id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
cbcc737a-2775-46ce-b581-0ed7bc4496e0 | trentmkelly/LessWrong-43k | LessWrong | Post/meta-skepticism I
Less Wrong has been significantly influenced by the skeptic movement. This has general been good for the epistemic health of our community, but at the same time we should also worry about whether everything we have inherited is true and beneficial. In other words, we need to apply skepticism to ... |
6c2cfd83-9ef7-4684-a716-9c58dc13868c | trentmkelly/LessWrong-43k | LessWrong | Meetup : MelbLW Social Meetup: Feb 2016
Discussion article for the meetup : MelbLW Social Meetup: Feb 2016
WHEN: 19 February 2016 06:30:00PM (+1100)
WHERE: Bull and Bear Tavern, 347 Flinders Lane, Melbourne VIC 3000
This month's LessWrong Melbourne social meetup is on again this week!
Facebook event page: https://... |
70e3e6ba-cf7f-41f4-bb24-08076f89e0f0 | trentmkelly/LessWrong-43k | LessWrong | Catastrophic sabotage as a major threat model for human-level AI systems
Thanks to Holden Karnofsky, David Duvenaud, and Kate Woolverton for useful discussions and feedback.
Following up on our recent “Sabotage Evaluations for Frontier Models” paper, I wanted to share more of my personal thoughts on why I think catas... |
e68c4ff3-6119-47f8-b4a8-e73896ac85ee | trentmkelly/LessWrong-43k | LessWrong | Another Case Study of Inadequate Equilibrium in Medicine
Science Journalist Julie Rehmeyer suffered from crippling Chronic Fatigue Syndrome. She's plugging a new book discussing her experiences with the not-medically-established treatment. The article in this link post discusses her decision to attempt the treatment, ... |
525c2c46-6639-4a86-b94c-19fea9390210 | StampyAI/alignment-research-dataset/arbital | Arbital | Quotient by subgroup is well defined if and only if subgroup is normal
Let $G$ be a [https://arbital.com/p/-3gd](https://arbital.com/p/-3gd) and $N$ a [https://arbital.com/p/-4h6](https://arbital.com/p/-4h6) of $G$.
Then we may define the *quotient group* $G/N$ to be the set of [left cosets](https://arbital.com/p/4j4)... |
25f32810-36f7-44e9-a365-71c5bc92ff9a | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | [AN #148]: Analyzing generalization across more axes than just accuracy or loss
Alignment Newsletter is a weekly publication with recent content relevant to AI alignment around the world. Find all Alignment Newsletter **[resources here](http://rohinshah.com/alignment-newsletter/)**. In particular, you can look through... |
dfbef90d-537e-4e8d-98b0-b7b494e1a65f | trentmkelly/LessWrong-43k | LessWrong | Taxonomy of possibility
Followup to: Will issues are quite nearly skill issues
You do a thing iff you can do it and you want to do it.
Something you can do, but didn't, looks just the same to the simple observer as something you can't do. Likewise with what you want to do, but didn't. When you don't do something, ob... |
947220aa-c9c7-4ead-b1ba-4642bf361f93 | trentmkelly/LessWrong-43k | LessWrong | Friedman's "Prediction vs. Explanation"
David D. Friedman asks:
> We do ten experiments. A scientist observes the results, constructs a theory consistent with them, and uses it to predict the results of the next ten. We do them and the results fit his predictions. A second scientist now constructs a theory consistent... |
1f9bd70b-8b7e-4990-aa06-810be9ab0823 | trentmkelly/LessWrong-43k | LessWrong | Rationality Reading Group: Part I: Seeing with Fresh Eyes
This is part of a semi-monthly reading group on Eliezer Yudkowsky's ebook, Rationality: From AI to Zombies. For more information about the group, see the announcement post.
----------------------------------------
Welcome to the Rationality reading group. Thi... |
901d66e0-3b9b-4463-a9c1-e69bf664a6d9 | trentmkelly/LessWrong-43k | LessWrong | Paper: "The Ethics of Advanced AI Assistants" -Google DeepMind
Google Deepmind just released a 200 page paper. A few Authors are from the community. |
4f7106f3-c06d-4c05-85c9-a0df87e89a08 | trentmkelly/LessWrong-43k | LessWrong | [Prize] Essay Contest: Cryonics and Effective Altruism
I'm starting a contest for the best essay describing why a rational person of a not particularly selfish nature might consider cryonics an exceptionally worthwhile place to allocate resources. There are three distinct questions relating to this, and you can pick a... |
937dbb32-8f4c-439f-835b-4fbea82835fd | trentmkelly/LessWrong-43k | LessWrong | Counterintuitive World - Good intro to some topics
http://motherjones.com/kevin-drum/2010/09/counterintuitive-world
|
57ca8bf0-a8e6-4a97-a353-3de0cd3c6b35 | trentmkelly/LessWrong-43k | LessWrong | What does "probability" really mean?
Recently I read Wei Dai's "What Are Probabilities, Anyway?" post, and just wanted to see if the LessWrong community has now reached a consensus on the interpretation of probability. I am of the impression that most LWers endorse multiverse theories, whether it be the Many-Worlds In... |
a893560a-5576-483d-9e54-cf0fe1ea991c | trentmkelly/LessWrong-43k | LessWrong | Simulacrum Levels of Trust
Epistemic Status: Pattern matching. The model completes a pattern in an intuitive way. Little originality besides the act of pattern completion itself.
As I was reading the recent discussion about networks of trust, I noticed a mismatch between models described therein and the social enviro... |
7b68a337-ba94-4c15-b62e-63ba9049bbf9 | trentmkelly/LessWrong-43k | LessWrong | Forecasting as a tool for teaching the general public to make better judgements?
Tl;dr: We are wondering whether there might be more value in forecasting as a popularized educational activity than seems to be the consensus. Looking for explicit opinions and feedback.
We are a team working on popularizing evidence- a... |
5fd08050-b357-4822-bc26-f864966d7ba5 | trentmkelly/LessWrong-43k | LessWrong | [Aspiration-based designs] 2. Formal framework, basic algorithm
Summary. In this post, we present the formal framework we adopt during the sequence, and the simplest form of the type of aspiration-based algorithms we study. We do this for a simple form of aspiration-type goals: making the expectation of some variable ... |
e348598f-4bbb-47cd-aa27-2afbe9905e22 | trentmkelly/LessWrong-43k | LessWrong | Meetup : San Francisco Meetup: Board Games
Discussion article for the meetup : San Francisco Meetup: Board Games
WHEN: 09 March 2015 06:15:00PM (-0700)
WHERE: 1390 Market St., San Francisco, CA
(Note that this is back in my apartment, not app academy: we have tables and boardgames here).
We'll be meeting up to han... |
96297d1a-b229-4a56-acc4-f554f424c64e | StampyAI/alignment-research-dataset/blogs | Blogs | Fiction
*While I tend to publish most of my writing for free, I strongly believe that money is not evil. Therefore, anyone is welcome to take characters or settings from my original online fiction, such as the beisutsukai or the Baby-Eating Aliens, and use them in new commercial works of your own creation. I do ask fo... |
464c28fa-6fe4-4308-af70-d31a5e31415e | trentmkelly/LessWrong-43k | LessWrong | Two Truths and a Lie
Response to Man-with-a-hammer syndrome.
It's been claimed that there is no way to spot Affective Death Spirals, or cultish obsession with the One Big Idea of Everything. I'd like to posit a simple way to spot such error, with the caveat that it may not work for every case.
There's an old game ca... |
94b962dc-a3de-4eb5-ab89-4a207c629f66 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Two Alternatives to Logical Counterfactuals
The following is a critique of the idea of logical counterfactuals. The idea of logical counterfactuals has appeared in previous agent foundations research (especially at MIRI): [here](https://intelligence.org/2017/03/18/new-paper-cheating-death-in-damascus/), [here](https:/... |
8b7b138d-4ffb-4bfa-884a-565f280b338d | trentmkelly/LessWrong-43k | LessWrong | Parenting Technique: Increase Your Child’s Working Memory
I continually train my ten-year-old son’s working memory, and urge parents of other young children to do likewise. While I have succeeded in at least temporarily improving his working memory, I accept that this change might not be permanent and could end a few... |
6f9a7428-0a94-4ff6-9cf0-638c53fe773c | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Could Democritus have predicted intelligence explosion?
Also see: [History of the Friendly AI concept](http://friendly-ai.com/faq.html#WhatIsTheHistory).
The [ancient atomists](http://en.wikipedia.org/wiki/Atomism) reasoned their way from first principles to materialism and atomic theory before Socrates began his li... |
4a50f313-31db-435c-bef4-27de8cbf1e21 | trentmkelly/LessWrong-43k | LessWrong | Passing Troll Bridge
In an earlier discussion about the Troll Bridge problem, Abram mentioned a Lobian proof that a logical induction based agent would converge to not crossing the bridge.
It looked rather sketchy, though, and further discussion by Paul in the comments revealed that Troll Bridge might be passable.
(... |
5e84d4c1-86ba-4af6-ad1b-280108842a93 | trentmkelly/LessWrong-43k | LessWrong | Weekly LW Meetups: Portland, Berkleley, San Diego, Pittsburgh, Houston, Seattle, Madison, Fort Collins, Sydney, Melbourne
There are upcoming irregularly scheduled Less Wrong meetups in:
* Portland Meetup?: 14 January 2012 12:00PM
* San Diego experimental meetup: 15 January 2012 01:00PM
* Pittsburgh Meetup: Big Gam... |
318915d1-4e8c-4f45-b440-c77e53fac718 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Something to Protect
Today's post, Something to Protect was originally published on 30 January 2008. A summary (taken from the LW wiki):
> Many people only start to grow as a rationalist when they find something that they care about more than they care about rationality itself. It takes something reall... |
45c9350f-a1c6-441c-8bc9-790ff0c5514c | trentmkelly/LessWrong-43k | LessWrong | [Thought Experiment] Tomorrow's Echo - The future of synthetic companionship.
For those who are interested in the likely future tension between AI and human companionship, you may be interested in checking out a thought experiment that I've crafted.
The distant future of Replika and other AI Companion apps could expl... |
dc3a7e65-4fe1-4e4e-b3b3-fd596f6917e6 | trentmkelly/LessWrong-43k | LessWrong | On the possibility of impossibility of AGI Long-Term Safety
Preface
The following article is a layman’s summary of researcher and philosopher Forrest Landry’s work titled No People as Pets: A Dialogue on the Complete Failure of Exogenous AGI/APS Alignment. It is a basic presentation of an argument as to why any form o... |
377d2cfd-b471-421b-9e4d-87650bedd76d | trentmkelly/LessWrong-43k | LessWrong | Destructive mathematics
Follow-up to: Constructive mathematics and its dual
In last post, I've introduced constructive mathmatics, intuitionistic logic (JL) and its dual, uninspiringly called dual-intuitionistic logic (DL).
I've said that JL differs from classical logic about the status of the law of excluded middle,... |
aecaf470-beee-4eff-ab0a-5da7c799fd99 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Hyderabad Meetup
Discussion article for the meetup : Hyderabad Meetup
WHEN: 08 July 2012 03:00:00PM (+0530)
WHERE: Hyderabad, India
Cafe Coffee Day, NEXT TO Airtel Showroom, Madhapur Main Road, Madhapur, Hyderabad (Landmark: OPPOSITE Krishe Sapphire)
Ph: +91 9566057018
Discussion article for the meetup ... |
055da46a-5597-4113-9a9d-8d3db328943e | trentmkelly/LessWrong-43k | LessWrong | Adumbrations on AGI from an outsider
Preamble
A lot of people have written against AI Doom, but I thought it might be interesting to give my account as an outsider encountering these arguments. Even if I don’t end up convincing people who have made AI alignment central to their careers and lives, maybe I’ll at least ... |
b0ed70fd-d440-4ba0-900b-4f0fdd0dbc6d | trentmkelly/LessWrong-43k | LessWrong | Who Organizes Dances?
Most contra dances are organized by a committee of volunteers: ~3 to ~8 people who divide up the work. This includes both advance work like coordinating with the venue, booking performers, and publicizing the dance, and also day-of work like setup, cleanup, and handling things that come up at the... |
470878be-a0d4-49d2-9332-14059fe08d85 | trentmkelly/LessWrong-43k | LessWrong | Doing Sport Reliably via Dancing
For me, sport is important because it has a reliable anti-depressant effect. I also have more energy throughout the day. I also heard it helps with memory formation when done a couple of hours after learning.
I find dancing very fun. That makes it easy to start. It's also a good worko... |
39698872-6bae-48a7-8ab4-c02c0954ccbf | trentmkelly/LessWrong-43k | LessWrong | Flowsheet Logic and Notecard Logic
(Disclaimer: The following perspectives are based in my experience with policy debate which is fifteen years out of date. The meta-level point should stand regardless.)
If you are not familiar with U.S. high school debate club ("policy debate" or "cross-examination debate"), here is... |
bf121dfa-3412-49c9-9436-7a11f856cf49 | trentmkelly/LessWrong-43k | LessWrong | Self-improvement without self-modification
This is just a short note to point out that AIs can self-improve without having to self-modify. So locking down an agent from self-modification is not an effective safety measure.
How could AIs do that? The easiest and the most trivial is to create a subagent, and transfer t... |
1e186d2e-8df4-4748-9d44-98c1e634c9ab | trentmkelly/LessWrong-43k | LessWrong | What is operations?
This the first in a sequence of posts about “operations”.
Acknowledgements to Malo Bourgon, Ray Arnold, Michelle Hutchinson, and Ruby for their feedback on this post.
My ops background
Several years ago, I decided to focus on operations work for my career. From 2017 to 2019 I was one of the oper... |
280dd5e5-c199-49d9-9f2e-e18bb7195c4d | trentmkelly/LessWrong-43k | LessWrong | On the nature of purpose
[cross-posted from my blog]
Introduction
Is the concept of purposes, and more generally teleological accounts of behaviour, to be banished from the field of biology?
For many years - essentially since the idea of Darwinian natural selection has started to be properly understood and in... |
84ced080-716d-41b8-a430-a4e2a4cd2548 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Melbourne Practical Rationality
Discussion article for the meetup : Melbourne Practical Rationality
WHEN: 03 January 2014 06:30:00PM (+1100)
WHERE: Level 2, 491 King St West Melbourne 3003
Practical Rationality. This meetup repeats on the first Friday of each month and is distinct from our monthly Social M... |
74a28675-a66c-466c-8325-c6bb13540064 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Thursday Meetup at UB
Discussion article for the meetup : Thursday Meetup at UB
WHEN: 21 March 2013 07:00:00PM (-0400)
WHERE: University at Buffalo-North Campus, Rm 124 Capen Hall Buffalo,NY
So I recently read Jackdaws' "The Eighth Meditation on Superweapons and Bingo" and I think it would be a great discu... |
a46400b9-8546-4e89-b9c4-111aee607801 | trentmkelly/LessWrong-43k | LessWrong | NIST: draft plan for AI standards development
The National Institute of Standards and Technology, a part of the United States Department of Commerce, has released a draft plan for public comment. It was released July 02; comments are accepted until July 19; the final plan is due August 10. It is 36 pages long, includi... |
fb84a6a0-03ba-41ec-a9e3-bfa7f336100b | trentmkelly/LessWrong-43k | LessWrong | FAI-relevant XKCD
http://xkcd.com/962/
|
c0c9cc8b-514f-489c-8c0f-7e3e59d3e495 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Zombies! Zombies?
Today's post, Zombies! Zombies? was originally published on 04 April 2008. A summary (taken from the LW wiki):
> Don't try to put your consciousness or your personal identity outside physics. Whatever makes you say "I think therefore I am", causes your lips to move; it is within the c... |
6a158d23-6721-4afb-ac8a-031867e7f92d | trentmkelly/LessWrong-43k | LessWrong | A case for AI alignment being difficult
This is an attempt to distill a model of AGI alignment that I have gained primarily from thinkers such as Eliezer Yudkowsky (and to a lesser extent Paul Christiano), but explained in my own terms rather than attempting to hew close to these thinkers. I think I would be pretty go... |
96e038e7-aba5-4c85-9d49-3ab74685856b | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Secure homes for digital people
Being a “[digital person](https://www.cold-takes.com/imagining-yourself-as-a-digital-person-two-sketches/)” could be scary—if I don’t have control over the hardware I’m running on, then someone else could get my code and run tons of copies in horrible conditions. (See also: qntm’s [Lena... |
d7fc0db1-113e-4673-84a1-1b48cba958e3 | trentmkelly/LessWrong-43k | LessWrong | A Bunch of Matryoshka SAEs
This work was done as part of MATS 7.0.
MATS provides a generous compute stipend, and towards the end of the program we found we had some unspent compute. To let this not go to waste, we trained batch topk Matryoshka SAEs on all residual stream layers of Gemma-2-2b, Gemma-2-9b, and Gemma-3-... |
b2a8d888-1609-4054-b194-5ff6fc637ba7 | trentmkelly/LessWrong-43k | LessWrong | What Are Your Preferences Regarding The FLI Letter?
There's a big issue and it doesn't seem to having very much voting happening around it, and it has less really high quality voting, which might be sad, given the importance and stakes and so on?
I think governance innovations that are inclusive of digital people wil... |
ea780dc5-2015-42d4-9e72-bf2fc4d05f95 | trentmkelly/LessWrong-43k | LessWrong | Savulescu: "Genetically enhance humanity or face extinction"
In this video, Julian Savulescu from the Uehiro centre for Practical Ethics argues that human beings are "Unfit for the future" - that radical technological advance, liberal democracy and human nature will combine to make the 21st century the century of glob... |
96132674-4640-46ce-839a-d86380746714 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Training goals for large language models
*This post was written under Evan Hubinger’s mentorship, as part of the*[*Stanford Existential Risks Initiative ML Alignment Theory Scholars (SERI MATS) program*](https://www.lesswrong.com/posts/8vLvpxzpc6ntfBWNo/seri-ml-alignment-theory-scholars-program-2022)*. Many of the ide... |
5128847a-30df-466c-956b-839406a2496b | trentmkelly/LessWrong-43k | LessWrong | Open & Welcome Thread - September 2019
* If it’s worth saying, but not worth its own post, here's a place to put it.
* You can also make a shortform post.
* And, if you are new to LessWrong, here's the place to introduce yourself.
* Personal stories, anecdotes, or just general comments on how you found us a... |
f59eecfa-3b47-4a45-8308-359f03ce50dc | trentmkelly/LessWrong-43k | LessWrong | Inverse Problems In Everyday Life
There’s a class of problems broadly known as inverse problems. Wikipedia explains them as follows:
An inverse problem in science is the process of calculating from a set of observations the causal factors that produced them. [...] It is called an inverse problem because it starts wit... |
403f3d59-cb3a-4059-9b90-9396ae4263c8 | trentmkelly/LessWrong-43k | LessWrong | Preserving our heritage: Building a movement and a knowledge ark for current and future generations
Note: This post is written with partial assistances from ChatGPT. Furthermore, this post is explicitly released under public domain.
TL;DR version: An essay highlighting the needs to build or energize a movement to sup... |
ef725518-8469-4582-afe3-cd86f5746338 | trentmkelly/LessWrong-43k | LessWrong | Morality as Cooperation Part III: Failure Modes
This is a Part III of a long essay. Part I introduced the concept of morality-as-cooperation (MAC) in human societies. Part II discussed moral reasoning and introduced a framework for moral experimentation.
Part III: Failure modes
Part I described how human morality ha... |
1e1ef37d-8e8d-406d-b360-fa962e32ccb4 | trentmkelly/LessWrong-43k | LessWrong | What is known about invariants in self-modifying systems?
I have been trying to find out what is known about invariants in self-modifying systems. This might become a rather acute topic if we end up moving towards self-modifying AIs or self-modifying ecosystems of AIs.
But it seems that not much has been done. For ex... |
6fe12684-1f6c-41ea-b979-358107d0cf9c | trentmkelly/LessWrong-43k | LessWrong | Truth is Symmetric
The Taj Mahal is symmetric with respect to right-left reflection. That is to say, if you create a mirror image of it that flips right and left, you get the exact same thing. Therefore, if as we're standing outside looking at it my friend Jen tells me that she thinks the left side of the Taj Mahal is... |
fd975b30-11c4-4b72-9d3e-a82046315f9c | StampyAI/alignment-research-dataset/arbital | Arbital | Reflective consistency
A decision system is "reflectively consistent" if it can approve the construction of similar decision systems. For example, if you have an expected utility satisficer (it either takes the null action, or an action with expected utility greater than $\theta$) then this agent can self-modify to a... |
8dfda30c-8419-4c24-a6ea-c3ca75334add | trentmkelly/LessWrong-43k | LessWrong | Unregulated Peptides: Does BPC-157 hold its promises?
Empiric status: I studied bioinformatics, but I'm not working in the field. I researched the article over a few months.
After reading about peptides and BPC-157 potential effects on wound healing, I decided to research BPC-157 and write this article to summarize... |
eaaf3f30-a95d-47a1-93cc-4f9a1ca0053a | StampyAI/alignment-research-dataset/arxiv | Arxiv | Machine Explanations and Human Understanding
1. introduction
----------------
Although recent advances in deep learning have led to machine learning (ML) models with impressive performance (He
et al., [2015](#bib.bib27); Mnih
et al., [2015](#bib.bib43); Silver
et al., [2017](#bib.bib54)), there are growing concerns... |
1637fa17-67b8-4d55-9c9e-81559067c523 | trentmkelly/LessWrong-43k | LessWrong | States of knowledge as quantum configurations
I'm in the middle of reading the <a http://lesswrong.com/lw/r5/the_quantum_physics_sequence/> sequence on quantum mechanics </a>. |
77518cdf-fae5-452b-aefd-3c37014c45b2 | trentmkelly/LessWrong-43k | LessWrong | Torture vs. Shampoo
I was reading the original comment thread on Torture vs. Dust Specks, and notice Eliezer saying he wouldn't pay a penny to avoid a single dust speck - which confused me, until I noticed that the original specification of the problem says the dust speck "floated into your eye and irritated it just a... |
a24aefbc-790d-49d7-8098-2430e738aa18 | trentmkelly/LessWrong-43k | LessWrong | Friendly, but Dumb: Why formal Friendliness proofs may not be as safe as they appear
While pondering the AI box problem, I tend to mentally "play" both sides, checking if there are any arguments that could convince me to let an AI out. Several I was nearly convinced by, but others have pointed out the flaws with these... |
a58435e5-62a4-4167-bc2e-615fa1b31832 | trentmkelly/LessWrong-43k | LessWrong | Depression as a defense mechanism against slavery
Individuals who have to conform to an external authority too powerful to resist often get depressed: which among other effects, includes lower productivity and higher risk for suicide. This suggests one way how a tendency for depression, and resulting behaviors of akr... |
c4a83b66-28ae-4833-83c5-4bc747536253 | trentmkelly/LessWrong-43k | LessWrong | Health Inflation, Wealth Inflation, and the Discounting of Human Life
Abstract:
> This Article presents two new arguments against “discounting” future human lives during cost-benefit analysis, arguing that even absent ethical objections to the disparate treatment of present and future humanity, the economic calcu... |
3ec2cef0-cdb1-4ccb-b5c7-c5d6ec5835db | trentmkelly/LessWrong-43k | LessWrong | Sunday, Nov 8: Tuning Your Cognitive Algorithms
For this Sunday's LW Online Meetup, I'll be will be leading an exercise on Mindful Puzzle Solving, derived from the Tuning Your Cognitive Algorithms exercise on bewelltuned.com.
The basic premise is to solve a medium-difficulty-puzzle, while spending a lot of attention... |
9b13b983-710c-4fa2-8929-6d64fc9238cb | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Singapore AI Policy Career Guide
*This career guide was also co-authored by Tan Zhi Xuan.*
*The original version of this career guide is on EA Singapore's website. I've removed large portions of it, so that it's better suited for the average EA forum audience. If you're based in Singapore, you might want to read the ... |
25db7f75-2cbc-4455-8e4a-5e2994c7032c | trentmkelly/LessWrong-43k | LessWrong | Sensation & Perception
(The below notes are pretty much my attempt to summarise the content in this sample chapter from this book. I am posting this in discussion because I don’t think I will get the time/be bothered enough to improve upon this, so I am posting it now and hope someone finds it interesting or useful. I... |
b4a24589-393b-4f75-ac0d-b97f7b19bf2b | trentmkelly/LessWrong-43k | LessWrong | Meetup : West LA Meetup 07-12-2011 - Bayes' Theorem
Discussion article for the meetup : West LA Meetup 07-12-2011 - Bayes' Theorem
WHEN: 12 July 2011 07:00:00PM (-0700)
WHERE: 10800 West Pico Blvd, Suite 312, Los Angeles, CA 90064
When: 7pm - 9pm July 12th.
Where: The Westside Pavillion - on the bridge, which conn... |
10310372-f048-46b3-b4c1-98c92fd58849 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | GPT-4 aligning with acasual decision theory when instructed to play games, but includes a CDT explanation that's incorrect if they differ
I did some tests with GPT-4 (through the [chat.openai.com](https://chat.openai.com) interface) to see what kind of decision theory it would employ. To prevent publication bias, I de... |
aeda0685-3ab3-4473-93d2-cf4bdbc99460 | trentmkelly/LessWrong-43k | LessWrong | Evaluating weather forecast accuracy: an interview with Eric Floehr
Eric Floehr has a business that "holds a mirror up" to weather forecasters, and aggregates and evaluates forecasters for weather forecast consumers. Rationalists interested in improving our societies truth orientation might be mildly interested.
http... |
126e774c-454d-4422-adf1-4e4a9a0a5878 | trentmkelly/LessWrong-43k | LessWrong | Optimizing optimizing LessWrong
Our optimization process sucks.
Every now and then someone makes up a thread concerning the optimization of LW, we have a nice discussion, one or the other idea gets a number of upvotes, sometimes quite a lot, but in the end, nothing happens.
What's more, it is predictable that nothin... |
2f921fb9-03cc-4936-bebc-2b3361dcd51f | trentmkelly/LessWrong-43k | LessWrong | AI Probability Trees - Joe Carlsmith (2022)
I am reviewing the work AI experts on what they think will happen with AI. This is a summary of Joe Carlsmith’s thoughts from his paper. AI risk scares me but often I feel pretty disconnected from it. This has helped me think about it.
Here are Carlsmith’s thoughts in brie... |
24dc9717-7ff6-42f8-b596-61b6bbcadf20 | trentmkelly/LessWrong-43k | LessWrong | Less Wrong Poetry Corner: Walter Raleigh's "The Lie"
Followup to: Rationalist Poetry Fans, Unite!, Act of Charity
This is my favorite poem about revealing information about deception! It goes like this (sources: Wikipedia, Poetry Foundation, Bartleby)—
> Go, Soul, the body's guest,
> Upon a thankless arrant:
> Fear ... |
fd20dfdb-9ff1-4d9b-b9e7-71b718e58d17 | trentmkelly/LessWrong-43k | LessWrong | [LINK] Relational models of Exchange
The title may make it seem like it's mind-killing stuff (politics, religion, etc) but in fact it's about the different way people relate to one another. A lot of the things discussed in the article get mentioned here as "cognitive biases" but in fact they are a fundamental part of ... |
27c83e97-b7cc-49f7-b0f2-8d5f372e92ea | trentmkelly/LessWrong-43k | LessWrong | The Parable of Predict-O-Matic
I've been thinking more about partial agency. I want to expand on some issues brought up in the comments to my previous post, and on other complications which I've been thinking about. But for now, a more informal parable. (Mainly because this is easier to write than my more technical th... |
b109277f-b7c4-469a-8cad-fc5a75d46993 | trentmkelly/LessWrong-43k | LessWrong | Decision Transformer Interpretability
TLDR: We analyse how a small Decision Transformer learns to simulate agents on a grid world task, providing evidence that it is possible to do circuit analysis on small models which simulate goal-directedness. We think Decision Transformers are worth exploring further and may prov... |
95274de8-b338-4a31-8f25-0e58b40bcc24 | trentmkelly/LessWrong-43k | LessWrong | Ask LW: Why no reproductive human cloning?
From what I can tell human cloning for the purpose of, ya know, actually cloning a person in the Dolly sense, is legal in many parts of the United States. It looks hard to pull off but without conceptual problems. Seems likely that after the first few clones are born there'll... |
452f2c86-6dad-4d88-8a94-42c55f28f29d | StampyAI/alignment-research-dataset/blogs | Blogs | 2015 FLOPS prices
In April 2015, the lowest GFLOPS prices we could find were approximately $3/GFLOPS. However recent records of hardware performance from 2015 and earlier imply substantially lower prices, suggesting that something confusing has happened with these sources of data. We have not resolved this.
Recent d... |
f5a63496-aec2-489e-a8c0-2dc6db7beabf | trentmkelly/LessWrong-43k | LessWrong | Wanting More Intellectual Stamina
As a sophomore undergraduate student, my most valuable rewards from the college experience have come from personal growth, rather than the classroom. However, one problem that I can't seem to shake is dealing with all the subcategories of my total personality.
On the one hand, I am h... |
7784cf52-6ca7-43fe-bf23-39955b2d7d2a | trentmkelly/LessWrong-43k | LessWrong | Gradient surfing: the hidden role of regularization
> Produced under the mentorship of Evan Hubinger as part of the SERI ML Alignment Theory Scholars Program - Winter 2022 Cohort
In a previous post, I demonstrated that Brownian motion near singularities defies our expectations from "regular" physics. Singularities t... |
87f72b86-925a-49d7-a0bc-135b4a4de357 | trentmkelly/LessWrong-43k | LessWrong | ChatGPT understands language
Cross-posting this from my blog, since it seems relevant.
The case for GPT understanding language, by way of understanding the world
There's a debate going on about whether or not language models similar to ChatGPT have the potential to be scaled up to something truly transformative. The... |
fa311925-6ae6-4026-85e2-b342d55a360d | trentmkelly/LessWrong-43k | LessWrong | Anatomy of a full school climate strike
If students decided to indefinitely strike (Mon-Fri) over climate inaction, what might it look like, and how might it play out? Here is my preliminary brainstorm:
Who would participate?
The most likely participants are aged 12-17. Below that age you are less independent-minded... |
c3589398-9f6a-4d12-82ec-111149aacd22 | trentmkelly/LessWrong-43k | LessWrong | Request for proposals: improving capability evaluations
Open Philanthropy is launching an RFP for work on AI capability evaluations. We're looking to fund three types of work:
1. Global Catastrophic Risk (GCR)-relevant capability benchmarks for AI agents
2. Research to improve our understanding of how capabilities ... |
74dc9b60-02de-429f-a34e-7ca57d7760a1 | trentmkelly/LessWrong-43k | LessWrong | Does quantum mechanics predict all the effects of relativity except gravity?
(My reading of physics books is progressing very slowly, so I'll be done in a year at best, so I'm asking this question here.) Does quantum mechanics describe the slowing down of time and the contraction of objects when approaching the speed ... |
53717c9b-e434-4c68-82f3-25c5f1db2e84 | trentmkelly/LessWrong-43k | LessWrong | Proposal for a Post-Labor Societal Structure to Mitigate ASI Risks: The 'Game Culture Civilization' (GCC) Model
Abstract: Accelerating AI development presents existential risks and necessitates examining future human societal structures in the context of mass automation. Current socio-economic systems, particularly ca... |
b78b25ac-9847-4530-95b6-e841516b810a | trentmkelly/LessWrong-43k | LessWrong | Explicit Optimization of Global Strategy (Fixing a Bug in UDT1)
When describing UDT1 solutions to various sample problems, I've often talked about UDT1 finding the function S* that would optimize its preferences over the world program P, and then return what S* would return, given its input. But in my original descrip... |
dbd85bf8-1dec-4969-a5e7-6d2eb6df2d4b | trentmkelly/LessWrong-43k | LessWrong | Violin Supports
Violins are a bit of a strange design. Classically you hold them up by pinching them between your chin and shoulder (restricting head motion), though in more casual contexts people sometimes use their left arm (restricting hand motion). Neither of these are great! Why can't the violin stay up on its ow... |
d5e78480-ecba-46ad-a537-806607d53eef | trentmkelly/LessWrong-43k | LessWrong | AI Training Should Allow Opt-Out
Last year, GitHub announced their Copilot system, an AI assistant for developers based on OpenAI's Codex model, as a free closed beta. Yesterday, they added that Copilot would now be available to everyone, but at a cost of $10 per month per user. Copilot is trained on all public GitHub... |
1926886a-922f-4868-9d9c-ccf49123df93 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Explorers in a virtual country: Navigating the knowledge landscape of large language models
**Summary**
-----------
In this post, I present a story that illustrates the interaction with large language models (LLMs) through prompts as 'exploring an unmapped virtual country.' This story aims to help people understand h... |
17edf46f-2dc0-49d3-926e-43ed7f6c39a6 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Learning the prior
Suppose that I have a dataset D of observed (*x*, *y*) pairs, and I’m interested in predicting the label *y*\* for each point *x*\* in some new set D\*. Perhaps D is a set of forecasts from the last few years, and D\* is a set of questions about the coming years that are important for planning.
The... |
bc3b87e1-a2a5-448f-a0f5-192d1867a6ac | trentmkelly/LessWrong-43k | LessWrong | Seeking Advice About Career Paths for Non-USA Citizen
Hi all,
Mostly lurker, I very rarely post, mostly just read the excellent posts here.
I'm a Filipino, which means I am a citizen of the Republic of the Philippines. My annual salary, before taxes, is about $20,000 (USA dollars). I work at an IC development com... |
3bced73f-1795-44c5-a666-e7b8a13db064 | trentmkelly/LessWrong-43k | LessWrong | Having Useful Conversations
Holding conversations in person is useful; feedback is quick, and it seems to be much easier to change your behavior as a result of actually talking with people.
Having effective goal-oriented conversations is somewhat difficult. One source of difficulty is a strong tendency to stray from... |
83934c13-b3c4-46b0-9331-ba9065564db2 | trentmkelly/LessWrong-43k | LessWrong | Mech Interp Project Advising Call: Memorisation in GPT-2 Small
I've recently been having advising calls with REMIX teams (Redwood's interpretability sprint) trying to give advice & feedback on projects. As an experiment, I've published a recording of one advising call (with Tessa Barton & Kushal Jain on memorisation i... |
5c135261-307f-450c-b552-7246abd26490 | trentmkelly/LessWrong-43k | LessWrong | Weekly LW Meetups: Brussels, Houston, Madison, Melbourne, Moscow, Philadelphia (2), Sydney
There are upcoming irregularly scheduled Less Wrong meetups in:
* Jazz meetup in Philadelphia: 10 February 2012 06:00PM
* First Brussels meetup: 11 February 2012 11:00AM
* Moscow 11 February meetup: 11 February 2012 06:00PM
... |
0ea94131-141e-48e1-b286-38f9c562a7b3 | trentmkelly/LessWrong-43k | LessWrong | Super-forecasters as a service
I've just started building a website yesterday that I think would be super interesting, but I'm not sure if it's legal or if Metaculus/Elicit would be fine with it.
The idea: Super-forecasters as a Service.
Say I wanted to know if I should book a flight to Costa Rica this summer, but... |
f85401a9-91bd-4924-90a4-a8920e12de0b | StampyAI/alignment-research-dataset/lesswrong | LessWrong | GPT learning from smarter texts?
(Epistemic status: I do not understand GPT deeply, so this is just a random idea.)
If I understand it correctly, GPT learns from existing texts. Lots of texts.
Would it be possible to make GPT smarter by simply giving it *smarter text*? Of course, writing tons of smarter text would b... |
771c59dd-e63e-4871-b2e1-bf8f1ba31b3d | trentmkelly/LessWrong-43k | LessWrong | Resurrection through simulation: questions of feasibility, desirability and some implications
Could a future superintelligence bring back the already dead? This discussion has come up a while back (and see the somewhat related); I'd like to resurrect the topic because ... it's potentially quite important.
Algorithmi... |
2b18fad3-71d3-448c-8e8b-7c08edc2f182 | trentmkelly/LessWrong-43k | LessWrong | Democracy beyond majoritarianism
The classical definition of democracy is “rule of majority with respect to the minority”. But the classics perfectly knew how oppressive can be the 51% of people over the rest and how difficult is to implement “respect”. I simply reject the majoritarian principle: democracy shall be ab... |
d65b2211-3afb-4409-bc81-eb45d67231fc | trentmkelly/LessWrong-43k | LessWrong | LIMA: Less Is More for Alignment
Abstract
> Large language models are trained in two stages: (1) unsupervised pretraining from raw text, to learn general-purpose representations, and (2) large scale instruction tuning and reinforcement learning, to better align to end tasks and user preferences. We measure the relativ... |
49e07674-c952-4dc2-b257-9307c137ef95 | trentmkelly/LessWrong-43k | LessWrong | GPT-4o is out
OpenAI just announced an improved LLM called GPT-4o.
From their website
> Today, GPT-4o is much better than any existing model at understanding and discussing the images you share. For example, you can now take a picture of a menu in a different language and talk to GPT-4o to translate it, learn about ... |
069f4f80-177f-42b9-b968-bd2fb263176f | trentmkelly/LessWrong-43k | LessWrong | Environments for killing AIs
4. Environments for killing AIs
Summary of entire Series: An alternative approach to designing Friendly Artificial Intelligence computer systems.
Summary of this Article: Killing a rogue AI may be impossible in our current environment, but we can change that by changing the environment... |
7db2ed64-e47d-43ae-b6a8-c4f0059b5fe5 | trentmkelly/LessWrong-43k | LessWrong | post-rational distractions
DonyChristie's intellectual fap post has called for post-rational techniques.
I got most of the way through a comment reply before I realised it was a joke. April fools and all.
Fruits of that effort here are some thoughts
***
Developing your centre's. Sarah Perry's are knitting and moun... |
25037c90-fa02-4dfb-bae4-30f050c90e06 | trentmkelly/LessWrong-43k | LessWrong | Expevolu, Part II: Buying land to create countries
This is the second of a series of three posts outlining the expevolu system; if you haven’t read the first one I’d recommend you start there:
Expevolu, a laissez-faire approach to country creation
PART II – Perpetual Auctions
Table of Contents:
1) The Problem
2) Th... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.