/LessWrong-43k | LessWrong | [Linkpost] Silver Bulletin: For most people, politics is about fitting in
Nate Silver tries to answer the question: "How do people formulate their political beliefs?"
An important epistemological question that is, he says, under-discussed.
He lays out his theory:
> I think political beliefs are primarily formulated... |
761d4cd0-a37a-4c02-9369-e9170437fd76 | trentmkelly/LessWrong-43k | LessWrong | My Opportunity Costs
When I was younger, I had time and energy to spare on weird side-projects, and a comparative lack of ideas worth spending them on. Now I have some ideas, but no time and energy to spare. I share these ideas below, in case anyone is in the same situation I was a decade ago[1].
Editing Weird Worth... |
0219d4d4-354e-48a2-bd03-e137bb2a3994 | trentmkelly/LessWrong-43k | LessWrong | Knowledge Base 4: General applications
This post presents some possible applications of the general knowledge base that can be built using information management methods described in the post Knowledge Base 2: The structure and the method of building. Applications of the knowledge base constrained to products availabl... |
f3392530-9d81-4e46-a4a4-03829bfbca43 | trentmkelly/LessWrong-43k | LessWrong | For signaling? (Part I)
Your T-shirt is embarrassing. Have you considered wearing a less embarrassing T-shirt?
You are suggesting I spend my precious time trying to look good. Well I am good, and so I’m not going to do that. Because signaling is bad. You can tell something is bad when the whole point of it is to have... |
42b9aa8b-20cf-4775-bbca-49697e7af94d | trentmkelly/LessWrong-43k | LessWrong | The ethics of breaking belief
I'm not sure if this is precisely the correct forum for this, but if there is a better place, I don't know what it would be. At any rate...
I'm a student a Catholic university, and there are (as one might surmise) quite a lot of Catholics here, along with assorted other theists (yes, ... |
7e3aa1e5-4a9d-45cb-901b-7abef3d00704 | StampyAI/alignment-research-dataset/special_docs | Other | Responses to the Journey to the Singularity
Chapter 3
Responses to the Journey
to the Singularity
Kaj Sotala and Roman Yampolskiy
3.1 Introduction
The notion of catastrophic AGI risk is not new, and this concern was expressed by
early thinkers in the field. Hence, there have also been many proposals concerning
what to ... |
1f4b4047-717e-4f06-8a8e-0d9aea93f022 | trentmkelly/LessWrong-43k | LessWrong | The wild
The idea of art about nature doesn’t sound exciting to me in the abstract. Perhaps I remember that I am evolutionarily supposed to see it and go, ‘oh fantastic, it’s green and blue near each other, maybe I’m in for some reproductive success’, and that doesn’t sound very inspiring. (Yes, I know that simple evo... |
92077a7a-2db2-4c20-94f5-0acc3b81a799 | StampyAI/alignment-research-dataset/blogs | Blogs | The Sword of Good
*…fragments of a novel that would never be written…*
---
Captain Selena, late of the pirate ship *Nemesis,* quietly extended the very tip of her blade around the corner, staring at the tiny reflection on the metal. At once, but still silently, she pulled back the sword; and with her other hand... |
0eac5f09-926d-445a-98a1-ac1a09fab116 | trentmkelly/LessWrong-43k | LessWrong | On “COVID-19 Superspreader Events in 28 Countries: Critical Patterns and Lessons”
Analysis of / response to: COVID-19 Superspreader Events in 28 Countries: Critical Patterns and Lessons
The article above, pointed out to me by many good sources, does one of the things we should be doing orders of magnitude more of tha... |
3d0dd5aa-b4db-47e4-8fb7-f8ab73cd3fa4 | trentmkelly/LessWrong-43k | LessWrong | Cognitive mistakes I've made about COVID-19
I think that COVID-19 has been an interesting test of rationality. We’ve faced a novel risk that was initially quite poorly characterized, with the mechanism of transmission unclear, as well as the risk of death or disability from catching it. As such, now that I’m in ‘wait ... |
a1b0d62e-d379-4cd2-90ec-ee28e966345f | StampyAI/alignment-research-dataset/special_docs | Other | Safely Interruptible Agents
Safely Interruptible Agents
Laurent Orseau
Google DeepMind
5 New Street Square,
London EC4A 3TW, UK
lorseau@google.comStuart Armstrong
The Future of Humanity Institute
University of Oxford, UK
stuart.armstrong@philosophy.ox.ac.uk
Machine Intelligence Research Institute
Berkeley, CA 94704
Ab... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.