id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
b86a0ac3-cd3e-4fcc-9edb-59e9bd7c2670 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Podcast with Divia Eden on operant conditioning
I interviewed Divia Eden for 2.5 hours about operant conditioning on my side podcast, [The Filan Cabinet](https://thefilancabinet.com/). I think it's both an interesting conversation in its own right, as well as being kinda related to human rationality as well as AI and ... |
203e58d0-8b77-4b4f-9be0-1ee91efbf94e | StampyAI/alignment-research-dataset/arxiv | Arxiv | Playing the Blame Game with Robots
Playing the Blame Game with Robots∗
Markus Kneer†
Department of Philosophy
University of Zurich
Zürich, Switzerland
markus.kneer@uzh.ch Michael T. Stuart
Carl Friedrich von Weizsäcker -Zentrum
University of Tübingen
Tübingen , Germany
mike.stuart.post@gmail.... |
184f9293-9a90-4b90-9ea8-2213d3dbcf20 | trentmkelly/LessWrong-43k | LessWrong | The mechanics of my recent productivity
A decade ago, I decided to save the world. I was fourteen, and the world certainly wasn't going to save itself.
I fumbled around for nine years; it's surprising how long one can fumble around. I somehow managed to miss the whole idea of existential risk and the whole concept of... |
efbd171e-c1b2-4106-9105-21e97c6125d9 | trentmkelly/LessWrong-43k | LessWrong | Do the best ideas float to the top?
It may depend on what we mean by “best”.
Epistemic status: I understand very little of anything.
Speculation about potential applications: regulating a logical prediction market, e.g. logical induction; constructing judges or competitors in e.g. alignment by debate; designing comm... |
42958502-c0a9-41e4-9e18-5d4cb5212531 | trentmkelly/LessWrong-43k | LessWrong | AI Governance & Strategy: Priorities, talent gaps, & opportunities
Over the last few weeks, I’ve had 1:1s with several AI governance professionals to develop better models of the current AI governance & strategy landscape. Some topics that regularly came up include:
* What are the most important/neglected areas in A... |
c27389c7-36c3-4cfe-bb5c-a8328de462fb | trentmkelly/LessWrong-43k | LessWrong | School essay: outsourcing some brain work
I'm currently writing an essay for one of my classes, 'Theoretical Foundations of Nursing.' I'm about the most 'gong-si' class I've ever taken. (That is a Chinese term for 'shit talking,' which is my boyfriend's favourite term for any field that gets into arguments over defini... |
27889e7e-1df2-4f32-b6a3-88fd6b0d26f1 | trentmkelly/LessWrong-43k | LessWrong | Decision-theoretic problems and Theories; An (Incomplete) comparative list
So, this is a work-in-progress, but the idea is to a) get an eventually exhaustive list of decision-theoretic problems, and b) detail the '''answers''' given by each major decision theory.
(Stretch goals would including listing other kinds of ... |
e880de16-1088-43b1-aac0-c56e64d1c151 | StampyAI/alignment-research-dataset/special_docs | Other | Corrigibility
Corrigibility
InAAAI Workshops: Workshops at the Twenty-Ninth AAAI Conference on Arti cial Intelligence,
Austin, TX, January 25{26, 2015. AAAI Publications.
Nate Soares andBenja Fallenstein andEliezer Yudkowsky
Machine Intelligence Research Institute
fnate,benja,eliezer g@intelligence.orgStuart Armstrong... |
20f27aa3-b0d0-4780-9d02-6d70688b5984 | trentmkelly/LessWrong-43k | LessWrong | Positive outcomes under an unaligned AGI takeover
The following is a hypothetical story about a surprisingly positive outcome to an unaligned AGI takeover. This is not meant to be realistic, but merely semi-plausible, in order to show that the orthogonality thesis does not necessarily lead to defection against humans ... |
031fb3a6-cb8c-43e6-a5b7-a858d5d43f87 | trentmkelly/LessWrong-43k | LessWrong | Should I delay having children to take advantage of polygenic screening?
I would like to know whether I should delay having children to take advantage of polygenic screening technology. I imagine this could be valuable for other aspiring parents to know as well, and would (probably) have positive externality for aspir... |
e0fd513d-8dcc-48d8-8151-4b03ac9bc0f7 | trentmkelly/LessWrong-43k | LessWrong | Group rationality diary, May 5th - 23rd
This is the public group rationality diary for May 5 - 23, 2015. It's a place to record and chat about it if you have done, or are actively doing, things like:
* Established a useful new habit
* Obtained new evidence that made you change your mind about some belief
* Decid... |
e819357e-7db0-46d7-a1ed-46dd3fc9fc8b | trentmkelly/LessWrong-43k | LessWrong | Rationality quotes: August 2010
This is our monthly thread for collecting these little gems and pearls of wisdom, rationality-related quotes you've seen recently, or had stored in your quotesfile for ages, and which might be handy to link to in one of our discussions.
* Please post all quotes separately, so that the... |
967783b9-2009-489d-9a81-05b0e8b8a95d | trentmkelly/LessWrong-43k | LessWrong | Putanumonit: If rationality is a religion, it's a crappy one.
|
52e4bcb7-7e5c-49c8-a029-e564cf6d42ef | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Can GPT-3 produce new ideas? Partially automating Robin Hanson and others
**Brief description of the experiment**
---------------------------------------
I asked a language model to replicate a few patterns of generating insight that humanity hasn't really exploited much yet, such as:
1. Variations on "if you never ... |
83e212ed-e707-4b69-ba4b-0cbeb706425b | trentmkelly/LessWrong-43k | LessWrong | Modulating sycophancy in an RLHF model via activation steering
Produced as part of the SERI ML Alignment Theory Scholars Program - Summer 2023 Cohort, under the mentorship of Evan Hubinger. Thanks to Alex Turner for his feedback and ideas.
This is a follow-up post to "Reducing sycophancy and improving honesty via ac... |
4d590b01-504e-4d53-a004-6b24994ab28e | trentmkelly/LessWrong-43k | LessWrong | Reality-Revealing and Reality-Masking Puzzles
Tl;dr: I’ll try here to show how CFAR’s “art of rationality” has evolved over time, and what has driven that evolution.
In the course of this, I’ll introduce the distinction between what I’ll call “reality-revealing puzzles” and “reality-masking puzzles”—a distinction tha... |
19d12458-fe5d-4ac9-93dc-4a35b5c6d199 | trentmkelly/LessWrong-43k | LessWrong | How to parallelize "inherently" serial theory work?
Things this question is assuming, for the sake of discussion: The hardest parts of AI alignment are theoretical. Those parts will be critical for getting AI alignment right. The biggest bottlenecks to theoretical AI alignment, are "serial" work, as described in this ... |
5209c6f6-f7fe-4b2d-b339-7e401ccd54cc | trentmkelly/LessWrong-43k | LessWrong | Deep folding docs site?
I'm trying to re-find a nested folding docs site. It was styled to look like Google Docs.
I read an article there, a detailed report, possibly from Redwood Research, covering an argument and deep, iterative explanation that could be read as a single paragraph of headers, each unfolding into a ... |
b0cb0c16-8a99-4393-b273-798413e2d9e1 | trentmkelly/LessWrong-43k | LessWrong | AGI Safety Fundamentals curriculum and application
Over the last year EA Cambridge has been designing and running an online program aimed at effectively introducing the field of AGI safety; the most recent cohort included around 150 participants and 25 facilitators from around the world. Dewi Erwan runs the program; I... |
fa8ee8f6-c760-45cb-8fe9-e850f0ae9755 | trentmkelly/LessWrong-43k | LessWrong | [Link] Colonisation of Venus
I was wondering what people thought of this paper by Geoffrey Landis on colonising Venus. In it he suggests that cloud-top Venus is one of the most benign environments in the Solar System. Temperature and gravity are similar to Earth, there's some radiation shielding and useful resources, ... |
84a8a5cd-399b-4fe4-87e9-b6193270655c | trentmkelly/LessWrong-43k | LessWrong | Water Preparedness for Disasters
Overview
This guide goes into details on storing and purifying water. This is meant to give you a tool to reason about how to prepare for and act in emergencies that disrupt your water supply.
Storing Water
How much to store?
* Ready.gov recommends storing 3 gallons of water pe... |
0300a00f-07a9-422f-97e3-0531cf91bdd7 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] The Halo Effect
Today's post, The Halo Effect was originally published on 30 November 2007. A summary (taken from the LW wiki):
> Positive qualities seem to correlate with each other, whether or not they actually do.
Discuss the post here (rather than in the comments to the original post).
This post... |
40dc9683-78d6-4a23-b8f1-a2e9f6047170 | trentmkelly/LessWrong-43k | LessWrong | The Limits of My Rationality
As requested here is an introductory abstract.
The search for bias in the linguistic representations of our cognitive processes serves several purposes in this community. By pruning irrational thoughts, we can potentially effect each other in complex ways. Leaning heavy on cognitivist ped... |
3447f4ae-12e9-43d0-b743-69e6df498e84 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | The ‘Old AI’: Lessons for AI governance from early electricity regulation
*Note: neither author has a background in history, so please take this with a lot of salt. Sam thinks this is more likely than not to contain an important error. This was written in April 2022 and we’re posting now as a draft, because the altern... |
bd84cc8e-a140-4196-a594-f11f40d43fbb | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Who Aligns the Alignment Researchers?
There may be an incentives problem for AI researchers and research organizations who face a choice between researching Capabilities, Alignment, or neither. The incentives structure will lead individuals and organizations to work towards Capabilities work rather than Alignment. The... |
ac11684f-e91b-4ef2-8f75-38eddb2e1571 | trentmkelly/LessWrong-43k | LessWrong | Quarantine Preparations
A month ago I wrote about disaster preparedness, and while the current coronavirus outbreak had started it wasn't something I knew about yet. Now that there's a real possibility that it will spread globally, it's worth preparing for this specific disaster.
The ideal time to start thinking abou... |
2b58c46d-b99c-42a0-aa28-8cca593d6bee | StampyAI/alignment-research-dataset/blogs | Blogs | ethics and anthropics of homomorphically encrypted computations
ethics and anthropics of homomorphically encrypted computations
---------------------------------------------------------------
suppose you are a superintelligence that is aligned with some human values. you are going about your day, tiling the cosmos w... |
efab6f85-7fea-4bf1-9792-78db969c1784 | trentmkelly/LessWrong-43k | LessWrong | IRL 4/8: Maximum Entropy IRL and Bayesian IRL
Every Monday for 8 weeks, we will be posting lessons about Inverse Reinforcement Learning. This is lesson 4.
Note that access to the lessons requires creating an account here.
This lesson comes with the following supplementary material:
* The Principle of Maximum Entro... |
ac944834-83c0-4719-b8ea-e55edd91bb59 | trentmkelly/LessWrong-43k | LessWrong | Old urine samples from the 2008 and 2012 Olympics show massive cheating
|
d024fe1f-916e-4cef-b7de-66c4efd0d585 | trentmkelly/LessWrong-43k | LessWrong | Mental representation and the is-ought distinction
I'm reading Thinking, Fast and Slow. In appendix B I came across the following comment. Emphasis mine:
> Studies of language comprehension indicate that people quickly recode much of what they hear into an abstract representation that no longer distinguishes whether ... |
e647c47b-0337-4d76-b76f-1fc78866f890 | trentmkelly/LessWrong-43k | LessWrong | Open thread, August 21 - August 27, 2017
IF IT'S WORTH SAYING, BUT NOT WORTH ITS OWN POST, 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. (Immediately before; refresh ... |
69e8cee5-585c-4847-b567-b6fe1605cadb | trentmkelly/LessWrong-43k | LessWrong | Treatments correlated with harm
There's a billion different ways studies can go wrong through failure of statistics to correctly capture reality.
One very specific one is: your successful treatments will often look like they're making things worse.
This is merely a special case of confounding, but it comes up often ... |
86e0d99e-e57c-499b-b836-77396bfedaf5 | trentmkelly/LessWrong-43k | LessWrong | Signup to wiki broken ?
Hi,
(Sorry if the discussion if not the best place to post that, but didn't find any better place).
It seems the signup to the http://wiki.lesswrong.com/wiki/ is broken :
Account creation from this IP address (10.254.182.117) has been blocked by Gwern.
10.254 ? Seems that the blocking was ... |
351158d0-425e-4654-88e9-cfa9cf687613 | trentmkelly/LessWrong-43k | LessWrong | Hessian and Basin volume
Thanks to Thomas Kwa for the question which prompted this post.
Note: This is mostly a primer / introductory reference, not a research post. However, the details should be interesting even to those familiar with the area.
When discussing “broad basins” in the loss landscape of a DNN, the H... |
b9a525ed-c572-4c99-8f96-cb6d68b0e88b | trentmkelly/LessWrong-43k | LessWrong | CFAR is looking for a videographer for next Wednesday
Hi all, CFAR is looking for a videographer in the Bay Area to shoot and edit a 1-minute video introducing us. Do you know anyone?
If so, please send an email to them and me (critch@rationality.org) that introduces us!
We'll need to shoot the video on Wednesda... |
22b2f65c-d722-4a87-af9e-7b244481bdbb | trentmkelly/LessWrong-43k | LessWrong | Michael Simm - Introducing Myself
Hi, LessWrong Community. I'd like to introduce myself!
My name is Michael Simm. I am passionate about disruptive systems (eg, understanding and using emerging technologies to make the future better). I'd been interested in EA principles long before I learned about the movement, so on... |
981909a4-e6c5-4956-a871-a9452f07bbac | trentmkelly/LessWrong-43k | LessWrong | Counterfactual Mugging Poker Game
,,,
Consider the following game:
Player A receives a card at random that is either High or Low. He may reveal his card if he wishes.
Player B then chooses a probability p that Player A has a high card.
Player A always loses p2 dollars. Player B loses p2 dollars if the card is low a... |
23237d50-87fd-40d5-8c98-214afa60f511 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Newcomb's Problem standard positions
[Marion Ledwig's dissertation](http://kops.ub.uni-konstanz.de/volltexte/2000/524/pdf/ledwig.pdf ) summarizes much of the existing thinking that's gone into Newcomb's Problem.
(For the record, [I myself](http://www.overcomingbias.com/2008/01/newcombs-proble.html) am neither an evi... |
778bbf0b-ef25-4857-b404-bbd62c0374de | trentmkelly/LessWrong-43k | LessWrong | Weekly LW Meetups
This summary was posted to LW Main on February 12th. The following week's summary is here.
Irregularly scheduled Less Wrong meetups are taking place in:
* Ann Arbor Meetup, 2/19/16: 19 February 2016 07:00PM
* European Community Weekend: 02 September 2016 03:35PM
* San Francisco Meetup: Projects:... |
26408337-74b7-4a2a-85d6-55d62ae837b1 | trentmkelly/LessWrong-43k | LessWrong | The Many Worlds of Hugh Everett
I've just finished this book and its one of the most enjoyable things I've read in a long time. Being a staple of science fiction and the only interpretation of quantum mechanics to enter the popular imagination it's a little surprising that "The Many Worlds of Hugh Everett" by Peter By... |
7060505a-678a-40a5-bbed-414040e31c26 | trentmkelly/LessWrong-43k | LessWrong | How To Fermi Model
[Note from Eli in 2020: I wrote this document in 2016, in conjunction with two workshops that I helped Oliver Habryka run. If I were to try and write a similar document today, it would likely be substantially different in form and style. For instance, reading this in 2020, I’m not very compelled by ... |
260d9c63-3931-47ab-b0b5-017a91183f42 | trentmkelly/LessWrong-43k | LessWrong | My favorite essays of life advice
I start each of my weekly reviews by re-reading one of my favorite essays of life advice—a different one each week. It’s useful for a few different reasons:
* It helps me get into the right reflective frame of mind.
* The best essays are dense enough with useful advice that I find... |
2c4e59d8-6f41-4ba8-ab94-d838af0fdcee | trentmkelly/LessWrong-43k | LessWrong | Somerville Election Thoughts
Instead of a primary, Somerville holds preliminary elections. For each role, if there are more than twice as many candidates as spots there's preliminary election. This year that applies to Mayor (four candidates), and the councilors for Wards five (three candidates) and seven (four candid... |
07013097-a823-4e8f-a784-2b3ca60d4ea1 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Un-manipulable counterfactuals
.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: none; ... |
624a7cf3-7629-4edb-a302-19bdd0b7726f | trentmkelly/LessWrong-43k | LessWrong | New contractor role: Web security task force contractor for AI safety announcements
Web security task force contractors for AI safety announcements
Survival and Flourishing .Com is looking for white-hat hackers and security professionals who can join our task force of “on call” professionals for a week or so, once or... |
75c3e15f-ac09-4a0e-adb0-6d59aea03c42 | trentmkelly/LessWrong-43k | LessWrong | How do SAE Circuits Fail? A Case Study Using a Starts-with-'E' Letter Detection Task
TLDR:
We investigated cases where SAE circuits "fail" at detecting if words start with "E", in that the circuit omits the most important computational pathway (latent) in the model for detecting the letter "E". We find that in the va... |
70f6a719-4c75-485d-b1b1-94b0984083bc | trentmkelly/LessWrong-43k | LessWrong | The map of organizations, sites and people involved in x-risks prevention
Three known attempts to make a map of x-risks prevention in the field of science exist:
1. First is the list from the Global Catastrophic Risks Institute in 2012-2013, and many links there are already not working:
2. The second was done by S. ... |
848b7c4b-d7f0-4194-8176-9609bc545a49 | StampyAI/alignment-research-dataset/special_docs | Other | Robust Multi-Agent Reinforcement Learning via Minimax Deep Deterministic Policy Gradient
Introduction Most real-world problems involve interactions between multiple agents and the complexity of problem increases significantly when the agents co-evolve together. Thanks to the recent advances of deep reinforcement leari... |
6f0d93b3-116c-453a-ac7d-37e9b0e1e500 | StampyAI/alignment-research-dataset/special_docs | Other | The Technological Singularity
[]
The Technological Singularity
The MIT Press Essential Knowledge Series
Understanding Beliefs, Nils J. Nilsson
Computing: A Concise History, Paul E. Ceruzzi
The Conscious Mind, Zoltan L. Torey
Crowdsourcing, Daren C. Brabham
Free Will, Mark Balaguer
Information and the Modern Co... |
19dde46f-3728-4e46-9567-a8e5e3dfbfee | trentmkelly/LessWrong-43k | LessWrong | Steelmining via Analogy
This post has been written for the first Refine blog post day, at the end of a week of readings, discussions, and exercises about epistemology for doing good conceptual research. Thanks Adam Shimi, Linda Linsefors, Dan Clothiaux for comments.
To steelmine (as per Tamsin): to intentionally look... |
c95dfb65-a05f-4fe3-a554-3773f892e867 | trentmkelly/LessWrong-43k | LessWrong | Robustness to Scaling Down: More Important Than I Thought
(Edit: I added text between "...was really about reductions." and "To use the mental move of robustness...", because comments showed me I hadn't made my meaning clear enough.)
This post is part of the work done at Conjecture.
In Robustness To Scale, Scott Gar... |
18111422-e797-45d6-9328-005e32825bfb | StampyAI/alignment-research-dataset/lesswrong | LessWrong | The Social Alignment Problem
*TLDR: I think public outreach is a very hopeful path to victory. More importantly, extended large-scale conversation around questions such as whether public outreach is a hopeful path to victory would be very likely to decrease p(doom).*
You’re a genius mechanical engineer in prison. You... |
049a72a0-9481-4574-ae1d-397ccba7ec74 | trentmkelly/LessWrong-43k | LessWrong | A quantitative introduction to churning
Credit card companies offer sign up bonuses and other benefits to incentivize you to open a credit card with them. Churning is the art of going after these benefits systematically. It's surprisingly lucrative.
This post serves two purposes. One, I will describe common churning... |
e6b460a1-26f4-471b-ada4-69ca72cb29d6 | trentmkelly/LessWrong-43k | LessWrong | Effectiveness of different supplement brands?
A friend of mine told me she got very good results from Vitamin World melatonin, and little or no effect from Natrol melatonin, and that reminded me of recent news that many herbal supplements don't have any herbal content.
Does anyone have information, whether based i... |
4def3ba7-9c06-4043-be5b-e2990f7dc17b | StampyAI/alignment-research-dataset/lesswrong | LessWrong | PZ Myers on the Infeasibility of Whole Brain Emulation
From: **<http://freethoughtblogs.com/pharyngula/2012/07/14/and-everyone-gets-a-robot-pony/>**
>
> I’ve worked with tiny little zebrafish brains, things a few hundred microns long on one axis, and I’ve done lots of EM work on them. You can’t fix them into a sta... |
1e279b5e-9634-415c-814e-96796eaa267a | StampyAI/alignment-research-dataset/arbital | Arbital | Value identification problem
The subproblem category of [value alignment](https://arbital.com/p/5s) which deals with pinpointing [valuable](https://arbital.com/p/55) outcomes to an [advanced agent](https://arbital.com/p/2c) and distinguishing them from non-valuable outcomes. E.g., the [Edge Instantiation](https://arb... |
38b070ff-d850-4436-a90c-1de800aee4f9 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Book Mini-Review: Doug Hubbard's How to Measure Anything
Discussion article for the meetup : Book Mini-Review: Doug Hubbard's How to Measure Anything
WHEN: 15 December 2013 04:00:00PM (-0500)
WHERE: 869 Stockton Street, Suite 1-2 , Jacksonville, FL
Folks who are enjoying this fine Jacksonville winter: come... |
54c5bf05-ba91-4241-856f-c3fa2269afe4 | trentmkelly/LessWrong-43k | LessWrong | Job Board (28 March 2033)
Job Board (28/03/2033)
In-person Therapy Assistant - YouTherapy
In the current mental health crisis, the well being of our friends is our priority! YouTherapy is committed to providing high quality personalised psychological counselling to over two million customers. We are seeking highly q... |
b2dc2a2f-4cda-4388-91d0-cf5e2451ddab | trentmkelly/LessWrong-43k | LessWrong | How do you Murphyjitsu essentially risky activities?
In the CFAR Handbook they have the following process instructions for Murphyjitsu:
> 1. Select a goal. A habit you want to install, or a plan you’d like to execute, or a project you want to complete.
> 2. Outline your plan. Be sure to list next actions, concrete ... |
9ec11667-a6a7-4688-ab22-2e349acb3e54 | trentmkelly/LessWrong-43k | LessWrong | Survival without dignity
I open my eyes and find myself lying on a bed in a hospital room. I blink.
"Hello", says a middle-aged man with glasses, sitting on a chair by my bed. "You've been out for quite a long while."
"Oh no ... is it Friday already? I had that report due -"
"It's Thursday", the man says.
"Oh grea... |
f53bed3f-7007-477f-b335-a97cf261f69c | trentmkelly/LessWrong-43k | LessWrong | What in your opinion is the biggest open problem in AI alignment?
|
34203ab8-3e98-4a43-9189-62afc7941367 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Adversarial Policies: Attacking Deep Reinforcement Learning.
1 Introduction
---------------
The discovery of adversarial examples for image classifiers prompted a new field of research into adversarial attacks and defenses [Szegedy et al., [2014](#bib.bib28)].
Recent work has shown that deep RL policies are also vu... |
a500086b-12f2-4bfb-a09f-055273d7e127 | trentmkelly/LessWrong-43k | LessWrong | Epistemic states as a potential benign prior
Malignancy in the prior seems like a strong crux of the goal-design part of alignment to me. Whether your prior is going to be used to model:
* processes in the multiverse containing the AI which does said modeling,
* processes which would output all of some blog so we c... |
b7fb9c74-f1ba-42a5-beb5-b9ac393e8df2 | trentmkelly/LessWrong-43k | LessWrong | More Clothes Over Time?
A friend recently reshared this:
> Today I want to talk about why you buy the way you do. Did you know that WE collectively buy five times more clothes than we bought in 1990? — @AjaSaysHello
This seemed a bit unlikely to me, if they're talking about Americans, and fashion waste stats are typ... |
12fdf3e7-ff97-48ec-bfea-20d7f12eea6c | trentmkelly/LessWrong-43k | LessWrong | No Logical Positivist I
Followup to: Making Beliefs Pay Rent, Belief in the Implied Invisible
Degrees of Freedom accuses me of reinventing logical positivism, badly:
> One post which reads as though it were written in Vienna in the 1920s is this one [Making Beliefs Pay Rent] where Eliezer writes
>
> > "We can buil... |
d10860d5-9815-477f-899e-9bc6c801e1df | StampyAI/alignment-research-dataset/arxiv | Arxiv | On modelling the emergence of logical thinking
Introduction
------------
There is much debate about whether mathematics is discovered or invented.
The Platonic view is that mathematical objects exist in a reality separate and independent of ours, with truths we are only discovering. Mathematical truths, e.g. the fa... |
c361c1e9-283e-45c5-88c2-361ccd6fbe4a | trentmkelly/LessWrong-43k | LessWrong | Any further work on AI Safety Success Stories?
TL;DR, Are they any works similar to Wei_Dai's Ai Safety "Success Stories" that provide a framework to think about the landscape of possible success stories & pathways humanity will take to survive misaligned AI?
I've been trying to think of systematic ways of assessing ... |
7fe502a7-56e1-45e0-9fda-82874623ccf4 | trentmkelly/LessWrong-43k | LessWrong | A Proper Scoring Rule for Confidence Intervals
,,,,,,,,,,,,,,,,,
You probably already know that you can incentivise honest reporting of probabilities using a proper scoring rule like log score, but did you know that you can also incentivize honest reporting of confidence intervals?
To incentize reporting of a 90% con... |
1a359946-d46d-4c6b-ab5e-1810799191b8 | trentmkelly/LessWrong-43k | LessWrong | Risks from AI persuasion
A case for why persuasive AI might pose risks somewhat distinct from the normal power-seeking alignment failure scenarios.
Where I'm currently at: I feel moderately confident that powerful persuasion is useful to think about for understanding AI x-risk, but unsure whether it's best regarded a... |
8f05a55c-7872-4a04-917d-e016b01748dc | trentmkelly/LessWrong-43k | LessWrong | How I Learn From Textbooks
After a long semi-hiatus during my MS degree, I am eager to revisit my sequence on scholarship, particularly the topic of learning new subjects from textbooks. This article provides a general overview based on my own introspection and experiences, rather than an extensive literature review. ... |
1a294263-dda9-4b14-8f69-7032e9bf63c1 | trentmkelly/LessWrong-43k | LessWrong | Why work at AI Impacts?
AI Impacts is beginning a serious hiring round (see here for job postings), so I’d like to explain a bit why it has been my own best guess at the highest impact place for me to work for me. (As in, this is a personal blog post by Katja on the AI Impacts blog, not some kind of officialesque miss... |
4ef3acfa-465f-4a68-97cc-2c35736e57d9 | trentmkelly/LessWrong-43k | LessWrong | Value of Information: Four Examples
Value of Information (VoI) is a concept from decision analysis: how much answering a question allows a decision-maker to improve its decision. Like opportunity cost, it's easy to define but often hard to internalize; and so instead of belaboring the definition let's look at some exa... |
40ecc0a2-1d94-4041-b0c3-e0890cf4fabc | trentmkelly/LessWrong-43k | LessWrong | Wanted: "The AIs will need humans" arguments
As Luke mentioned, I am in the process of writing "Responses to Catastrophic AGI Risk": A journal-bound summary of the AI risk problem, and a taxonomy of the societal proposals (e.g. denial of the risk, no action, legal and economic controls, differential technological deve... |
6b78bf46-54d5-49a7-bb04-f6af50cbb01b | trentmkelly/LessWrong-43k | LessWrong | Book review: Age Later
Book review: Age Later, by Nir Barzilai.
Books by serious researchers on how to defeat aging are now coming out almost as fast as I have time to read them.
This one mostly aims to enable us live in good health to 115, preferably via a few simple pills.
Age Later is fairly similar to Sinclair'... |
63e13f66-d07b-47ef-af71-027449fbc6cd | trentmkelly/LessWrong-43k | LessWrong | Liquid vs Illiquid Careers
We're used to thinking about skills and experience in terms of their market value - how useful they are and how much employers or customers would pay for them. But another, more subtle dimension gets less attention: liquidity.
Just like in financial markets, some human capital is easier t... |
8ca27293-3470-4bce-bec0-86d22f88c3e9 | trentmkelly/LessWrong-43k | LessWrong | Cached Phrases
Recently I've noticed that, while introspecting, my internal monologue will state an opinion on a preceding thought, and I will feel an immediate repulsion towards that phrase as something disingenuous or alien. I will then recognize it as what I've come to term a "cached phrase". A variation/subset o... |
2ea604ad-4db5-421f-b114-419e27780e65 | trentmkelly/LessWrong-43k | LessWrong | LW Bipolar Support Group?
Related to: Intrapersonal negotiation
I'm writing to inquire about whether there's interest on LW in developing a bipolar support group.
There's a general issue of the people at in-person support groups and designated online forums. been relatively uneducated; having little capacity for or ... |
7fb35450-76ed-48de-8970-2179c1c55488 | trentmkelly/LessWrong-43k | LessWrong | "Talking with God", a transhumanist short story
Talking with God is a pleasant and inspiring transhumanist short story. I've got some quibbles, but I'll save them for the comments because I think the story is better without spoilers.
There's a discussion forum at the story's site. |
5b1d031d-8e22-441a-aa32-181f5fef73b1 | trentmkelly/LessWrong-43k | LessWrong | Two-year update on my personal AI timelines
I worked on my draft report on biological anchors for forecasting AI timelines mainly between ~May 2019 (three months after the release of GPT-2) and ~Jul 2020 (a month after the release of GPT-3), and posted it on LessWrong in Sep 2020 after an internal review process. At t... |
1c5d0d98-469e-43ee-9325-1ef51377790c | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Applications for AI Safety Camp 2022 Now Open!
If you’ve read about alignment research and you want to start contributing, the new iteration of the AI Safety Camp is a great opportunity!
It’s a virtual camp from January to May 2022, where you collaborate with other applicants to work (1h / normal workday, 7h / weeken... |
4d36cd7f-7df0-4579-93af-dfad7be4ded4 | trentmkelly/LessWrong-43k | LessWrong | Politics Discussion Thread August 2012
In line with the results of the poll here, a thread for discussing politics. Incidentally, folks, I think downvoting the option you disagree with in a poll is generally considered poor form.
1.) Top-level comments should introduce arguments; responses should be responses to ... |
71bd1d5f-7c61-447e-b457-eed62dc2a62a | trentmkelly/LessWrong-43k | LessWrong | Was Homer a stochastic parrot? Meaning in literary texts and LLMs
Cross posted from New Savanna.
The phrase “stochastic parrot” was coined, I believe, by Emily Bender, a computational linguist and one of the coauthors of the paper, On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? Consider this p... |
28f373b0-925b-42ba-8204-801e937391ab | trentmkelly/LessWrong-43k | LessWrong | Bragging thread August 2015
Your job, should you choose to accept it, is to comment on this thread explaining the most awesome thing you've done this month. You may be as blatantly proud of yourself as you feel. You may unabashedly consider yourself the coolest freaking person ever because of that awesome thing you're... |
aca19517-d137-4f07-9df3-994bf55d2e2a | StampyAI/alignment-research-dataset/arxiv | Arxiv | Masked World Models for Visual Control.
1 Introduction
---------------
Model-based reinforcement learning (RL) holds the promise of sample-efficient robot learning by learning a world model and leveraging it for planning [chua2018deep, deisenroth2011pilco, lenz2015deepmpc] or generating imaginary states for behavio... |
c44c4342-9e1b-4f35-a662-1ccf321621a4 | trentmkelly/LessWrong-43k | LessWrong | What I Learned From Running a Pol.is Conversation
Try Things
A couple weeks ago, I asked around facebook and discord for people willing to test out Polis, an interactive survey tool.
Polis appealed to my aesthetic. It hosts a conversation where participants submit twitter-size comments on a topic which other particip... |
754e7ab2-b4ad-43f8-8562-e4dbe33940a9 | trentmkelly/LessWrong-43k | LessWrong | AI & wisdom 1: wisdom, amortised optimisation, and AI
Written for the AI Impacts essay competition on the automation of wisdom and philosophy
At least in name, AI is about intelligence. However, intelligence is not the only mental quality that matters. Many deep mental skills, in particular regarding good, deep, or l... |
10f45547-95b5-42ef-a8ad-e61bfb7085eb | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "When I criticize, I'm a genius. I can go through a book of highly-referenced scientific articles and find errors in each of them. Boy, I feel smart. How are these famous people so dumb?
But when I write, I suddenly become stupid. I sometimes spend half a day writing something and then realize at the end, or worse, aft... |
e89022fc-8852-4c74-986b-2bea85830ed1 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Devil's Offers
Today's post, Devil's Offers was originally published on 25 December 2008. A summary (taken from the LW wiki):
> It is dangerous to live in an environment in which a single failure of resolve, throughout your entire life, can result in a permanent addiction or in a poor edit of your own ... |
43f320c9-31d3-4875-8558-1eecb4bd93a4 | trentmkelly/LessWrong-43k | LessWrong | Information Loss --> Basin flatness
This work was done under the mentorship of Evan Hubinger through the SERI MATS program. Thanks to Lucius Bushnaq, John Wentworth, Quintin Pope, and Peter Barnett for useful feedback and suggestions.
In this theory, the main proximate cause of flat basins is a type of information lo... |
5f947988-2daa-4e26-87ad-24742b3851e1 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | AI and neuroscience: The virtuous circle - DeepMind: The Podcast (S1, Ep1)
I think I was about seven years old when
I wrote my first line of code it was
probably something simple printing my
name to the screen or a two-dimensional
shape that could be twisted and
stretched by my sequence of carefully
typed letters and ... |
d7b6dbe5-6739-41ad-ae12-38dbe0fe2ad7 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | A long reply to Ben Garfinkel on Scrutinizing Classic AI Risk Arguments
In July, Ben Garfinkel scrutinized the classic AI Risk arguments in a 158 minute-long [interview](https://80000hours.org/podcast/episodes/ben-garfinkel-classic-ai-risk-arguments/) with 80000 hours, which I strongly recommend.
I have formulated a... |
85e6a31b-1c63-4927-a199-06094219c500 | trentmkelly/LessWrong-43k | LessWrong | The limits of black-box evaluations: two hypotheticals
A prominent approach to AI safety goes under the name of "evals" or "evaluations". These are a critical component of plans that various major labs have, such as Anthropic's responsible scaling policy or OpenAI's preparedness framework. At bottom, these approaches ... |
90f088cf-daf3-414b-89a2-b0a7163966e8 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Causality, Transformative AI and alignment - part I
**TL;DR:** transformative AI(TAI) plausibly requires causal models of the world. Thus, a component of AI safety is ensuring secure paths to generating these causal models. We think the lens of causal models might be undervalued within the current alignment research l... |
bc96c065-ee93-43af-85cd-fe4d61a578f1 | trentmkelly/LessWrong-43k | LessWrong | The Darwin Game
Click here to participate. Entries must be submitted on October 18th, 2020 or earlier.
Entry is now closed.
----------------------------------------
In 2017, Zvi posted an exciting story about The Darwin Game, a variation of iterated prisoner's dilemma.
I will run my own version of the game in the ... |
80c740ad-53c5-4466-b7c6-f47e7379ec7e | trentmkelly/LessWrong-43k | LessWrong | Algorithms as Case Studies in Rationality
This post springs out of a very long line of thought, which I will only summarise small parts of.
It began with the puzzling realisation that the algorithm which computers use to perform symbolic integration is radically different from the guess-and-check method taught in sch... |
9aa180c6-e6e6-4c47-976e-83b52e5eca48 | trentmkelly/LessWrong-43k | LessWrong | Life, not a game
Life is a rigged game. Quit the red bloody market, seclude from all the randomness of it and disappear completely. But that's a premise behind “do not compare yourself to others instead compare to the person you where yesterday”. Claiming that one secludes himself from the need to see yourself as lowe... |
e5e0b617-2559-4f5e-b317-fba49996a3bf | trentmkelly/LessWrong-43k | LessWrong | Depression and Creativity
This is cross-posted from New Savanna.
NOTE: I’ve posted this interaction with Claude, not so much to present the ideas Claude offered about possible relationships between depression and creativity, but as an example of the kind of conversational interaction one can have with it. I was part... |
26530cdc-9423-4df5-8db0-ab251784647b | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Functional Decision Theory: A New Theory of Instrumental Rationality
|
8850a7ad-1a40-4cc9-8ee9-741b28de4112 | trentmkelly/LessWrong-43k | LessWrong | Explaining Capitalism Harder
A friend recently shared a sharing of a screenshot of a reblogging of a reblogging of this tumblr post:
> Pro-Capitalist's defense of capitalism is just explaining how it works, and then when you say "yes I know, I just think it shouldn't be like that" they explain it to you again but a... |
cc2b9fa5-c988-43b4-b55a-5626d6d75392 | trentmkelly/LessWrong-43k | LessWrong | Commentary On "The Abolition of Man"
C.S. Lewis wrote a short book attacking moral subjectivism in education; it's available online here as a pdf, here as raw text, and here as a series of videos [1 2 3], and I think probably worth reading in full (at 50 pages or ~100 minutes of video at 1x speed). This post is mostly... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.