id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
9d609023-51a4-45a8-a99c-7aa8bd5cf92e | trentmkelly/LessWrong-43k | LessWrong | Towards dissolving the mystery of consciousness
1
Let us consider a world where it is well known that light is a wave, characterized by wavelength. The white color is known to be a mix of many different waves as shown by a prism separating sunlight into a rainbow. Physicists measure and catalog the wavelengths of dif... |
4b0d115a-b49a-4671-a2d3-21cdf463a2b3 | trentmkelly/LessWrong-43k | LessWrong | The Alignment Newsletter #12: 06/25/18
Highlights
Factored Cognition (Andreas Stuhlmuller): This is a presentation that Andreas has given a few times on Factored Cognition, a project by Ought that is empirically testing one approach to amplification on humans. It is inspired by HCH and meta-execution. These approaches... |
440f9ee8-de8c-479b-86aa-5d23ca377ec9 | trentmkelly/LessWrong-43k | LessWrong | Tortuga Meetups Starting this Thursday
Shannon and I are going to be hosting South Bay Less Wrong meetups at the Tortuga community in Mountain View on Thursday nights starting at 7. Come prepared to reveal something you're consistently irrational about. We'll spend some time throwing ideas around and then hang out a... |
1f2d3c53-3512-4cf9-bf87-aead44facc57 | StampyAI/alignment-research-dataset/special_docs | Other | “Unsupervised” translation as an (intent) alignment problem
Suppose that we want to translate between English and an alien language (Klingon). We have plenty of Klingon text, and separately we have plenty of English text, but it’s not matched up and there are no bilingual speakers.
We train GPT on a mix of English an... |
3aef3789-a55a-4ac7-bbe6-bb95f80f0630 | trentmkelly/LessWrong-43k | LessWrong | Mathematicians & mathletes: the Singularity Institute wants your strategic input!
The Singularity Institute is undergoing a series of important strategic discussions. There are many questions for which we wish we had more confident answers. We can get more confident answers on some of them by asking top-level mathemat... |
0b7621a5-4a1b-439b-af6b-d14461e1d74b | trentmkelly/LessWrong-43k | LessWrong | Help forecast study replication in this social science prediction market
This is a linkpost for: https://www.replicationmarkets.com/
From their sign-up page:
> Help the Replication Markets team spot reliable science, and win $$!
> From mid-2019 to mid-2020, we will run prediction markets on 3,000 recently-published... |
bd6a5a5d-5fa0-48ef-b43a-e45f36c3c080 | trentmkelly/LessWrong-43k | LessWrong | Zstd Window Size
At work we've recently been using zstd as a better-compressing alternative to gzip, and overall I've been pretty happy with it. A minor documentation gripe, though, is that the behavior around multithreaded compression is a bit unclear. I understand it's chunking the work and sending chunks to differe... |
2e2488a6-26d4-4555-b2cd-531d399f3c84 | trentmkelly/LessWrong-43k | LessWrong | Quantification of eyewitness reliability?
This mentions some of the limitations of eyewitness testimony; does anybody here have any references giving any hard numbers about how reliable eyewitness accounts are, under any given circumstances?
I'd like to be more conscious about my Bayesian-type updates of my beliefs b... |
2fe8b494-5a95-4351-8374-7379c8682ee2 | StampyAI/alignment-research-dataset/blogs | Blogs | Tallinn-Evans Challenge Grant Success!
Thanks to the effort of our donors, the Tallinn-Evans Singularity Challenge has been met! All $125,000 contributed will be matched dollar for dollar by Jaan Tallinn and Edwin Evans, raising a total of $250,000 to fund the Machine Intelligence Research Institute’s operations in 20... |
fbb01d38-fbaa-4c1b-b2cc-9349b61115c4 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Infra-Bayesian physicalism: a formal theory of naturalized induction
*This is joint work by Vanessa Kosoy and Alexander "Diffractor" Appel.*
*For the proofs, see [1](https://www.alignmentforum.org/posts/cj3PRu8QoFm4BA8oc/infra-bayesian-physicalism-proofs-part-i) and [2](https://www.alignmentforum.org/posts/CPr8bRGekTy... |
fa34ca8f-8229-408f-8940-b1e4f935a571 | trentmkelly/LessWrong-43k | LessWrong | ELK Sub - Note-taking in internal rollouts
My ELK submission was labelled under 'Strategy: train a reporter that is useful for another AI'. This is definitely a fair description, though the AI it needs to be useful to is itself - the reporter is essentially internalized. I also agree that the proposed counterexample, ... |
9daba229-6934-4a0d-9950-05401a08c14c | trentmkelly/LessWrong-43k | LessWrong | AI Governance: A Research Agenda
Allan Dafoe, head of the AI Governance team at FHI has written up a research agenda. It's a very large document, and I haven't gotten around to reading it all, but one of the things I would be most excited about is people in the comments quoting the most important snippets that give a ... |
6d58b48c-3b3a-40e8-bf88-b595c078dd6a | trentmkelly/LessWrong-43k | LessWrong | New Empty Units
Discussing housing policy in left-wing spaces I often run into an argument which is, essentially "building more units doesn't help with the housing shortage because so many will be bought by speculators with no intention of living there." This view, however, implies there's an excellent opportunity to ... |
c3b2ad33-44fa-4e4b-8ba6-cf59c1081c58 | trentmkelly/LessWrong-43k | LessWrong | Composting fruitless debates
Why do long, uninspiring, and seemingly-childish debates sometimes emerge even in a community like LessWrong? And what can we do about them? The key is to recognize the potentially harsh environmental effect of an audience, and use a dying debate to fertilize a more sheltered private con... |
463a2a9f-88b1-4d6f-8699-297c2d56c948 | trentmkelly/LessWrong-43k | LessWrong | Developmental Stages in Multi-Problem Grokking
Summary
This post is my capstone project for BlueDot Impact’s AI Alignment course. It was a 12 week online course that covered AI risks, alignment, scalable oversight, technical governance and more. You can read more about it here.
In this project, I investigated the use... |
284e5509-3a76-41b4-9a43-3f3093de0f48 | trentmkelly/LessWrong-43k | LessWrong | Cosmopolitan values don't come free
Short version: if the future is filled with weird artificial and/or alien minds having their own sort of fun in weird ways that I might struggle to understand with my puny meat-brain, then I'd consider that a win. When I say that I expect AI to destroy everything we value, I'm not s... |
7272fb06-96d5-4d6b-9ba8-e6ddce50bec7 | trentmkelly/LessWrong-43k | LessWrong | Circling
Circling is a practice, much like meditation is a practice.
There are many forms of it (again, like there are many forms of meditation). There are even life philosophies built around it. There are lots of intellectual, heady discussions of its theoretical underpinnings, often centered in Ken Wilber's Integra... |
b07cf9ef-65bf-436d-af4f-dfa377f984d0 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Moscow experimental LW group meetup
Discussion article for the meetup : Moscow experimental LW group meetup
WHEN: 25 July 2015 01:00:00PM (+0300)
WHERE: Москва, Ростокинский проезд, д.3
Welcome to experimental meetup of Moscow LW group!
Our plan:
* A talk about cognitive biases.
* Fallacymania game ( h... |
f3e1827e-49b7-469c-a402-b6d3f8ba521a | trentmkelly/LessWrong-43k | LessWrong | Good, Evil and (?)Indifferent God Challanges
Let's assume for the sake of discussion, that some form of the omniscient, omnipotent, personal creator of the universe(s) exists. (I do not hold that assumption, I am curious about some logical implications and correlations of what I am going to describe, everything here i... |
9d53ddad-7869-45c9-aab1-f21dbd70dc9c | StampyAI/alignment-research-dataset/arbital | Arbital | AIXI
[Marcus Hutter's AIXI](http://www.hutter1.net/ai/aixigentle.htm) is the [perfect rolling sphere](https://arbital.com/p/12b) of [advanced agent](https://arbital.com/p/2c) theory - it's not realistic, but you can't understand more complicated scenarios if you can't envision the rolling sphere. At the core of AIXI i... |
929ff0a2-3140-4e0a-899b-0fcaf02695aa | trentmkelly/LessWrong-43k | LessWrong | The Darwin Game - Conclusion
Evolution is unintelligent. The bugs removed intelligence from the design of the bots. The more bugs I wrote into my simulator, the better my simulation replicated real-world Darwinian population dynamics. After two alternate timelines with a buggy game engine, I have finally gotten around... |
28888a54-0899-455d-9460-c17a2e838fa0 | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: e1da9eb34eb18310
OpenAI, Google DeepMind and Anthropic sound alarm: 'We may be losing the ability to understand AI' | VentureBeat Skip to main content Events Video Special Issues Jobs VentureBeat Homepage Subscribe Artificial Intelligence View All AI, ML and Deep Learning Auto ML Data Labelling Synthetic Data Conv... |
d64cf5e8-37d8-4dcc-87ad-77cdcf1cff5d | trentmkelly/LessWrong-43k | LessWrong | Are aircraft carriers super vulnerable in a modern war?
It seems like aircraft carriers are a good candidate for something that only exists because it made sense in WWII and it looks the part of “impressive military asset”, i.e. it’s all larping at this point. It seems vulnerable to attack relative to its huge cost be... |
6ddfd29f-77ee-4a6b-81e2-08ebfa85d414 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | POWERplay: An open-source toolchain to study AI power-seeking
We're open-sourcing **POWERplay**, a research toolchain you can use to study power-seeking behavior in reinforcement learning agents. POWERplay was developed by [Gladstone AI](https://www.gladstone.ai/) for internal research.
![](https://39669.cdn.cke-cs.c... |
7538210a-c1b9-4520-bfd3-b6bf1727c871 | trentmkelly/LessWrong-43k | LessWrong | [S] D&D.Sci: All the D8a. Allllllll of it. Evaluation and Ruleset
This is a follow-up to last week's D&D.Sci scenario: if you intend to play that, and haven't done so yet, you should do so now before spoiling yourself.
There is a web interactive here you can use to test your answer, and generation code available her... |
bd26520f-328e-4ef2-81f6-2cdc0c0c3184 | trentmkelly/LessWrong-43k | LessWrong | New tool for exploring EA Forum, LessWrong and Alignment Forum - Tree of Tags
Explore the hidden treasures of the forums
With this tool you can zoom in on your favorite topics from EA Forum, LessWrong, and Alignment Forum. Or you can just wander around and see what you find.
You start by seeing the whole forum split ... |
fad5beda-fb45-4e93-8967-d9fbf689a269 | trentmkelly/LessWrong-43k | LessWrong | Book Review: On the Edge: The Business
Previously: The Fundamentals, The Gamblers
Having previously handled the literal gamblers, we are ready to move on to those who Do Business using Riverian principles.
Or at least while claiming to use Riverian principles, since Silicon Valley doesn’t fit into the schema as clea... |
134fb4e4-7ffe-4d36-a5ed-335c94d1e59e | trentmkelly/LessWrong-43k | LessWrong | Utopian hope versus reality
I've seen an interesting variety of utopian hopes expressed recently. Raemon's "Ritual" sequence of posts is working to affirm the viability of LW's rationalist-immortalist utopianism, not just in the midst of an indifferent universe, but in the midst of an indifferent society. Leverage Res... |
3e8178c4-a1a7-410f-8b38-11a34afbf81c | trentmkelly/LessWrong-43k | LessWrong | Can Covid-19 spread by surface transmission?
I've seen a lot of claims lately that coronavirus doesn't spread on surfaces, and therefore we can stop worrying about packages (and probably takeout food, even uncooked?).
My understanding of the claim is something like "we just haven't actually seen any evidence of surf... |
7afd7d5b-da84-4b12-a229-5b00ac34f5a4 | trentmkelly/LessWrong-43k | LessWrong | Whole Brain Emulation : the gentleman's choice for Friendly AI. Feedback needed, editing's a mess.
Eliezer Yudkowsky made the following statement "All of this makes it rather implausible that the first human being would be scanned into a computer and sanely upgraded before anyone anywhere first built an Artifici... |
2302196f-7571-43ee-a492-4ce85133a46f | trentmkelly/LessWrong-43k | LessWrong | RAISE is launching their MVP
After over a year of building the organisation and working and reworking the product, I’m glad to announce that RAISE will begin publishing lessons on a regular basis starting next Monday.
These lessons will include:
* An Inverse Reinforcement Learning (IRL) track, sourced from a set of... |
35b72c01-8a21-4911-a85a-f8603060994d | trentmkelly/LessWrong-43k | LessWrong | Seven sources of goals in LLM agents
LLM agents[1] seem reasonably likely to become our first takeover-capable AGIs.[2] LLMs already have complex "psychologies," and using them to power more sophisticated agents will create even more complex "minds." A profusion of competing goals is one barrier to aligning this type... |
9b0d8518-00e7-458f-a1d5-9e0c006cfa36 | trentmkelly/LessWrong-43k | LessWrong | Making DALL-E Count
Can DALL-E count? Does DALL-E's counting ability depend on what it is counting? Let's find out!
I only generate the images once and paste them in along with the prompt in quotations.
Numbers
"Zero"
"One"
"Two"
"Three"
We have three leaves, but I'm guessing DALL-E is noticing that "three"... |
a0e7a447-d368-4f8d-afd6-79f651875f1c | trentmkelly/LessWrong-43k | LessWrong | Prior probabilities and statistical significance
How does using priors affect the concept of statistical significance? The scientific convention is to use a 5% threshold for significance, no matter whether the hypothesis has been given a low or a high prior probability.
If we momentarily disregard the fact that there... |
fe20bb1e-042c-463f-8b32-726753404890 | trentmkelly/LessWrong-43k | LessWrong | stop solving problems that have already been solved
Crossposted from here.
I attended a collegiate Bollywood-Fusion dance competition a couple of weekends ago. This setting was nothing new to me; I competed at many competitions back when I was in college, and after graduating college, I spent a couple of years volunt... |
24b66e9c-ec6c-47a4-ac99-00e19080e83e | trentmkelly/LessWrong-43k | LessWrong | Exponentiation goes wrong first
The great Catholic mathematician Edward Nelson does not believe in completed infinity, and does not believe that arithmetic is likely to be consistent. These beliefs are partly motivated by his faith: he says arithmetic is a human invention, and compares believing (too strongly) in its... |
8f60c75b-5bb4-4ee3-95b8-976e1de9c64d | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | New reference standard on LLM Application security started by OWASP
The [OWASP Top 10](https://owasp.org/www-project-top-ten/)[[1]](#fny7npzbpes8s) is the probably the most well-known and recognised reference standard for the most critical web application security risks. This organisation has now started to working on... |
4d1aa97c-4c4c-4e51-b9ce-099a1ba7bd44 | trentmkelly/LessWrong-43k | LessWrong | Brute-forcing the universe: a non-standard shot at diamond alignment
This is an expanded version of my answer to application problem 2 for Nate Soares and Vivek Hebbar's SERI MATS stream. This Alignment idea is somehow non-standard. See Section C for a discussion of that, along with some general ideas on Alignment. Th... |
d53600fd-71c0-46f0-8eef-343b00008076 | trentmkelly/LessWrong-43k | LessWrong | I’m an Artist. How Can an Artist Help?
I get asked that a lot, and increasingly I wonder; does the person asking think I’m a non-profit president? Do they imagine that when I was a kid, people asked me “what do you want to be when I grew up” and I said “I want to help people, so I’d like to run the United Way” and t... |
04cc3a0e-b7de-4733-85b5-38e82790e3f5 | trentmkelly/LessWrong-43k | LessWrong | How do I use caffeine optimally?
I just started a new job, and I'm really excited for the potential of drinking coffee, but I'm worried about dependency or other negative effects.
I don't want to be upset or feel unwell if I don't have coffee, and I don't want any long-term negative health effects from drinking coffe... |
a39d2b24-de89-4cb9-a2bb-6daf91080817 | StampyAI/alignment-research-dataset/arxiv | Arxiv | The Pragmatic Turn in Explainable Artificial Intelligence (XAI)
The Pragmatic Turn in Explainable Artificial Intelligence (XAI) Minds and Machines, 29(3), 441-459 DOI: 10.1007/s11023-019-09502-w Please quote the printed version Andrés Páez Universidad de los Andes apaez@uniandes.edu.co ABSTRACT In this paper I argu... |
5f749eeb-b672-42b0-9f93-516a648d7c36 | trentmkelly/LessWrong-43k | LessWrong | LINK: Where Humans Meet Machines: Intuition, Expertise and Learning (Brynjolfsson talks to Kahneman)
None |
7fca5170-baf7-4412-9e9b-2360f7857b7f | LDJnr/LessWrong-Amplify-Instruct | LessWrong | ""All men are mortal. Socrates is a man. Therefore Socrates is mortal." — Aristotle(?) Socrates raised the glass of hemlock to his lips... "Do you suppose," asked one of the onlookers, "that even hemlock will not be enough to kill so wise and good a man?" "No," replied another bystander, a student of philosophy; "all m... |
34fd0b71-90ef-4424-bce1-ed8ae785e56c | trentmkelly/LessWrong-43k | LessWrong | Examples of Acausal Trade with an Alien Universe?
I understand the basic concept of counterfactual trade, and I can understand some examples where it can make sense to trade acausally between two different histories of our familiar world; for example, in Embedded Agency, Scott G and Abram discuss a game where Alice re... |
50ac34f1-12e1-4545-bdf9-67bc646d70b6 | trentmkelly/LessWrong-43k | LessWrong | Expectation = intention = setpoint
When I was first learning about hypnosis, one of the things that was very confusing to me is how "expectations" relate to "intent". Some hypnotists would say "All suggestion is about expectation; if they expect to have an experience they will", and frame their inductions in terms of... |
61151da9-48ca-48b8-aba6-795f91b4ac7c | trentmkelly/LessWrong-43k | LessWrong | Meetup : Washington DC: Goals, Political Advocacy as Effective Altruism, and Stories
Discussion article for the meetup : Washington DC: Goals, Political Advocacy as Effective Altruism, and Stories
WHEN: 17 November 2013 03:00:00PM (-0500)
WHERE: National Portrait Gallery, Washington, DC 20001, USA
So, we came up w... |
3d1ddefc-426e-47e3-92be-902505290435 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Melbourne Social Meetup
Discussion article for the meetup : Melbourne Social Meetup
WHEN: 18 July 2014 06:30:00PM (+1000)
WHERE: 9/239 Canterbury Rd, Blackburn
The social meetup is on again for July! This time we will be meeting in Blackburn. Come along for a chat and a game or two.
We'll be starting at 6... |
3dbdc6c8-6fa1-4a46-a4fb-60e38d730587 | trentmkelly/LessWrong-43k | LessWrong | Rationality Quotes January - March 2017
Another quarter, another rationality quotes thread. The rules are:
* Provide sufficient information (URL, title, date, page number, etc.) to enable a reader to find the place where you read the quote, or its original source if available. Do not quote with only a name.
* Post ... |
fe0efd6f-7962-4d1e-8e2a-f5bebc586121 | trentmkelly/LessWrong-43k | LessWrong | Naturalistic dualism
And it's all around us
as ghosted machines […]
And as much as I'd like to
believe there's a truth
about our illusion,
well, I've come to conclude
there's just nothing beyond it
the mind can perceive
except for the pictures
in the space in between.
Jan Blomqvist, The Space In... |
9120d23d-e8aa-4a7b-b059-6b772ef3d27d | trentmkelly/LessWrong-43k | LessWrong | Freezer Contents
This afternoon I defrosted our chest freezer, which I probably should have done about two years ago. Aside from having spent a long time dealing with frost buildup, another downside of waiting so long turned out to be that by the time I learned that the drain didn't work it was already out of warranty... |
432bd8f7-b0bc-4c97-9453-3ff2b3a97bfd | trentmkelly/LessWrong-43k | LessWrong | A Critique of AI Alignment Pessimism
Epistemic status: Exploratory. I have read Superintelligence, the Sequences and some other articles on AI risk, and am looking to take things back to basics. This article sums up where I'm at right now. I welcome feedback on the points people disagree with, requests for clarifica... |
00b92b13-ed38-408c-aebb-0275e33332c8 | trentmkelly/LessWrong-43k | LessWrong | Renaming "Frontpage"
We're about to revamp the frontpage design (you can see a hint of what's to come on the new /allPosts page).
While we're at it, I'd like to fix a longstanding problem, which is that "frontpage posts" is a fairly confusing concept for the site to rely on.
"Frontpage posts" are posts that the mods... |
763fdf38-da18-4f14-94f9-0eb497ceb120 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "We used to make land. We built long wharves for docking ships, and
then over time filled in the areas between them. Later we built up
mudflats wholesale to make even larger areas. Here's a map of Boston
showing how much of the land wasn't previously dry: (Map
reproduction courtesy of the Norman B. Leventhal Map & Educ... |
6f96b0c9-f8cf-4028-b5fb-2ffffafb78f1 | trentmkelly/LessWrong-43k | LessWrong | 0 And 1 Are Not Probabilities
One, two, and three are all integers, and so is negative four. If you keep counting up, or keep counting down, you’re bound to encounter a whole lot more integers. You will not, however, encounter anything called “positive infinity” or “negative infinity,” so these are not integers.
Posi... |
db95940a-4146-4c1c-a74f-861a0e874cfc | trentmkelly/LessWrong-43k | LessWrong | What would you do with a financial safety net?
In the open thread, moridinamael hypothesized that LWers would be willing to take more risks in order to become rich if they had a financial safety net. This seems like an idea worth exploring further.
What would you do if you had a financial safety net (maybe a year'... |
99699250-d36a-4d06-a2ca-d66aa7608c80 | trentmkelly/LessWrong-43k | LessWrong | My take on agent foundations: formalizing metaphilosophical competence
I have some rough intuitions about the purpose of MIRI's agent foundations agenda, and I'd like to share them here. (Note: I have not discussed these with MIRI, and these should not be taken to be representative of MIRI's views.)
I think there's a... |
f5acd74c-da39-41d7-9ade-21d73fb29816 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Comments on Manheim's "What's in a Pause?"
I agree with David Manheim's post at a high level. I especially agree that a pause on large training runs is needed, that “We absolutely cannot delay responding”, and that we should be focusing on a pause mediated by “a multilateral agreement centered on countries and interna... |
cf1af560-6b1c-4f27-a788-b27670796c89 | trentmkelly/LessWrong-43k | LessWrong | A wild theist platonist appears, to ask about the path
I recognize the title could be more informative. At the same time I believe it says what is important.
I believe in a deity, I believe in mathematical entities in the same way.
The community of LessWrong (from whenceforth: LessWrong) is deeply interesting to me... |
d39368ed-c4f9-47c5-bbfa-edbb8ede0a94 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Seattle Secular Solstice
Discussion article for the meetup : Seattle Secular Solstice
WHEN: 10 December 2016 04:00:00PM (-0800)
WHERE: 114 Alaskan Way S, Seattle, Washington 98104
A night to gather and celebrate humanity, warmth, knowledge and progress, the solstice is an annual tradition full of songs, st... |
7379a1a2-2264-447c-823a-7d8db4cfb097 | trentmkelly/LessWrong-43k | LessWrong | Implications of simulators
In this post, I:
* Explain the idea of language models as simulators in a way I find compelling.
* Introduce the notion of separate simulator selectors and simulation infrastructure within a model, and provide some evidence for this.
* Discuss what the theory means about the agency of pr... |
b7e466e9-a185-4c20-8ca8-f09ea820f158 | trentmkelly/LessWrong-43k | LessWrong | "Playing to Win"
John F. Rizzo is an expert on losing. However, if you want to win, you would do better to seek advice from an expert on winning.
David Sirlin is such an expert, a renowned Street Fighter player and game designer. He wrote a series of articles with the title "Playing to Win", about playing competitive... |
45df6853-f5d8-410f-adea-9ce096d53d95 | trentmkelly/LessWrong-43k | LessWrong | The Critical Rationalist View on Artificial Intelligence
Critical Rationalism (CR) is being discussed on some threads here at Less Wrong (e.g., here, here, and here). It is something that Critical Rationalists such as myself think contributors to Less Wrong need to understand much better. Critical Rationalists claim t... |
7935d993-f859-4c90-b751-8088de5abb60 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Article Review: Google's AlphaTensor
[Cross-posted from my Substack at <https://aizi.substack.com/p/article-review-googles-alphatensor]>
[?
I wonder about a scenario where the first AI with human or superior capabilities would be nothing goal-oriented, eg a language model like GPT. Then one instance of it would be used, possibly by a random user, to make a conversational agen... |
67a8678d-1f0d-4a10-a967-4d812648c962 | trentmkelly/LessWrong-43k | LessWrong | Resetting Gandhi-Einstein
Toy model of an upload-based AI that doesn't seem to suffer too many of the usual flaws:
Find an ethical smart scientist (a Gandhi-Einstein), upload them, and then run them at ultra high speed, with the mission of taking over the world/bringing friendliness to it. Every hour of subjective ti... |
7dcb2264-1759-4ba7-9f55-f0108ed7dae4 | trentmkelly/LessWrong-43k | LessWrong | Conflicting advice on altruism
As far as I can tell, rather than having a single well-defined set of preferences or utility function, my actions more closely reflect the outcome of a set of competing internal drives. One of my internal drives is strongly oriented towards a utilitarian altruism. While the altruist inte... |
d02f4c1e-14bb-49c6-bfe9-305ac4c02f64 | trentmkelly/LessWrong-43k | LessWrong | Continuous Adversarial Quality Assurance: Extending RLHF and Constitutional AI
Introduction
Lately, the problem of aligning artificial intelligence with human values rapidly changed its status from hypothetical to most concrete, with the rise of more general and more powerful models. The existing methods (Constitutio... |
72c1688b-6cbf-46f9-9770-35d0d94c24de | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Five neglected work areas that could reduce AI risk
*Crossposted to Lesswrong* [*here*](https://www.lesswrong.com/posts/fEAGPyHR9GaK2cwRq/five-neglected-work-areas-that-could-reduce-ai-risk)
Tldr: We identify five areas of work that should be further investigated:
1. Helping information aggregators scale during adva... |
9f5fbcc0-934f-45df-88ff-56f63fe16bb7 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Useful Statistical Biases
Today's post, Useful Statistical Biases was originally published on April 1, 2007. A summary (from the LW wiki):
> If you know an estimator has high variance, you can intentionally introduce bias by choosing a simpler hypothesis, and thereby lower expected variance while raising ... |
248f7146-326a-459f-b6fd-19e653a7bba9 | trentmkelly/LessWrong-43k | LessWrong | Doing Research Part-Time is Great
This is a crosspost from https://chillphysicsenjoyer.substack.com/p/pursuing-physics-research-part-time.
Intro
Disclaimer - I’m a part-time research associate doing biophysics with a uni research group in the UK. But I have a day job in an unrelated field that pays the bills.
Whil... |
24c9545c-2ff0-41db-8c1e-6516fe01dd8f | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Limiting Causality by Complexity Class
The standard account of causality depends on the idea of intervention: The question of what follows if X not just naturally occurs, but we bring it about artificially independently of its usual causes. This doesn't go well with embedded agency. If the agent is part of the world,... |
a67f4c98-95ef-4f95-a7f6-a5f555a45edc | trentmkelly/LessWrong-43k | LessWrong | The Grandest Vision for Humanity (Light)
This is the third speech in the wedding ceremony of Ruby & Miranda. See the Sequence introduction for more info. The speech was given by Riva-Melissa Tez.
----------------------------------------
Tara descends from podium.
Brienne: We hope to banish the darkness. But our amb... |
70a1ba9c-91d0-4dd0-b386-442ee4f94707 | trentmkelly/LessWrong-43k | LessWrong | Preschooler Turnovers
I recently got into making proper flaky pastry, and while it's a bit of a hassle it's really very tasty. I think I started with this recipe, and I've been getting decent at it:
The kids really like the turnovers, and will ask for them much more often than I'm up for.
A few days ago Anna (5y) ... |
aac691cb-04ff-4006-9563-db71752e5773 | trentmkelly/LessWrong-43k | LessWrong | Running the Stack
Look at the image here:
https://en.wikipedia.org/wiki/Stack_(abstract_data_type)
After looking at that image, you understand the concept well enough to use it as a mental model.
Hard-won lessons —
(1) I joke that "meditation is having exactly one thing on the stack." One thing at a time on the st... |
1139f587-b9c2-4f2a-9584-001e410c8e5f | trentmkelly/LessWrong-43k | LessWrong | How does information affect hookups?
With social networking sites enabling the romantically inclined to find out more about a potential lover before the first superficial chat than they previously would have in the first month of dating, this is an important question for the future of romance.
Lets assume that in loo... |
b780a3b6-db93-45a8-b8ad-5288f54d78cc | trentmkelly/LessWrong-43k | LessWrong | ≤10-year Timelines Remain Unlikely Despite DeepSeek and o3
[Thanks to Steven Byrnes for feedback and the idea for section §3.1. Also thanks to Justis from the LW feedback team.]
Remember this?
Or this?
The images are from WaitButWhy, but the idea was voiced by many prominent alignment people, including ... |
509798e8-b878-43c7-a6b1-610f2e12e8d4 | trentmkelly/LessWrong-43k | LessWrong | Stats Advice on a New N-back Game
Cross-posted to my blog. I expect this will be of some interest to the LessWrong community both because of previous interest in N-back and because of the opportunity to apply Bayesian statistics to a real-world problem. The main reason I'm writing this article is to get feedback on my... |
f782e593-ffe2-4c7a-a772-8934b58a06b0 | trentmkelly/LessWrong-43k | LessWrong | The Rhythm of Disagreement
Followup to: A Premature Word on AI, The Modesty Argument
Once, during the year I was working with Marcello, I passed by a math book he was reading, left open on the table. One formula caught my eye (why?); and I thought for a moment and said, "This... doesn't look like it can be right...... |
ee708a09-d9a0-4b8e-af58-1434de4732ce | trentmkelly/LessWrong-43k | LessWrong | How likely is it that AI will torture us until the end of time?
Disclaimer: in this post I touch on some very dark and disturbing topics. I'm talking about suicide, my reasoning may be wrong and should not be used to retroactively justify suicide.
I've been stuck on s-risks for over a month now. My life has been turn... |
4c3dff5d-c22b-42ce-ad72-9a2c1c28c7d2 | trentmkelly/LessWrong-43k | LessWrong | Announcing #AISummitTalks featuring Professor Stuart Russell and many others
Register now: #AISummitTalks II, featuring Professor Stuart Russell and many others @ Wilton Hall, Bletchley, Tuesday 31 October, 14:00 to 15:30 GMT! - https://lu.ma/n9qmn4h6
About the Talks
The first edition of #AISummitTalks: Navigating E... |
ab1e5833-0432-4446-b8fd-1c18f081e014 | trentmkelly/LessWrong-43k | LessWrong | We have a new discussion area
After contributions from a number of us (by random example here, here) over a number of months, particularly User:wmoore and User:tommccabe (and all happening before User:Yvain's work here, so we missed those ideas) we have a discussion area.
Discussion, including discussion of the discu... |
7482e628-ea44-40ed-8e7a-b4609655f075 | trentmkelly/LessWrong-43k | LessWrong | Tags or Sub-Groups
There are two main ways of dividing discussion in a group so that people only see what they want to see and both have advantages and disadvantages.
Tags are the most common method used. They have the following advantages, mostly related to flexibility:
* Anyone can invent a new tag on the spot an... |
f785fc17-0578-4880-a51d-9241686f6729 | trentmkelly/LessWrong-43k | LessWrong | Scalable Oversight and Weak-to-Strong Generalization: Compatible approaches to the same problem
Thanks to Roger Grosse, Cem Anil, Sam Bowman, Tamera Lanham, and Mrinank Sharma for helpful discussion and comments on drafts of this post.
Throughout this post, "I" refers to Ansh (Buck, Ryan, and Fabien helped substant... |
1f549d69-8418-4a58-a6d8-2673b8a76118 | trentmkelly/LessWrong-43k | LessWrong | A challenge for AGI organizations, and a challenge for readers
(Note: This post is a write-up by Rob of a point Eliezer wanted to broadcast. Nate helped with the editing, and endorses the post’s main points.)
Eliezer Yudkowsky and Nate Soares (my co-workers) want to broadcast strong support for OpenAI’s recent dec... |
0adae875-f539-42f5-9798-1a60762d67ca | trentmkelly/LessWrong-43k | LessWrong | Playing With a Talk Box
Sometimes I describe my goal in playing around with different ways of making music as trying to maximize my musical information rate: how many bits per second? With my hands I'm generally playing keyboard or mandolin, and they are very busy; compare to trumpet, where one hand is choosing combin... |
83f3dbab-e81b-4160-99fb-36fddf802a58 | trentmkelly/LessWrong-43k | LessWrong | Is it worthwhile to save the cord blood and tissue?
My wife and I are expecting a baby this May. I only recently learned about this, but apparently there is an option to save the cord blood and tissue during the delivery. This seems potentially very useful, so I'm wondering if anyone has done research into this or has... |
c2abd0b0-aee1-41b6-8e8d-2ea51b4534da | StampyAI/alignment-research-dataset/special_docs | Other | Robust program equilibrium
Theory and Decision (2019) 86:143–159
https://doi.org/10.1007/s11238-018-9679-3
Robust program equilibrium
Caspar Oesterheld1,2
Published online: 23 November 2018
© The Author(s) 2018
Abstract
One approach to achieving cooperation in the one-shot prisoner’s dilemma is Ten-
nenholtz’s (Games ... |
e0df659f-51c3-49a9-a1a1-4dcd064757ae | trentmkelly/LessWrong-43k | LessWrong | [LINK] Physicist Carlo Rovelli on Modern Physics Research
A blog post in Scientific American, well worth reading. Rovelli is a researcher in Loop Quantum Gravity.
Some quotes:
Horgan: Do multiverse theories and quantum gravity theories deserve to be taken seriously if they cannot be falsified?
Rovelli: No.
Horgan:... |
74023d61-9c46-41ad-9b74-7ca079ba339e | StampyAI/alignment-research-dataset/arxiv | Arxiv | SentRNA: Improving computational RNA design by incorporating a prior of human design strategies
SentRNA: Improving computational RNA design by incorporating a prior of human design
strategies
Jade Shi1, EteRNA players, Rhiju Das2, and Vijay S. Pande3*
1. Department of Chemistry, Stanford University, jadeshi@stanfo... |
fea3519f-9f5f-4cea-9d15-c34a5025287c | trentmkelly/LessWrong-43k | LessWrong | Mapping the Archipelago
I got excited reading Meta-tations on Moderation: Towards Public Archipelago for two reasons: there's a clear island of the archipelago I've been mostly avoiding on LessWrong, and the whole place has been growing at a high enough rate to demand fracturing.
Since we have the chance to direct th... |
0e417439-5eff-4238-b554-53620500f26f | trentmkelly/LessWrong-43k | LessWrong | Two angles on Repetitive Strain Injury
Discussion of buckling-spring keyboards, which give accurate tactile feedback. You can get them for about $70, and a lot of people swear by them.
Here's my RSI story: Some years ago, I was getting a lot of pain in my right elbow, presumably as + result of excessive Blockout (3D ... |
39f71831-220e-4b9c-93b6-d9c38c6c4099 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Adversarial Robustness as a Prior for Learned Representations
1 Introduction
---------------
Beyond achieving remarkably high accuracy on a variety of
tasks [[KSH12](#bib.bibx33), [He+15](#bib.bibx26), [CW08](#bib.bibx11)], a major
appeal of deep learning is the ability to learn effective feature
representations of... |
9774894f-7d48-4206-a05d-fb7bef8b9b60 | trentmkelly/LessWrong-43k | LessWrong | A market is a neural network
If you were a bad AI, what would you do? I’d make myself useful.
First, I’d provide humans with everything they asked for. That would encourage them to give me more tasks, which I would reliably carry out. I’d suggest new ways I could make their lives easier. I’d gradually take over all t... |
5c1f6760-0176-43e0-9d37-dc8963b88a39 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Questions of Reasoning under Logical Uncertainty
I'm pleased to announce a new paper from MIRI: *[Questions of Reasoning Under Logical Uncertainty](https://intelligence.org/files/QuestionsLogicalUncertainty.pdf)*.
Abstract:
>
> A logically uncertain reasoner would be able to reason as if they know both a program... |
bc5c7bd6-4f99-4387-bbc0-e699a70ae9db | trentmkelly/LessWrong-43k | LessWrong | The (local) unit of intelligence is FLOPs
[Crossposting again on Lesswrong and Windowsontheory, with the hope I am not overstaying my welcome in LW.]
Wealth can be measured by dollars. This is not a perfect measurement: it’s hard to account for purchasing power and circumstances when comparing people across varying ... |
f1aa7077-7af1-4528-8255-d33fc43dd5c8 | trentmkelly/LessWrong-43k | LessWrong | What would you like to see posts about?
I've just come back from the latest post on revitalizing LW as a conversational locus in the larger Rational-Sphere community and I'm personally still very into the idea. This post is directed at you if you're also into the idea. If you're not, that's okay; I'd still like to giv... |
be9d405d-a190-461e-aaa3-e519a5da045b | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Planning capacity and daemons
Update March 2023: This is too confusing, skip it.
In [my last post](https://www.alignmentforum.org/posts/E3vqfD3CLtNDNoeBr/inner-alignment-what-are-we-pointing-at) I asked if there were more natural terms for inner alignment, outer alignment, and mesa optimizers. I'm looking for a ... |
0dc865c5-59fb-4e4d-a7a2-eabd68f6dbc6 | trentmkelly/LessWrong-43k | LessWrong | Anti-akrasia remote monitoring experiment
So we (Richard Hollerith and me) tried out my anti-akrasia idea. Actually we've been doing it for more than a week now. Turns out it works just like I thought it would: when you know an actual person is checking your screen at random intervals, and they will IM you whenever yo... |
23ac72e7-570f-4cc6-b2ba-4a1b19621e53 | trentmkelly/LessWrong-43k | LessWrong | LessWrong Hamburg Third Meetup Notes: Small Steps Forward
Review of our third Meetup : LessWrong Hamburg - Structure
Summary
To make it short: We didn't follow the nice agenda we planned. We did the procrastination topic but diverged a lot.
Course of events
In the long open beginning (expected) we talked a lot, p... |
9dcfb663-78c2-4683-9e18-e41af7893d42 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Singular learning theory and bridging from ML to brain emulations
This is a fairly "chat"-style dialogue that I (kave) had with Garrett about singular learning theory (SLT) and his [ambitious plans](https://www.lesswrong.com/posts/d4qbjx35SBMGyFNWZ/my-hopes-for-alignment-singular-learning-theory-and-whole) for solving... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.