id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
21cf86b0-2a15-4c50-8333-df579c82b251 | trentmkelly/LessWrong-43k | LessWrong | Meetup Report Thread: February 2014
A month ago, a new type of thread was proposed: a monthly page for meetup reports. The idea is that meetup attendees, or organizers, who wanted to share information about how the meetup went could do so in the comments of this thread. This is so information is dispersed, but without... |
23656f71-194e-448a-8480-8600f8846487 | trentmkelly/LessWrong-43k | LessWrong | Dying for a donation
The most outstanding feature of organ markets is that most people hate the idea. This is a curiosity deserving a second glance. There are organ shortages almost everywhere, with people dying on waiting lists hourly. To sentence them to death based on a cursory throb of disgust is not just uncivili... |
c00ad866-6258-4e0a-b5c9-894eccaa28f0 | trentmkelly/LessWrong-43k | LessWrong | New LW Meetups: Paris, San Francisco
This summary was posted to LW main on January 2nd. The following week's summary is here.
New meetups (or meetups with a hiatus of more than a year) are happening in:
* Paris LW Meetup - LHC Exhibit: 17 January 2015 02:00PM
* San Francisco Meetup: 12 January 2015 06:00PM
Irregu... |
c6b8d7c7-d82f-4a5a-9116-099b77bc73e2 | trentmkelly/LessWrong-43k | LessWrong | AI #83: The Mask Comes Off
We interrupt Nate Silver week here at Don’t Worry About the Vase to bring you some rather big AI news: OpenAI and Sam Altman are planning on fully taking their masks off, discarding the nonprofit board’s nominal control and transitioning to a for-profit B-corporation, in which Sam Altman wil... |
e917deae-f269-4478-9d1f-1f5f897e16ca | trentmkelly/LessWrong-43k | LessWrong | The steering problem
Most work on AI safety starts with a broad, vague problem (“How can we make an AI do good things?”) and relatively quickly moves to a narrow, precise problem (e.g. "What kind of reasoning process trusts itself?“).
Precision facilitates progress, and many serious thinkers are skeptical of imprecis... |
ef3c9bda-a5e7-420d-8bd9-d3f2a2d602bc | StampyAI/alignment-research-dataset/lesswrong | LessWrong | A moral backlash against AI will probably slow down AGI development
*Note 1 : This was posted to EA Forum on May 31* [*here*](https://forum.effectivealtruism.org/posts/veR4W92bZsTsGgS3D/a-moral-backlash-against-ai-will-probably-slow-down-agi)*, as a submission for the 2023 Open Philanthropy AI Worldviews contest, due ... |
cc51ea9a-66af-4503-b39a-1484ec99a24d | StampyAI/alignment-research-dataset/arxiv | Arxiv | Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications
1 Introduction
---------------
\IEEEPARstart
Recently, applications with graph-based data have rapidly increased in many domains such as computer vision [[1](#bib.bib1)], Computer graphics [... |
c7f3bb67-61f6-4c52-9331-3a664f8e0901 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods
Appren ticeship
Learning using Inverse Reinforcement Learning and
Gradient Methods
Gergely Neu¤
Budap
est University of Technology and Economics
M} uegyetem rkp. 3-9.
H-1111 Budapest, HungaryCsaba Szepesv¶ ari¤
Department of Computing Sc... |
d3698656-0184-4154-8c4b-2e3158ffc76a | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post3761
A putative new idea for AI control; index here . Techniques used to counter agents taking biased decisions do not produce uninfluenceable agents . However, using counterfactual tools, we can construct uninfluenceable ˆ P and P , starting from biased and influenceable ones. Why is uninfluenceable necessary... |
4f50412a-6dec-48db-908b-4851aa747455 | StampyAI/alignment-research-dataset/blogs | Blogs | July 2019 Newsletter
Hubinger et al.'s “[Risks from Learned Optimization in Advanced Machine Learning Systems](https://intelligence.org/learned-optimization/)”, one of our new core resources on the alignment problem, is now available on [arXiv](https://arxiv.org/abs/1906.01820), the [AI Alignment Forum](https://www.al... |
1da6d28b-bcd2-449f-b6d0-817f8e1a8a6c | trentmkelly/LessWrong-43k | LessWrong | Effect heterogeneity and external validity in medicine
Our paper "Effect heterogeneity and variable selection for standardizing causal effects to a target population" has just been publised in the European Journal of Epidemiology at https://link.springer.com/article/10.1007/s10654-019-00571-w . While the journal's ver... |
3ec0dd21-5d9b-4b13-b04f-9da16687b2e7 | trentmkelly/LessWrong-43k | LessWrong | Reality has a surprising amount of detail
|
178e1e90-5f85-4891-acf4-703b1a991ee8 | trentmkelly/LessWrong-43k | LessWrong | Why Eat Less Meat?
Previously, I wrote on LessWrong about the preliminary evidence in favor of using leaflets to promote veganism as a way of cost-effectively reducing suffering. In response, there was a large discussion with 530+ comments. In this discussion, I found that a lot of people wanted me to write about w... |
e3bbc57a-f025-4a51-95aa-f1aed1fbb824 | trentmkelly/LessWrong-43k | LessWrong | Omicron Post #3
I have split off the Omicron post from the weekly post, which covers other aspects of Covid. I made judgment calls on where to put a few things.
Omicron continues to spread quickly, but the news surrounding Omicron is clearly slowing down, so these updates can hopefully space out a bit more.
Past Omi... |
bccde405-0fcc-4ac0-b6cf-e85df34388c9 | trentmkelly/LessWrong-43k | LessWrong | The Anthropic Principle Tells Us That AGI Will Not Be Conscious
More specifically, the Anthropic Principle tells us that AGI/TAI are unlikely to be conscious in a world where 1) TAI is achieved, 2) Alignment fails, and 3) the 'prominence' of consciousness scales with either increasing levels of capability or with a gr... |
29cad2e8-1248-47e9-ad1b-4d6e89984af8 | trentmkelly/LessWrong-43k | LessWrong | Free-to-Play Games: Three Key Trade-Offs
Most free-to-play games, especially mobile free-to-play games, use similar models to extract revenue and keep players coming back. These models work by creating toxic trade-offs that are central to their functioning. This post highlights the main three, and will act as referenc... |
7a10660c-851b-4de7-bbd7-40119c46dd19 | trentmkelly/LessWrong-43k | LessWrong | Simultaneously Right and Wrong
Related to: Belief in Belief, Convenient Overconfidence
"You've no idea of what a poor opinion I have of myself, and how little I deserve it."
-- W.S. Gilbert
In 1978, Steven Berglas and Edward Jones performed a study on voluntary use of performance inhibiting drugs. They ... |
2e96d07e-30da-4ec2-9bc0-bf5eb62ae388 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | How "honest" is GPT-3?
*Edited to add: There is now a [1k bounty for a closely related question](https://www.lesswrong.com/posts/H9knnv8BWGKj6dZim/usd1000-bounty-for-openai-to-show-whether-gpt3-was).*
In [Inaccessible Information](https://www.lesswrong.com/posts/ZyWyAJbedvEgRT2uF/inaccessible-information#II__Where_in... |
1506ed95-917e-4d7e-8cb8-73961348521c | trentmkelly/LessWrong-43k | LessWrong | Pivotal Acts might Not be what You Think they are
This article is mainly for people who have not read the pivotal act article on arbital or need a refresher. If you have, the most interesting section would probably be "Omnicient ML Researchers: A Pivotal Act without a Monolithic Control Structure".
Many people seem t... |
ded4ac3e-2892-4641-b783-81100cdd2b99 | trentmkelly/LessWrong-43k | LessWrong | [Linkpost] Can lab-grown brains become conscious?
Linkpost for: https://media.nature.com/original/magazine-assets/d41586-020-02986-y/d41586-020-02986-y.pdf
I figured this was probably of interest to people here, e.g. for seeing how scientists feel about this type of ethical concern and for thinking about the potentia... |
6cf9bec1-9560-4ec9-97c5-42fe9050a85c | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Taxonomy of AI-risk counterarguments
Partly inspired by [The Crux List](https://thezvi.substack.com/p/the-crux-list), the following is a non-comprehensive taxonomy of positions which imply that we should not be worried about existential risk from artificial superintelligence.
Each position individually is supposed to... |
44c4421d-5017-4cc9-bf78-c8c4e251b9ec | trentmkelly/LessWrong-43k | LessWrong | Poll: What value extra copies?
In the future, it may be possible for you to scan your own brain and create copies of yourself. With the power of a controllable superintelligent AI, it may even be possible to create very accurate instances of your past self (and you could take action today or in the near future to make... |
78e7887e-59e3-47f6-b84e-aca7e0bd63db | trentmkelly/LessWrong-43k | LessWrong | Meetup : Goal factoring
Discussion article for the meetup : Goal factoring
WHEN: 24 March 2017 05:45:00PM (+0100)
WHERE: Lindstedtsvägen 3, room 1537, SE-114 28 Stockholm, Sverige
Goal factoring is a technique for introspection to help identify and achieve your goals. It helps choose day-to-day activities that effi... |
bb9424f3-ffc6-43ff-9d02-31192ae084f2 | trentmkelly/LessWrong-43k | LessWrong | Debiasing by rationalizing your own motives
|
5afda00c-179a-49a5-b828-c8565d1389ad | trentmkelly/LessWrong-43k | LessWrong | New Meetup in New Hampshire
The inaugural New Hampshire Less Wrong meet-up will take place the week of June 29-July 4. I've created a Doodle poll to find out the best date for likely participants. If you are interested in attending, please fill out the poll here: http://doodle.com/4ypehfkvsm7cvf76
The first meeting w... |
62b8e80c-35a8-4a20-9ea5-e54b5ccd5ab5 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Ontological Crises in Artificial Agents' Value Systems
1. Abstract
------------
Decision-theoretic agents predict and evaluate the results of their actions using a model, or ontology, of their environment. An agent’s goal, or utility function, may also be specified in terms of the states of, or entities within, its... |
8f92e095-68d2-4b8a-bbd7-bd88543e74a8 | StampyAI/alignment-research-dataset/arbital | Arbital | Löb's theorem
We trust Peano Arithmetic to correctly capture certain features of the [standard model of arithmetic](https://arbital.com/p/). Furthermore, we know that Peano Arithmetic is expressive enough to [talk about itself](https://arbital.com/p/31z) in meaningful ways. So it would certainly be great if Peano Arit... |
edbd4c86-5f89-4309-93b7-f6d196987a2e | trentmkelly/LessWrong-43k | LessWrong | Are Metaculus AI Timelines Inconsistent?
The Metaculus prediction markets on AI timelines are the most referenced ones that I've seen.
The two main ones are as follows:
When will the first weakly general AI system be devised, tested, and publicly announced?: Current Community Prediction: April 14th, 2026
Criteria:
... |
9917f4a2-e88f-49b4-8dd1-8cb21d99d678 | trentmkelly/LessWrong-43k | LessWrong | [Sketch] Validity Criterion for Logical Counterfactuals
Epistemic Status
Originally written in a 47-minute sprint without any sort of proof checking or review[1]. I've edited it hence, but it's still just a rough sketch.
This should be understood as a brief high-level summary of the idea. I would hopefully refine the... |
ebd12b8c-3c6a-43cb-ab58-012905816f32 | trentmkelly/LessWrong-43k | LessWrong | Bayes' theorem, plausible deniability, and smiley faces
> I believe they refer to that as a, smiley face. They're frequently used by idiots at the end of emails and text messages.
>
> − Larry David, The Smiley Face
I have a dilemma. I live in an era of text messaging, Slack, and internet forums. Sometimes I'll be in... |
c426f269-9945-4c66-a568-8a1cd95be05b | trentmkelly/LessWrong-43k | LessWrong | If it were morally correct to kill everyone on earth, would you do it?
First consider the following question to make sure we're on the same page in terms of moral reasoning: social consequences aside, is it morally correct to kill one person to create a million people who would not have otherwise existed? Let's suppos... |
071218f6-3d24-4077-be78-ac02db52dda4 | trentmkelly/LessWrong-43k | LessWrong | Who ordered alignment's apple?
Crossposted from the EA forum: https://forum.effectivealtruism.org/posts/hSugooaEQNTeKFsDu/who-ordered-alignment-s-apple
This post was inspired by G. Gigerenzer's book, Gut Feelings: The Intelligence of the Unconscious. I'm drawing an analogy that I think informs us about how scien... |
84bcbc5a-c2df-4014-a1f0-bc0074069499 | trentmkelly/LessWrong-43k | LessWrong | I can see how I am Dumb
When I'm talking to somebody, sometimes I lose the conversational thread. Or sometimes I feel like there is this thing I want to say that seems relevant now, but I just can't remember it.
Or maybe I'm trying to solve a particular problem. I throw myself again and again at the problem, but it j... |
a4b6defa-0fa4-406e-9507-2721dfca0d61 | trentmkelly/LessWrong-43k | LessWrong | [Stub] Ontological crisis = out of environment behaviour?
One problem with AI is the possibility of ontological crises - of AIs discovering their fundamental model of reality is flawed, and being unable to cope safely with that change. Another problem is the out-of-environment behaviour - that an AI that has been trai... |
47b45327-89f7-4c4f-b3ef-6aed0f7f6f2e | trentmkelly/LessWrong-43k | LessWrong | The likely first longevity drug is based on sketchy science. This is bad for science and bad for longevity.
If you are interested in the longevity scene, like I am, you probably have seen press releases about the dog longevity company, Loyal for Dogs, getting a nod for efficacy from the FDA. These have come in the for... |
ecbb3014-ee0a-4346-be85-253b03975e36 | trentmkelly/LessWrong-43k | LessWrong | Superexponential Historic Growth, by David Roodman
This is research trying to do a similar analysis to Hanson's paper Long-Term Growth as a Sequence of Exponential Modes, and coming to different conclusions in some areas and the same conclusions in others. It also discusses Scott's post 1960: The Year the Singularity ... |
545eab98-c347-43f3-9df9-a9f1393735a3 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Law-Following AI 2: Intent Alignment + Superintelligence → Lawless AI (By Default)
*This post is written in my personal capacity, and does not necessarily represent the views of OpenAI or any other organization. Cross-posted to the [Alignment Forum](https://www.alignmentforum.org/posts/9aSi7koXHCakb82Fz/law-following-... |
2eebca02-879e-4a90-9af2-89475d7758fe | trentmkelly/LessWrong-43k | LessWrong | A general comment on discussions of genetic group differences
(content warning: discussion of racially motivated violence and coercion)
I wanted to share that I think it's not bad to think about the object level question of whether there are group differences in intelligence rooted in genetic differences. This is ... |
a0bc897c-deb1-4386-bfe8-559cf9f3c086 | trentmkelly/LessWrong-43k | LessWrong | Being Rational and Being Productive: Similar Core Skills?
A synthesis of How to Actually Change Your Mind and PJ Eby, written for a general audience.
Several years ago I started suspecting that I needed glasses. At first, I was afraid. I began trying to convince myself that my vision was normal.
But then I stopped... |
ad76543e-2e08-4a94-9568-05be837d317f | trentmkelly/LessWrong-43k | LessWrong | End of the Year Matching Challenge (Altruism)
None |
677cc50d-6fc1-4336-8f39-a3a07a524dbd | trentmkelly/LessWrong-43k | LessWrong | Book review: Happiness by Design
I've been reading a book called Happiness by Design, by Paul Dolan. Most of its material is very standard, but there was at least one thing I hadn't seen before. Dolan thinks that we should consider happiness to be a combination of the feelings of pleasure and purpose. He shows that th... |
62486672-b8c3-49ef-9460-28e4b9020d3f | StampyAI/alignment-research-dataset/lesswrong | LessWrong | [Linkpost] Concept Alignment as a Prerequisite for Value Alignment
> Value alignment is essential for building AI systems that can safely and reliably interact with people. However, what a person values -- and is even capable of valuing -- depends on the concepts that they are currently using to understand and evaluat... |
08304b54-9609-44c6-80b8-46669fd6484f | trentmkelly/LessWrong-43k | LessWrong | Do We Change Our Minds Less Often Than We Think?
In "We Change Our Minds Less Often Than We Think", Eliezer quotes a study:
> Over the past few years, we have discreetly approached colleagues faced with a choice between job offers, and asked them to estimate the probability that they will choose one job over another.... |
11e5a399-e251-4a99-a0b5-4db3ad2ceb2a | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Specification gaming examples in AI
Interesting list of examples where AI programs gamed the specification, solving the problem in rather creative (or dumb) ways not intended by the programmers. |
d9dcd601-a768-4ffd-bb5d-fc1c02298146 | trentmkelly/LessWrong-43k | LessWrong | Probability distributions and writing style
In his recent post, rhollerith wrote,
> I am more likely than not vastly better off than I would have been if <I had made decision X>
This reminded me of the slogan for the water-filtration system my workplaces uses,
> We're 100% sure it's 99.9% pure!
because both senten... |
0a157bd7-b055-425b-9a96-24c488284dd6 | trentmkelly/LessWrong-43k | LessWrong | KAN: Kolmogorov-Arnold Networks
ADDED: This post is controversial. For details see the comments below or the post Please stop publishing ideas/insights/research about AI (which is also controversial).
Abstract:
> Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) a... |
c52c3c00-cd00-4a9d-a7e3-c4c0f1fe6dc9 | StampyAI/alignment-research-dataset/arxiv | Arxiv | An Architectural Approach to Ensuring Consistency in Hierarchical Execution
|
1e475fab-901e-40f8-bd1d-187c81031c9b | trentmkelly/LessWrong-43k | LessWrong | Formal Open Problem in Decision Theory
(This post was originally published on March 31st 2017, and has been brought forwarded as part of the AI Alignment Forum launch sequence on fixed points.)
In this post, I present a new formal open problem. A positive answer would be valuable for decision theory research. A negat... |
282584bb-6aec-49b2-93dc-a24b2c7351c6 | trentmkelly/LessWrong-43k | LessWrong | Industry Matters
|
5ddb5e17-a70b-486c-bb09-f3e0a6a0143d | trentmkelly/LessWrong-43k | LessWrong | Meetup : SF Meetup: Group Debugging
Discussion article for the meetup : SF Meetup: Group Debugging
WHEN: 15 August 2016 06:15:10PM (-0700)
WHERE: SF
UPDATE: This meetup's location has been changed. This meetup will now be held outside, at the courtyard behind the Market on Market. Here's a map to the approximate lo... |
83072b97-10b9-44ad-abe9-d5fc27da1269 | trentmkelly/LessWrong-43k | LessWrong | Rationality Quotes January 2010
A monthly thread for posting rationality-related quotes you've seen recently (or had stored in your quotesfile for ages).
* Please post all quotes separately, so that they can be voted up/down separately. (If they are strongly related, reply to your own comments. If strongly ordered... |
4f37609b-cf96-4604-9891-abd77d56d906 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Urbana-Champaign: Noticing.
Discussion article for the meetup : Urbana-Champaign: Noticing.
WHEN: 05 October 2014 05:30:00PM (-0500)
WHERE: 206 S. Cedar St., Urbana, IL, 61801
Let's work on noticing things. Homework before this meetup: work on noticing when you're rationalizing, and do some physical act li... |
440240ea-1330-4233-9201-06d1fe09f8e5 | trentmkelly/LessWrong-43k | LessWrong | Sociopathy and Rationality
So I randomly ran across a very interesting site about sociopaths. The links at the FAQ and informal test are particularly intriguing (especially since many of us score lower on all 5 moral dimensions measured at yourmorals.org, although many of us would score higher if a liberty dimension w... |
e8422ed9-abf4-4833-829e-bcbc980239f9 | trentmkelly/LessWrong-43k | LessWrong | Don't Build Fallout Shelters
Related: Circular Altruism
One thing that many people misunderstand is the concept of personal versus societal safety. These concepts are often conflated despite the appropriate mindsets being quite different.
Simply put, personal safety is personal.
In other words, the appropriate acti... |
a2eb91c3-7d93-4f8a-9cb0-55b4c6c4d55c | trentmkelly/LessWrong-43k | LessWrong | My Weirdest Experience
I wrote about this a long time ago in some comments here- I'm not sure where or when- but there seemed to be a lot of interest in it. Because of this, I thought I would share the post I've written about it here. |
ff7ed7e2-a0b2-4960-83eb-941e99e7b52e | trentmkelly/LessWrong-43k | LessWrong | Ottawa meetup, Saturday May 14 6pm
Saturday May 14th, 18:00 - Late
1. Social: My house (Little Italy, Ottawa - PM me for address)
2. Games night: Poker @ Casino de Hull
Goals:
1. Continue getting to know each other and new members, continue getting more awesome, and discuss how to implement the various self-... |
c6fc9094-e173-447e-b2e4-92e227e272fb | trentmkelly/LessWrong-43k | LessWrong | [LINK] Human Brain Project aims to emulate brain by 2024
http://nextbigfuture.com/2011/05/henry-markram-and-human-brain-project.html
> Henry Markram says the mysteries of the mind can be solved -- soon. Mental illness, memory, perception: they're made of neurons and electric signals, and he plans to find them with a ... |
dd5e8c5c-4fc8-4f21-a8dd-af442fa3730a | StampyAI/alignment-research-dataset/blogs | Blogs | Learning to Segment Actions from Observation and Narration
Complex tasks that people carry out in the world, for example *making pancakes*, have multiple action steps (e.g., *pouring the mixture, flipping the pancake, removing the pancake*), and are structured. When we observe people carrying out tasks, we recognize w... |
7486ea98-e1b4-4e8d-a214-805ed64d5ae3 | trentmkelly/LessWrong-43k | LessWrong | Does it matter if you don't remember?
Does it matter if you experienced pain in the past, but you don't remember? (And there are no other side-effects, etc etc). At one point in Accelerando, Charles Strauss describes children that routinely decapitate and disembowel each other, only to be repaired (bodily and memory-w... |
f6ca9e55-b8f6-47db-9a74-db614196047e | trentmkelly/LessWrong-43k | LessWrong | Look At What's In Front Of You (Conclusion to The Nuts and Bolts of Naturalism)
If naturalism has been the subject of this sequence, then what is naturalism? Now might be a good time to try stating your own answer, in your own words, before reading more of mine.
----------------------------------------
Here is what ... |
d7ee83c3-7328-4797-99d4-44609d9a4b3d | trentmkelly/LessWrong-43k | LessWrong | Did ChatGPT just gaslight me?
This post is purely written in my personal capacity, and I do not speak for any organization I am affiliated with.
The transcripts below were generated today, November 30th. This was the first exchange I’d had with ChatGPT where I was genuinely trying to see if it could be useful to me. ... |
6a10ffea-9a06-42bc-a93d-944446e4ba3f | trentmkelly/LessWrong-43k | LessWrong | Open Thread - January 2018
Given that the last Open Thread that was intended to be weekly didn't get much traffic, let's try a monthly version. |
4bbc46ba-74c5-41b6-8dcc-39eff60082f0 | trentmkelly/LessWrong-43k | LessWrong | Clarification on Definition of AGI
I've seen the terms AGI and ASI floated around quite a bit, usually with the assumption that the reader knows what they are. From what I've seen it's generally presumed that an AGI is an artificial intelligence that is qualitatively human, in that it can do any task and generalize t... |
4e29ab79-a052-44da-899a-90161f8834c2 | trentmkelly/LessWrong-43k | LessWrong | Introduction: Bias in Evaluating AGI X-Risks
The rationality community has a tradition of checking for biases, particularly when it comes to evaluating the non-intuitive risks of general AI.
We thought you might like this list, adapted from a 2015 essay by Forrest Landry[1]. Many names of biases listed may already be... |
33e4bcee-c361-4acc-a53b-8f46b8cd154f | StampyAI/alignment-research-dataset/lesswrong | LessWrong | GPT-2's positional embedding matrix is a helix
In the context of transformer models, the "positional embedding matrix" is the thing that encodes the meaning of positions within a prompt. For example, given the prompt:
`Hello my name is Adam`
the prompt would generally be broken down into tokens as follows:
`['<|end... |
52603fa5-e023-4f79-90dd-e889e30185fc | trentmkelly/LessWrong-43k | LessWrong | …And I Show You How Deep The Rabbit Hole Goes
.
Seen on Tumblr, along with associated discussion:
Yellow:
People’s minds are heartbreaking. Not because people are so bad, but because they’re so good.
Nobody is the villain of their own life story. You must have read hundreds of minds by now, and it’s true. Everyb... |
43c5bead-09d2-4d58-83aa-a9387d61cdaf | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Some alignment ideas
**Epistemic status**: untested ideas
**Introduction**
This post is going to describe a few ideas I have regarding AI alignment. It is going to be bad, but I think there are a few nuggets worth exploring. The ideas described in this post apply to any AI trained using a reward function directly de... |
57be7f08-efe3-4e2b-97d0-fe19f70c1f41 | trentmkelly/LessWrong-43k | LessWrong | A Chinese Room Containing a Stack of Stochastic Parrots
Most people are familiar with John Searle's Chinese Room argument ("Minds, Brains, and Programs" (1980)):
> Suppose that I'm locked in a room and given a large batch of Chinese writing. Suppose furthermore (as is indeed the case) that I know no Chinese, either w... |
9fc80048-ce62-492c-9a73-1da3618fffb6 | trentmkelly/LessWrong-43k | LessWrong | Markets are Universal for Logical Induction
Background
Logical Induction is the best framework currently available for thinking about logical uncertainty - i.e. the “probability” that the twin primes conjecture is true, or that the (10101010)th digit of pi is 3. This is important for lots of reasons, and you should re... |
9349e23f-6d8b-4787-8905-1bd59125f0da | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Solve Corrigibility Week
A low-hanging fruit for solving alignment is to dedicate a chunk of time actually trying to solve a sub-problem collectively.
To that end, I’ve broken up researching the sub-problem of corrigibility into two categories in this [google doc](https://docs.google.com/document/d/1vMucI0L3ssECOpJJg... |
fd0ffc7a-4c63-4931-a32b-18789c50b428 | trentmkelly/LessWrong-43k | LessWrong | What questions do you have about doing work on AI safety?
As part of the work Nonlinear is doing to try and improve the state of AI safety research, we’re going to be talking with a range of researchers. One of our aims is to help people who are unsure about doing AI safety research figure out if this is a good fit fo... |
bf1e28a0-7780-4cd1-a3e9-b7184d21bd3d | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "This text originated from a retreat in late 2018, where researchers from FHI, MIRI and CFAR did an extended double-crux on AI safety paradigms, with Eric Drexler and Scott Garrabrant in the core. In the past two years I tried to improve it in terms of understandability multiple times, but empirically it seems quite in... |
40189a5e-03ac-4368-943a-e656e89675d8 | trentmkelly/LessWrong-43k | LessWrong | The Multi-Tower Study Strategy
Boxed Topics, Jenga Towers, And The Spacing Effect.
An undergraduate class on molecular biology teaches you about DNA transcription, the Golgi apparatus, cancer, and integral membrane proteins. Sometimes, these sub-topics are connected. But most often, they're presented in separate chap... |
163caf6f-ad66-4afc-9b96-c2f17944639d | trentmkelly/LessWrong-43k | LessWrong | High-School Algebra for Data Structures
A surprising amount of day-to-day software engineering can be expressed as solving equations like:
… finding the solution (x = “Alice”, y = “Liddell”), and then substituting that solution into some other expression.
For instance, suppose we have this data:
We want to list the... |
e15f40f5-feee-4379-9dba-e758e6c78c8e | trentmkelly/LessWrong-43k | LessWrong | Distillation of 'Do language models plan for future tokens'
Link to arxiv preprint: Do language models plan for future tokens, by Wilson Wu, John X Morris and Lionel Levine.
TLDR
* There are two reasons why the computations for the current token are helpful for future tokens’ computation. First, which they call ‘pr... |
4b05e6d5-1579-4a2f-9101-655b028578db | StampyAI/alignment-research-dataset/special_docs | Other | International Control of Powerful Technology: Lessons from the Baruch Plan for Nuclear Weapons
W
O R K I N G
P
A P E R
I n t e r n a t i o n a l C o n t r o l o f P o w e r f u l T e c h n o l o g y :
L e s s o n s f r o m t h e B a r u c h P l a n f o r N u c l e a r W e a p o n s
... |
f0142195-ca90-4084-bea7-16ea263ae6be | StampyAI/alignment-research-dataset/arbital | Arbital | How many bits to a trit?
There are [$\log_2](https://arbital.com/p/3nd) [bits](https://arbital.com/p/3p0) to a [https://arbital.com/p/3ww](https://arbital.com/p/3ww). This can be interpreted a few different ways:
1. If you multiply the number of messages you might want to send by 3, then the cost of encoding the mess... |
757f3e05-ac88-472c-b38e-91dd590d0130 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Naive TDT, Bayes nets, and counterfactual mugging
I set out to understand precisely why naive TDT (possibly) fails the [counterfactual mugging](http://wiki.lesswrong.com/wiki/Counterfactual_mugging) problem. While doing this I ended up drawing a lot of [Bayes nets](http://en.wikipedia.org/wiki/Bayes_net), and seemed t... |
9026d22a-2ae0-4d9d-b9c0-cfdc355be301 | trentmkelly/LessWrong-43k | LessWrong | Notes on Perseverance
This post examines the virtues of perseverance, persistence, resilience, grit, fortitude, tenacity, sisu, and others in that bailiwick. It is meant mostly as an exploration of what other people have learned about these virtues, rather than as me expressing my own opinions about them, though I’ve ... |
6ab3a6d0-0fed-4e20-a206-caf92561be3f | StampyAI/alignment-research-dataset/blogs | Blogs | Why Now Matters
I’m often asked whether [donations now](https://intelligence.org/2015/07/17/miris-2015-summer-fundraiser/) are more important than donations later. Allow me to deliver an emphatic *yes*: I currently expect that donations to MIRI today are worth much more than donations to MIRI in five years. As things ... |
e9a86618-4804-41b5-a1f9-8409eb9bf035 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Prior probability of this being the most important century
Summary
=======
* I think the prior probability of this being the [most important century](https://forum.effectivealtruism.org/s/isENJuPdB3fhjWYHd) is less than 1 % based on i) the self-sampling assumption ([SSA](https://www.lesswrong.com/tag/self-sampling-as... |
5aa9e556-f078-4653-bb15-8d96b05e6741 | trentmkelly/LessWrong-43k | LessWrong | My least favorite thing
Epistemic status: Anger. Not edited.
TL;DR The hamster wheel is bad for you. Rationalists often see participation in the hamster wheel as instrumentally good. I don't think that is true.
Meet Alice. She has had the opportunity to learn many skills in her school years. Alice is a bright hi... |
13dc2e31-a512-4518-ad01-74fd0d37f08c | trentmkelly/LessWrong-43k | LessWrong | On Rigorous Error Handling
In my long career as a programmer I've seen a lot of projects with a lot of error handling practices and, sadly, almost none that actually worked.
We are facing facing few high-level problems here:
1. For many applications error handling is not critical.
2. Error handling code is rarely ... |
8f166dca-a447-4842-bb45-b48a617c35ee | trentmkelly/LessWrong-43k | LessWrong | Open thread, Apr. 17 - Apr. 23, 2017
This is the (late) weekly open thread. See the tag. You'd think we could automate this. The traditional boilerplate follows.
----------------------------------------
If it's worth saying, but not worth its own post, then it goes here.
----------------------------------------
No... |
c3c3e57f-fadb-4f07-9bba-e340c28cea47 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Paradigm-building: Conclusion and practical takeaways
**Recapping the sequence**
--------------------------
Many thanks for reading this sequence all the way through! Recall this chart from [the introductory post](https://www.lesswrong.com/posts/4TuzWEKysvYdhRXLd/paradigm-building-introduction):
![](https://lh5.goog... |
e8bde084-c968-4fa8-8e6a-a3a28bcc3676 | trentmkelly/LessWrong-43k | LessWrong | The Desired Response
A friend once told me a story of how an interaction with her mother changed her perspective on communication. She said that she had been going through a break up at the time, and was venting to her mother, when her mother responded with "Do you want my advice, or my sympathy?"
Often times, when ... |
9377f19c-a3c6-45aa-acd5-90c88bb89739 | trentmkelly/LessWrong-43k | LessWrong | Meetup : First Medellin, Colombia Meetup
Discussion article for the meetup : First Medellin, Colombia Meetup
WHEN: 06 May 2017 06:00:00PM (-0500)
WHERE: Starbucks Coffee One Plaza, Medellin
In the spirit of http://lesswrong.com/lw/bc2/setting_up_lw_meetups_in_unlikely_places_positive/, I'm holding a meetup in Medel... |
1d3348d5-fd07-4140-9854-eaa2ac8da6e7 | trentmkelly/LessWrong-43k | LessWrong | On Dualities
I’ve been finding the word duality useful quite a bit recently. I find it very useful for describing situations where there are two very valuable perspectives (or lens) through which we can look at a situation and any attempt to answer the question needs to grapple with and account for both of these. The ... |
a65e0b38-5797-4412-ab49-de37be396dc4 | trentmkelly/LessWrong-43k | LessWrong | Holden Karnofsky's Singularity Institute critique: Is SI the kind of organization we want to bet on?
The sheer length of GiveWell co-founder and co-executive director Holden Karnofsky's excellent critique of the Singularity Institute means that it's hard to keep track of the resulting discussion. I propose to break o... |
54a0e068-cc13-45b5-9803-39cfb9431c1a | trentmkelly/LessWrong-43k | LessWrong | What are Responsible Scaling Policies (RSPs)?
This is an article in the featured articles series from AISafety.info. AISafety.info writes AI safety intro content. We'd appreciate any feedback.
The most up-to-date version of this article is on our website, along with 300+ other articles on AI existential safety.
MET... |
bb23bdc1-85cb-403f-a4a0-2465c8087ab7 | trentmkelly/LessWrong-43k | LessWrong | Tsinghua paper: Does RL Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
arXiv | project page | Authors: Yang Yue, Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Yang Yue, Shiji Song, Gao Huang
This paper from Tsinghua find that RL on verifiable rewards (RLVR) just increases the frequency at which... |
b11546aa-12e5-4b7e-b045-ae19231c4cee | trentmkelly/LessWrong-43k | LessWrong | Probability puzzle
I came up with this puzzle after reading Vaniver's excellent post on the Value of Information. I enjoyed working it out over Thanksgiving and thought I'd share it with the rest of you.
Your friend holds up a curiously warped coin. "Let's play a game," he says. "I've tampered with this quarter. I... |
97aa5c79-4e06-411e-8542-e3b5d82d715d | StampyAI/alignment-research-dataset/arxiv | Arxiv | Engines of Power: Electricity, AI, and General-Purpose Military Transformations
1 Engines of Power: Electricity, AI, and General-Purpose Military Transformations Jeffrey Ding and Allan Dafoe* Abstract Major theories of military innovation focus on relatively narrow technological developments, such as nuclear weapons ... |
83e5e939-fa9c-4afe-aed2-e709c3f860db | trentmkelly/LessWrong-43k | LessWrong | MIRI AMA plus updates
MIRI is running an AMA on the Effective Altruism Forum tomorrow (Wednesday, Oct. 11): Ask MIRI Anything. Questions are welcome in the interim!
Nate also recently posted a more detailed version of our 2016 fundraising pitch to the EA Forum. One of the additions is about our first funding target:
... |
85c38698-f082-49a0-aefa-9bbb0a49156c | trentmkelly/LessWrong-43k | LessWrong | The "AI Dungeons" Dragon Model is heavily path dependent (testing GPT-3 on ethics)
AI Dungeons is a text-based video game that uses GPT-3 to generate parts of the story. (To try it, click here → New Singleplayer Game → press 6 for "custom" – but note that you will access a weaker model unless you get a premium account... |
e3f65deb-f811-40df-bbc4-18fb6a457894 | trentmkelly/LessWrong-43k | LessWrong | Training AI agents to solve hard problems could lead to Scheming
TLDR: We want to describe a concrete and plausible story for how AI models could become schemers. We aim to base this story on what seems like a plausible continuation of the current paradigm. Future AI models will be asked to solve hard tasks. We expect... |
9d63f979-61d4-4a45-b3b5-095d7ef41ff1 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Intuitive examples of reward function learning?
Can you help find the most intuitive example of reward function learning?
In reward function learning, there is a set of possible non-negative reward functions, .mjx-chtml {display: inline-block; line-height: 0; text-indent: 0; text-align: left; text-transform: none; fo... |
eed20981-62b6-4e90-9999-4674c3624dc4 | trentmkelly/LessWrong-43k | LessWrong | Systematizing Epistemics: Principles for Resolving Forecasts
In a previous post, I discussed many methods for resolving predictions. I want to argue that there is a systematic distinction between rules and principles which I think is valuable.
In short, when making rules, one can front-load intentions by writing det... |
c77cb449-5242-4515-a065-d2bf2336b552 | trentmkelly/LessWrong-43k | LessWrong | Meetup : [Metro Detroit / Ann Arbor], Michigan: LW and SSC meetup where I bring food
Discussion article for the meetup : [Metro Detroit / Ann Arbor], Michigan: LW and SSC meetup where I bring food
WHEN: 13 May 2017 04:00:00PM (-0400)
WHERE: 255 E. Liberty St. Suite 225 Ann Arbor, MI 48103
Howdy, fellers! I wasn't a... |
b6236d2b-9fca-4dfd-a90f-ec4473dde1bf | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Decoherence as Projection
Today's post, Decoherence as Projection was originally published on 02 May 2008. A summary (taken from the LW wiki):
> Since quantum evolution is linear and unitary, decoherence can be seen as projecting a wavefunction onto orthogonal subspaces. This can be neatly illustrated ... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.