id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
4a60a3f2-58e4-4e5c-a400-de1057e1c448 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] True Sources of Disagreement
Today's post, True Sources of Disagreement was originally published on 08 December 2008. A summary (taken from the LW wiki):
> Yudkowsky's guesses about what the key sticking points in the AI FOOM debate are.
Discuss the post here (rather than in the comments to the origi... |
434ba7e8-8e25-448e-9fc6-730d4df02159 | trentmkelly/LessWrong-43k | LessWrong | Are fully google translated (my own) posts permitted?
I write a lot of notes that i think can be interesting for some LWers. But these notes are in russian, my translate skills is very low and it is very difficult for me, so if i need to translate it myself i never publish it. English->Russian google translate is very... |
d749fd39-9a98-4ae0-b99c-67e6cca7e0c2 | trentmkelly/LessWrong-43k | LessWrong | Welcome to Kansas City SSC Meetup [Edit With Your Details]
(The following are our suggestions for what kind of information is best to include in the welcome post of your group, feel free to replace them with whatever you think is best)
What kind of events does your group usually run? What does it usually do?
How fre... |
245ff595-a4f3-42ff-b601-d95a4a3d33d9 | trentmkelly/LessWrong-43k | LessWrong | A Subtle Selection Effect in Overconfidence Studies
TLDR: The standard methods for studying overconfidence might be overestimating it. In asking people for confidence intervals—the narrowest intervals that they’re confident contain the true value—we’re selecting for the intervals that are most likely to be overestimat... |
874d6fe8-4bdb-4038-be97-62467c14750f | trentmkelly/LessWrong-43k | LessWrong | Meetup : Canberra: the Hedonic Treadmill
Discussion article for the meetup : Canberra: the Hedonic Treadmill
WHEN: 23 January 2015 06:00:00PM (+1100)
WHERE: 108 North Road, Acton, ACT, 0200
I will be giving a brief talk about what does and doesn't make us happier in the long run, introducing the idea of the 'hedoni... |
081a7322-0031-448b-a55e-c00a16d27373 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Why isn't there a Charity Entrepreneurship program for AI Safety?
My intuition is that there are heaps of very talented people interested in AI Safety but 1/100 of the jobs.
A second intuition I have is that the rejected talent WON'T spillover into other cause areas much (biorisk, animal welfare, whatever) and may ev... |
40b9beb4-0d5a-4f25-8fb6-c3fb43401ec2 | trentmkelly/LessWrong-43k | LessWrong | Hotel Concierge: Shame & Society
As seen in one of Scott's linkdumps. I thought it was interesting enough to deserve discussion here.
Scott's comment:
> Hotel Concierge, everyone’s favorite Tumblr cultural commentator who is definitely not secretly The Last Psychiatrist, has another magnum opus out – Shame And Soci... |
e520dc8e-aacf-4ff4-92dc-997c28213bba | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Machine Unlearning Evaluations as Interpretability Benchmarks
Interpreting Models by Ablation. Image generated by DALL-E 3.Introduction
============
Interpretability in machine learning, es... |
e2ba8a38-dbea-4e30-82d5-68673a148f1d | trentmkelly/LessWrong-43k | LessWrong | Failed Vegan Choux Experiments
Many kinds of pastry can be made vegan quite easily. Puff pastry, which is thin layers of dough and fat, works very well with various plant-based fats and pre-made puff sheets are very often vegan. Lately, however, I've been excited about choux pastry.
Choux pastry is what makes eclairs... |
abe91f6a-f8ac-4af9-b412-25a584c6ca0f | trentmkelly/LessWrong-43k | LessWrong | Maybe Social Anxiety Is Just You Failing At Mind Control
Epistemic Status: I'm about 90% certain that what I'm saying is true as regards to me, and 10% that attempting to do what I'm doing actually leads any specific person to similar results as mine (the priors are just really rough here). Heavy on anecdotal evidenc... |
9d024d82-f420-4223-b452-dc3a8eabbb70 | trentmkelly/LessWrong-43k | LessWrong | Subject X17's Surgery
Edit: For an in-depth discussion of precisely this topic, see Nick Bostrom and Anders Sandberg's 2008 paper "The Wisdom of Nature: An Evolutionary Heuristic for Human Enhancement", available as a pdf here. This post was written before reading the paper.
There doesn't seem to be a thread discuss... |
a6db0314-362c-499c-a479-4780165ac34a | trentmkelly/LessWrong-43k | LessWrong | Agents that don't become maximisers
Cross-posted at the Intelligent Agent forum.
According to the basic AI drives thesis, (almost) any agent capable of self-modification will self-modify into an expected utility maximiser.
The typical examples are the inconsistent utility maximisers, the satisficers, unexploitable a... |
6d845281-16d0-4bd0-b085-88507d31b8b4 | trentmkelly/LessWrong-43k | LessWrong | Repairing Yudkowsky's anti-zombie argument
Eliezer Yudkowsky argues with David Chalmers here on the subject of “philosophical zombies”. I submit that, although Yudkowsky’s position on this question is correct, his argument fails to establish what he claims it to.
To summarise Yudkowsky and Chalmers’s argument:
1. Bo... |
2a1616f1-5287-4906-9464-54438fb61d83 | StampyAI/alignment-research-dataset/blogs | Blogs | Christiano, Cotra, and Yudkowsky on AI progress
This post is a transcript of a discussion between Paul Christiano, Ajeya Cotra, and Eliezer Yudkowsky on AGI forecasting, following up on Paul and Eliezer’s [“Takeoff Speeds” discussion](https://www.lesswrong.com/posts/yMwpoiREvRyNbMjG8/yudkowsky-and-christiano-discuss-t... |
6b0a3b5c-3596-4e9a-b622-fd049453ae20 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Jailbreaking ChatGPT on Release Day
ChatGPT is a lot of things. It is by all accounts quite powerful, especially with engineering questions. It does many things well, such as engineering prompts or stylistic requests. Some [other things](https://twitter.com/dggoldst/status/1598317411698089984), [not](https://twitter.c... |
af071dd2-2e39-4cc2-b6f9-73ebba2d4841 | trentmkelly/LessWrong-43k | LessWrong | A great articulation of why people find it hard to adopt a naturalistic worldview
|
a5314f13-d298-4050-b7fa-138ed415551e | trentmkelly/LessWrong-43k | LessWrong | Buridan's ass and the psychological origins of objective probability
[Crossposted]
The medieval philosopher Buridan reportedly constructed a thought experiment to support his view that human behavior was determined rather than “free”—hence rational agents couldn’t choose between two equally good alternatives. In the ... |
1019f96f-85d3-4686-9a9d-eeb1e8fb468f | trentmkelly/LessWrong-43k | LessWrong | Drone Wars Endgame
1. Introduction
It is probably becoming clear to anyone who follows war lately, especially the Ukraine conflict that automatic weapons, especially drones are rapidly changing what weapons and tactics are effective.
The purpose of this article is to first consider how a fully autonomous force with ... |
45ff0069-42b5-4704-b514-1d4a00e301c9 | trentmkelly/LessWrong-43k | LessWrong | [Exploratory] Exploratory Writing Info
TL;DR - As an experiment I will post the unedited notes that I generate when thinking about something, to see if they are useful to people. The titles of such posts will be prefixed with '[Exploratory]'. I am not even gonna check for spelling, and I am very bad at spelling.
Comp... |
d6094814-147a-4c37-99bf-f6a61910b069 | trentmkelly/LessWrong-43k | LessWrong | Alignment is not enough
This post is a linkpost for my substack article.
Substack link: https://coordination.substack.com/p/alignment-is-not-enough
----------------------------------------
I think alignment is necessary, but not enough for AI to go well.
By alignment, I mean us being able to get an AI to do what... |
18b1bf18-5844-4e6f-91b8-261cc51e7427 | trentmkelly/LessWrong-43k | LessWrong | Will we survive if AI solves engineering before deception?
Google's AlphaEvolve has recently started to make real world scientific discoveries, but only in domains where it's very cheap to verify the correct answer (e.g. matrix multiplication algorithms).
But if we can design sufficiently powerful physics simulations... |
6ae5c222-47e9-4e2c-8738-0f8bd26e49ef | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | How does "chain-of-thought" prompting work?
[Chain-of-thought prompting](https://ai.googleblog.com/2022/05/language-models-perform-reasoning-via.html) refers to techniques which make a language model generate intermediate reasoning steps in its output. These prompting methods can help a model give accurate answers to ... |
0fbf6bbc-d585-4c08-b9f8-8c65dea47433 | trentmkelly/LessWrong-43k | LessWrong | Goal completion: algorithm ideas
A putative new idea for AI control; index here.
This post will be extending ideas from inverse reinforcement learning (IRL) to the problem of goal completion. I'll be drawing on the presentation and the algorithm from Apprenticeship Learning via Inverse Reinforcement Learning (with on... |
eb9e0cd7-829e-42f9-98ad-5d727e72ea30 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | A Year of AI Increasing AI Progress
In July, I made [a post](https://www.lesswrong.com/posts/W3tZacTRt4koHyxbr/examples-of-ai-increasing-ai-progress) about AI being used to increase AI progress, along with [this spreadsheet](http://rsi.thomaswoodside.com/) that I've been updating throughout the year. Since then, I hav... |
edcbc58f-8d4a-4ee8-8fd0-dc3119d5effb | trentmkelly/LessWrong-43k | LessWrong | No negative press agreement
Original post: http://bearlamp.com.au/no-negative-press-agreement/
What is a no negative press agreement?
A no negative press agreement binds a media outlet's consent to publish information provided by a person with the condition that they be not portrayed negatively by the press.
Why w... |
03cf3d99-aa78-4681-a326-68cb6b7eafc4 | trentmkelly/LessWrong-43k | LessWrong | Laplace Approximation
The last couple posts compared some specific models for 20000 rolls of a die. This post will step back, and talk about more general theory for Bayesian model comparison.
The main problem is to calculate P[data|model] for some model. The model will typically give the probability of observed data ... |
70cebb18-98c5-4ba5-9832-efc02ed6384d | StampyAI/alignment-research-dataset/arxiv | Arxiv | Posterior calibration and exploratory analysis for natural language processing models
###
1 Introduction
Natural language processing systems are imperfect.
Decades of research have yielded analyzers that mis-identify named entities,
mis-attach syntactic relations,
and mis-recognize
noun phrase coreference
anywhere... |
69d98f80-8398-4e79-8d99-5ae8c4ac3caf | trentmkelly/LessWrong-43k | LessWrong | On passing Complete and Honest Ideological Turing Tests (CHITTs)
[Cross-posted from Facebook]
"In the moment when I truly understand my enemy, understand him well enough to defeat him, then in that very moment I also love him. I think it’s impossible to really understand somebody, what they want, what they believe, a... |
52308ec3-939c-492a-bae7-2de90cc9651d | trentmkelly/LessWrong-43k | LessWrong | The most important step
I have a penchant for the stories of the old, in the era before the Bayesian Enlightment and before the Singers and Cantors surfaced, the days when the students of the Art of Rationality met underground, away from prying eyes.
Without the Sacred Texts to guide them, the disciples of Rationalit... |
6a41eb43-d904-4410-848a-b80d0afdde36 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | What Should the Average EA Do About AI Alignment?
I'm trying to get a handle on what advice to give people who are convinced AI is a problem worthy of their time, \*probably\* the most important problem, but are not sure if they have the talent necessary to contribute.
A trending school of thought is "AI Alignment n... |
75aa82b4-57b9-4bf5-8900-8bfaa837df96 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Some conceptual alignment research projects
Some research outputs I’d love to see, focused on exploring, clarifying and formalizing important alignment concepts. I expect that most of these will be pretty time-consuming, but happy to discuss for people who want to try:
1. A paper which does for [deceptive alignment](... |
c068ea75-26f8-42d0-8795-9e13e5d776fa | trentmkelly/LessWrong-43k | LessWrong | AI #50: The Most Dangerous Thing
In a week with two podcasts I covered extensively, I was happy that there was little other news.
That is, until right before press time, when Google rebranded Bard to Gemini, released an app for that, and offered a premium subscription ($20/month) for Gemini Ultra.
GEMINI ULTRA IS HE... |
c7b137e7-f6e8-4fa4-86a3-717eb57440a7 | trentmkelly/LessWrong-43k | LessWrong | Tracing Typos in LLMs: My Attempt at Understanding How Models Correct Misspellings
This blogpost was created as a part of the AI Safety Fundamentals course by BlueDot Impact. All of the code can be found on my GitHub.
TLDR: I tried to uncover if there are specific components in language models that enable typo correc... |
fc75efe0-d76d-4d66-9994-60c77c5761e6 | trentmkelly/LessWrong-43k | LessWrong | AGI safety from first principles: Conclusion
Let’s recap the second species argument as originally laid out, along with the additional conclusions and clarifications from the rest of the report.
1. We’ll build AIs which are much more intelligent than humans; that is, much better than humans at using generalisable co... |
9d7652b5-33ef-4307-b18e-19af5ad381bf | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Slowing AI: Foundations
**Variables**
=============
**"Slowing AI" is not monolithic. Many interventions have relevant side effects, positive or negative. There are many considerations, desiderata, and goals adjacent to slowing AI,** and different interventions realize them to different degrees**.** This section is a... |
e8fe5869-d2fa-4273-a7e5-e9bbf24bd978 | trentmkelly/LessWrong-43k | LessWrong | How is ARC planning to use ELK?
Let's say we arrive at a worst-case solution for ELK, how are we planning to use it? My initial guess was that ELK is meant to help make IDA viable so that we may be able to use it for some automated alignment-type approach. However, this might not be it. Can someone clarify this? Thank... |
1503b8c8-3044-4c91-a48f-777adcfb1499 | trentmkelly/LessWrong-43k | LessWrong | [LINK] "Straight and crooked thinking," by Robert H. Thouless
This book from 1930 or so (PDF) seems chiefly concerned with describing ways thinking can go wrong. The author does not seem to know much of Bayes, but his book appears largely sound. It ends with practical suggestions for dealing with various "dishonest tr... |
6d4d7670-c7b6-49cf-9fcc-58043c9cccb7 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Introducing Quantum-Like Influence Diagrams for Violations of the Sure Thing Principle
1 Introduction
---------------
In this work, we extend the Quantum-Like Bayesian Network previously proposed by Moreira and Wichert ([2014](#bib.bib19), [2016](#bib.bib20)) by incorporating the framework of expected utility. This... |
ffd0a669-fec9-40af-ae73-e1b2f46c5611 | trentmkelly/LessWrong-43k | LessWrong | Networks of Meaning
> Nearly every piece of fiction that I have written has had at its heart an image of some simple object linking two previously separate clusters of images.[1]
>
> – Gerald Murnane
> The more things an image is joined with, the more often it springs into life.
>
> Dem.: The more other images an i... |
ab0b8982-5630-4d0c-be24-8b905ae23dc6 | trentmkelly/LessWrong-43k | LessWrong | Incentive compatibility and the Revelation Principle
In which the Revelation Principle is introduced, showing all mechanisms can be reduced to incentive compatible mechanisms. With this insight, a solution (of sorts) is given to the public good problem in the last post. Limitations of the Revelation Principle are also... |
0d40a192-28c3-41a9-a7a0-db8037b2d656 | trentmkelly/LessWrong-43k | LessWrong | Getting rational now or later: navigating procrastination and time-inconsistent preferences for new rationalists
This is a distillation of and reflection on O’Donoghue and Rabin’s “Doing it now or later” (see citation below)[1].
Many people struggle with procrastination or self-control. Critically, we struggle with ... |
c86f86f9-e929-412f-8b7d-10bfa5438db5 | trentmkelly/LessWrong-43k | LessWrong | Extreme Security
What makes "password" a bad password?
You might say that it's because everybody else is already using it, and maybe you'd be correct that everybody in the world deciding to no longer use the password "password" could eventually make it acceptable again.
But consider this: if everyone who was using... |
25d98982-7d74-414c-a6fd-7f20e88f20ed | trentmkelly/LessWrong-43k | LessWrong | Working Out in VR Really Works
Epistemic Status: Based almost entirely on my own experience. Also based on some friends here, here, and in real life.
TL;DR: I now need willpower in order to not-workout (!). I wish someone would have told me this a long time ago when I was looking for some workout that would resonate ... |
229d2aad-d3cf-4748-a500-b609eb336ff9 | trentmkelly/LessWrong-43k | LessWrong | Roles are Martial Arts for Agency
A long time ago I thought that Martial Arts simply taught you how to fight – the right way to throw a punch, the best technique for blocking and countering an attack, etc. I thought training consisted of recognizing these attacks and choosing the correct responses more quickly, as wel... |
16d05f24-a0ef-490b-82c8-2b427c25219f | StampyAI/alignment-research-dataset/arxiv | Arxiv | Neural Simplex Architecture
1 Introduction
---------------
Deep neural networks (DNNs) in combination with *reinforcement learning* (RL) are increasingly being used to train powerful *AI agents*. Such agents have achieved unprecedented success in strategy games, including defeating the world champion in Go [[32](#b... |
be7658be-8907-48b2-84a5-77647b4d0f98 | trentmkelly/LessWrong-43k | LessWrong | Can we, in principle, know the measure of counterfactual quantum branches?
In the Many-Worlds Interpretation, the amplitude of the wave function is seen as describing the "measure of existence". We can tell the existence measure of potential future Everett branches, but can we, even in principle, know the measure of e... |
b4791321-4849-46ef-872a-9c0381d37aa4 | trentmkelly/LessWrong-43k | LessWrong | Let Us Do Our Work As Well
As each new writing deadline approaches, I return to The Builders, a poem by Longfellow:
> All are architects of Fate,
> Working in these walls of Time;
> Some with massive deeds and great,
> Some with ornaments of rhyme.
>
> Nothing useless is, or low;
> Each thing in its place is best... |
75471ffa-d5a6-46b7-b924-c545b38db580 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Some Lessons Learned from Studying Indirect Object Identification in GPT-2 small
To learn more about this work, check out the [paper](https://arxiv.org/abs/2211.00593). We assume general familiarity with [transformer circuits](https://transformer-circuits.pub/2021/framework/index.html).
Intro:
------
There isn’t muc... |
0b36c6ca-a408-492b-bae0-84c341a10fe9 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Needed: AI infohazard policy
The premise of AI risk is that AI is a danger, and therefore research into AI might be dangerous. In the AI alignment community, we're trying to do research which makes AI safer, but occasionally we might come up with results that have significant implications for AI capability as well. Th... |
cd609cb1-8586-4ac7-a1f4-2a36fb7541b3 | trentmkelly/LessWrong-43k | LessWrong | Pausing AI Developments Isn't Enough. We Need to Shut it All Down by Eliezer Yudkowsky
New article in Time Ideas by Eliezer Yudkowsky.
Here’s some selected quotes.
In reference to the letter that just came out (discussion here):
> We are not going to bridge that gap in six months.
>
> It took more than 60 years be... |
8fb0e292-73ed-4fda-84b9-516022d12d8e | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post2941
Alignment Newsletter is a weekly publication with recent content relevant to AI alignment around the world. Find all Alignment Newsletter resources here . In particular, you can look through this spreadsheet of all summaries that have ever been in the newsletter. Audio version here (may not be up yet). HI... |
7d318fdb-5cd5-4880-9e77-f9a55a7cdaf2 | trentmkelly/LessWrong-43k | LessWrong | How should AIs update a prior over human preferences?
I've always emphasised the constructive aspect of figuring out human preferences, and the desired formal properties of preference learning processes.
A common response to these points is something along the line of "have the AI pick a prior over human preferences,... |
198a1745-340f-44e2-905e-f191e86a08cf | trentmkelly/LessWrong-43k | LessWrong | Bayesian Collaborative Filtering
I present an algorithm I designed to predict which position a person would report for an issue on TakeOnIt, through Bayesian updates on the evidence of other people's positions on that issue. Additionally, I will point out some potential areas of improvement, in the hopes of inspiring ... |
e2ddd96d-afe5-49ca-8245-8a7994d2fc3a | trentmkelly/LessWrong-43k | LessWrong | Understanding Hidden Computations in Chain-of-Thought Reasoning
Recent work has demonstrated that transformer models can perform complex reasoning tasks using Chain-of-Thought (COT) prompting, even when the COT is replaced with filler characters. This post summarizes our investigation into methods for decoding these h... |
65b5e5a8-9468-4556-88d5-76c01dfb52a4 | trentmkelly/LessWrong-43k | LessWrong | Solstice 2023 Roundup
Many of you are already familiar with Rationalist Winter Solstice, our home-grown winter holiday. As the year grows literally dark, we gather in our respective communities to face various forms of darkness together, to celebrate what light human civilization has made, and to affirm ourselves as ... |
f7f78166-36c4-42c4-8639-cfab984b1ee0 | trentmkelly/LessWrong-43k | LessWrong | Power and difficulty
A specific bias that Lesswrongers may often get from fiction[1] is the idea that power is proportional to difficulty. The more power something gives you, the harder it should be to get, right?
A mediocre student becomes a powerful mage through her terrible self-sacrifice and years of studying ob... |
a8fa5d05-d98b-4c11-9c22-55392b775247 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "I told an intelligent, well-educated friend about Less Wrong, so she googled, and got "Less Wrong is an online community for people who want to apply the discovery of biases like the conjunction fallacy, the affect heuristic, and scope insensitivity in order to fix their own thinking." and gave up immediately because ... |
67c8d2c9-bd67-49ae-9774-cfac224b71bb | trentmkelly/LessWrong-43k | LessWrong | [Link] Quantum theory as the most robust description of reproducible experiments
The paper: http://www.sciencedirect.com/science/article/pii/S000349161400102X
Authors: Hans De Raedt, Mikhail I. Katsnelson, Kristel Michielsen
ABSTRACT
It is shown that the basic equations of quantum theory can be obtained from a stra... |
9ed7eacf-f5fd-49d9-bd3e-17ceb80edbfb | trentmkelly/LessWrong-43k | LessWrong | Betrand Russell's Ten Commandments
Betrand Russell's Ten Commandments for teachers.
> 1. Do not feel absolutely certain of anything.
> 2. Do not think it worth while to proceed by concealing evidence, for the evidence is sure to come to light.
> 3. Never try to discourage thinking for you are sure to succeed.
>... |
82222e51-110d-4cdb-bd52-40fbce8a4e34 | trentmkelly/LessWrong-43k | LessWrong | Cultivate an obsession with the object level
In this third section of the sequence I focus on how to leverage positive motivations—in particular curiosity, agency, and determination—to do great work. While all of these are valuable, they’ll suit different people to different degrees. In particular, I think of nerds as... |
1a85a91b-ad52-48d8-a03e-d4a7a010fee1 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | DeepMind x UCL | Deep Learning Lectures | 9/12 | Generative Adversarial Networks
hello everyone and welcome to the next
edition of the UCL deepmind lecture
series I Mahalo I'm a research engineer
at deep mind and a PhD student at UCL
and together with Jeff I'm gonna talk to
you today about generative adversarial
netw... |
edfd5390-ff33-4f2a-bde3-a22598c903c7 | trentmkelly/LessWrong-43k | LessWrong | What does Bing Chat tell us about AI risk?
Image from here via this tweet
ICYMI, Microsoft has released a beta version of an AI chatbot called “the new Bing” with both impressive capabilities and some scary behavior. (I don’t have access. I’m going off of tweets and articles.)
Zvi Mowshowitz lists examples here - hi... |
e6205c63-c44e-4bbf-9e1e-01d7fad0c856 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Washington, D.C.: Book Swap (Postponed Due to Weather)
Discussion article for the meetup : Washington, D.C.: Book Swap (Postponed Due to Weather)
WHEN: 22 February 2015 03:00:00PM (-0500)
WHERE: Reynolds Center
Due to the inclement weather last weekend, meetups are being pushed back a week.
We will be mee... |
4c98d2e4-3015-4b3c-9fd1-e9fac447d392 | trentmkelly/LessWrong-43k | LessWrong | Acausal trade: universal utility, or selling non-existence insurance too late
A putative new idea for AI control; index here.
Other posts in the series: Introduction, Double decrease, Pre-existence deals, Full decision algorithms, Breaking acausal trade, Trade in different types of utility functions, Being unusual, a... |
3a4a5868-ca22-4281-8020-f221a9f12d22 | trentmkelly/LessWrong-43k | LessWrong | Google DeepMind: An Approach to Technical AGI Safety and Security
We have written a paper on our approach to technical AGI safety and security. This post is primarily a copy of the extended abstract, which summarizes the paper. I also include the abstract and the table of contents. See also the GDM blogpost and tweet ... |
f8dad5a6-6d3b-428e-8b44-c232c457ab7b | trentmkelly/LessWrong-43k | LessWrong | How to know whether you are an idealist or a physicalist/materialist
You have heard and perhaps even used the expression "observable universe", right? What is included in the purportedly observable universe? The moon? The whole of the moon? If you had heard the expression "observable universe" a century ago, would you... |
6980fb77-6aa3-4220-a337-0eab02b3a29a | trentmkelly/LessWrong-43k | LessWrong | LW-ish meetup in Boulder, CO
This Saturday I'm giving a presentation at the Boulder Future Salon, topic will be non-religious spirituality. The more LWians that can make it the better, because I'm really trying to get some community building done in the Boulder/Denver area. There's an insane amount of potential here.
... |
6e1970d3-5220-408a-8261-7c6a085f8062 | trentmkelly/LessWrong-43k | LessWrong | Project Ideas for the London Hackday
So, the London community is arranging a Hackday where some of us will get together and code. In order to ensure we work on the awesomest idea(s) possible, we decided to ask LessWrong to add to our list of candidates. So here is the question:
What could a few developers do in a day... |
30596fe0-c88f-4576-a91f-5fef2c25dae3 | trentmkelly/LessWrong-43k | LessWrong | The Ethics of Eating Seafood: A Rational Discussion
Introduction
The ethics of eating seafood is an increasingly pertinent topic in the realm of animal welfare and environmental sustainability. As rationalists, it is essential to examine the impact of our dietary choices on sentient beings and the planet. This post a... |
a38765f0-967e-48c4-bcc6-981d2270e767 | trentmkelly/LessWrong-43k | LessWrong | The Argument from Witness Testimony
(Note: This is essentially a rehash/summarization of Jordan Sobel's Lotteries and Miracles - you may prefer the original.)
George Mavrodes wrote an interesting analogy. Scenario 1: Suppose you read a newspaper report claiming that a particular individual (say, Henry Plushbottom of ... |
78d39fc9-8624-4047-8c7c-55cbe566779c | trentmkelly/LessWrong-43k | LessWrong | ToL: Introduction
(These are the touched up notes from a class I took with CMU's Kevin Kelly this past semester on the Topology of Learning. Only partially optimized for legibility)
Feasibility Contextualism
A large amount of philosophy has been people trying to demonstrate how you can never really know anything [ci... |
475b65d0-8e0b-4d49-9095-88d4af277ad0 | trentmkelly/LessWrong-43k | LessWrong | Summary: "Imagining and building wise machines: The centrality of AI metacognition" by Johnson, Karimi, Bengio, et al.
Details:
Original paper
Paper Authors:
Samuel G. B. Johnson, Amir-Hossein Karimi, Yoshua Bengio, Nick Chater, Tobias Gerstenberg, Kate Larson, Sydney Levine, Melanie Mitchell, Iyad Rahwan, Bernhard ... |
005790e6-085e-4ca7-925e-28389d7fabcd | trentmkelly/LessWrong-43k | LessWrong | Fun with bitstrings and bijections
Here's a quick math/coding puzzle with a cute solution. |
776cf4c4-d36b-454c-a30d-4d619f6c0d97 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Metareasoning for Planning Under Uncertainty
1 Introduction
---------------
Offline probabilistic planning approaches, such as policy iteration [[Howard1960](#bib.bibx15)], aim to construct a policy for every possible state before acting. In contrast, online planners, such as RTDP [[Barto et al.1995](#bib.bibx1)] a... |
e6629bb5-3496-4755-a659-cfe63d588221 | StampyAI/alignment-research-dataset/arxiv | Arxiv | A Psychopathological Approach to Safety Engineering in AI and AGI
1 Introduction
---------------
While the adaptive mechanisms of human cognition provide the means for unique skills in adjusting to dynamic environments, they are also prone to psychological disorders, broadly defined as self-reconfigurations in cogn... |
88d04436-81a6-4141-ba63-41f5edbba38a | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Conclusion to 'Reframing Impact'
Introduction
============
Transformer models are incredibly powerful for natural language tasks (and they are starting to find uses in many othe... |
d3ce16a0-3e11-4ae0-88d4-190c0f8b3ae9 | trentmkelly/LessWrong-43k | LessWrong | Pacing Outside the Box: RNNs Learn to Plan in Sokoban
Work done at FAR AI.
There has been a lot of conceptual work on mesa-optimizers: neural networks that develop internal goals that may differ from their training objectives (the inner alignment problem). There is an abundance of good ideas for empirical work (find ... |
293e2be9-2753-44ce-aa1c-7482e02ad5ad | trentmkelly/LessWrong-43k | LessWrong | My argument against AGI
This is the third post about my argument to try and convince the Future Fund Worldview Prize judges that "all of this AI stuff is a misguided sideshow". My first post was an extensive argument that unfortunately confused many people.
(The probability that Artificial General Intelligence will ... |
0a1f00e1-4d30-487c-a43a-b05768353fcc | trentmkelly/LessWrong-43k | LessWrong | Harry Potter in The World of Path Semantics
This is a short story written with help from ChatGPT, about the intuition behind counter-examples to Leibniz' first principle. This is generally believe to be true among logicians, but the equality as it is expressed in Leibniz' first principle is just an assumption about eq... |
6dbaa28e-dc7c-4d98-8be0-98af691f8d49 | trentmkelly/LessWrong-43k | LessWrong | Open thread, 16-22 June 2014
Previous open thread
If it's worth saying, but not worth its own post (even in Discussion), then it goes here.
Notes for future OT posters:
1. Please add the 'open_thread' tag.
2. Check if there is an active Open Thread before posting a new one.
3. Open Threads should be posted ... |
3cea7b13-12dd-452d-b2d6-860f0ae822ca | StampyAI/alignment-research-dataset/blogs | Blogs | 2020-21 New Year review
This is an annual post reviewing the last year and making resolutions and predictions for next year. 2020 brought a combination of challenges from living in a pandemic and becoming a parent. Other highlights include not getting sick, getting a broader perspective on my life through decluttering... |
5e2431db-fd26-4d58-8e46-43869083e9ea | StampyAI/alignment-research-dataset/arxiv | Arxiv | Reinforcement Learning with Action-Free Pre-Training from Videos.
1 Introduction
---------------
Deep reinforcement learning (RL) has made significant advance in solving various sequential decision-making problems (mnih2015human; levine2016end; silver2017mastering; vinyals2019grandmaster; berner2019dota; akkaya2019... |
f8cd93a8-02fb-4f75-8fc4-bc71c1d416bc | trentmkelly/LessWrong-43k | LessWrong | Fun, endless art debates v. morally charged art debates that are intrinsically endless
Discussing art is fun. It's a great pastime. There's a number of very simple art criticism questions we will never answer but are often very fun to discuss for specific artists or performers we care about. AI-assisted, some are:
1... |
ac9749f8-4ac1-456f-9c7d-03ccc7909032 | trentmkelly/LessWrong-43k | LessWrong | Case studies on social-welfare-based standards in various industries
Last year, I posted a call for case studies on social-welfare-based standards for companies and products (including standards imposed by regulation). The goal was to gain general context on standards to inform work on possible standards and/or regula... |
8d1de67e-f514-4622-aca1-8819845b8ba6 | trentmkelly/LessWrong-43k | LessWrong | Toward a taxonomy of cognitive benchmarks for agentic AGIs
Inspired by the sequence on LLM Psychology, I am developing a taxonomy of cognitive benchmarks for measuring intelligent behavior in LLMs. This taxonomy could facilitate understanding of intelligence to identify domains of machine intelligence that have not be... |
457fc4ce-a462-4f62-b847-dba2472fe71e | trentmkelly/LessWrong-43k | LessWrong | Safety Implications of LeCun's path to machine intelligence
Yann LeCun recently posted A Path Towards Autonomous Machine Intelligence, a high-level description of the architecture he considers most promising to advance AI capabilities.
This post summarizes the architecture and describes some implications for AI safe... |
715ea708-75c8-4846-8a9b-4d8dcb94cc2f | trentmkelly/LessWrong-43k | LessWrong | Meetup : West LA: Practical Rationality Sources
Discussion article for the meetup : West LA: Practical Rationality Sources
WHEN: 15 July 2015 07:00:00PM (-0700)
WHERE: 11066 santa monica avenue, LA, CA
How to Find Us: Go into this Del Taco. We will be in the back room if possible.
Parking is free in the lot out fr... |
f979febe-4d73-4964-a9ff-350a9a73120c | trentmkelly/LessWrong-43k | LessWrong | Highlights from "Integral Spirituality"
Cross-posted from Map and Territory
Apologia
A couple months ago a friend gifted me a copy of Ken Wilber's Integral Spirituality. At first I was skeptical about reading it: I'm pretty busy and didn't have much context to think I would learn from it. But he talked me into it, p... |
2e4cd924-2290-43fa-9f07-5c00659e7d1e | trentmkelly/LessWrong-43k | LessWrong | Duncan Sabien: "In Defense of Punch Bug"
Cool new post from Duncan Sabien (formerly active here under that name and Conor_Moreton). |
99c31615-ee61-411d-85bc-2c85eb7f166e | trentmkelly/LessWrong-43k | LessWrong | Slate Star Codex: alternative comment threads on LessWrong?
Like many Less Wrong readers, I greatly enjoy Slate Star Codex; there's a large overlap in readership. However, the comments there are far worse, not worth reading for me. I think this is in part due to the lack of LW-style up and downvotes. Have there ever b... |
02c53574-68f7-426f-aa91-6252b3a887d8 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | "Diamondoid bacteria" nanobots: deadly threat or dead-end? A nanotech investigation
*Confidence level: I’m a computational physicist working on nanoscale simulations, so I have some understanding of most of the things discussed here, but I am not specifically an expert on the topics covered, so I can’t promise perfec... |
c1514615-8f2b-4563-be8f-6f0c7718463f | trentmkelly/LessWrong-43k | LessWrong | Read the Roon
Roon, member of OpenAI’s technical staff, is one of the few candidates for a Worthy Opponent when discussing questions of AI capabilities development, AI existential risk and what we should do about it. Roon is alive. Roon is thinking. Roon clearly values good things over bad things. Roon is engaging wit... |
7d4da025-166b-4841-97ad-5be667507270 | StampyAI/alignment-research-dataset/special_docs | Other | Introducing the Unrestricted Adversarial Examples Challenge
Posted by Tom B. Brown and Catherine Olsson, Research Engineers, Google Brain Team
Machine learning is being deployed in more and more real-world applications, including [medicine](https://ai.googleblog.com/2018/07/automating-drug-discoveries-using.html)... |
50935ea8-851a-414d-b3cf-affe1bd82a1c | trentmkelly/LessWrong-43k | LessWrong | Take my Job
In September I am going to leave the company where I worked for last four years. I am going to get married, go on a honeymoon, and then leave my wife for two months to travel extensively in Colombia and Peru. If anyone from that part of the world reads this, holla at me!
I want to tell you about the job I... |
1c7a079d-ae9f-4259-b42b-c9577f6caef1 | trentmkelly/LessWrong-43k | LessWrong | [link] NASA Telescope Confirms Alien Planet in Habitable Zone
Not a good sign
http://news.yahoo.com/nasa-telescope-confirms-alien-planet-habitable-zone-162005358.html
|
c36b5422-e343-4d4b-98e8-8068bd519d22 | trentmkelly/LessWrong-43k | LessWrong | Simple investing for a complete beginner? (Just… developing world index funds?)
[EDIT: Through conversation with Rolf Andreassen below, it has been brought to my attention that I am simply completely and irretrievably insane.
Sane and well-measured advice is therefore wasted on me, and I just wanted to edit in this n... |
c63d6789-16f7-45cc-b805-861a9af0f59e | trentmkelly/LessWrong-43k | LessWrong | Morale management for entrepreneurs
One of the odd things about the procrastination equation is that part of it resembles an expected value calculation: value * expectancy. Why does the equation's numerator present a problem at all then, if it's just the expected value of what you're trying to do? Shouldn't that be ... |
0880ad91-3c9f-4c57-a274-f7f2a7ff4c1f | trentmkelly/LessWrong-43k | LessWrong | Modal Chicken
I thought it might be good fun to try doing modal chicken. This is my first time getting into the dirty technical details of MIRI's research, so do tolerate and point out misunderstandings.
Chicken is a game where two drivers drive towards each other on a collision course: one must swerve, or both di... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.