id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
3ec65a92-28fb-4cae-b9eb-2a41a69f7b53 | trentmkelly/LessWrong-43k | LessWrong | Formalizing the "AI x-risk is unlikely because it is ridiculous" argument
There is a lot of good writing on technical arguments against AI x-risk (such as Where I agree and disagree with Eliezer (which mostly argues for more uncertainty) and others). However, in the wider world the most popular argument is more of the... |
197ac674-c792-4b16-9b55-4bff8b9fb87e | trentmkelly/LessWrong-43k | LessWrong | Meetup : West LA Meetup 07-26-2011
Discussion article for the meetup : West LA Meetup 07-26-2011
WHEN: 26 July 2011 07:00:00PM (-0700)
WHERE: 10800 West Pico Blvd, Suite 312, Los Angeles, CA 90064
When: 7pm - 9pm July 26th.
Where: The Westside Pavillion - on the bridge, which connects Nordstrom 3rd floor with Barn... |
ce8c51c2-5f2b-468c-bf20-6e8d00a7a493 | StampyAI/alignment-research-dataset/arbital | Arbital | Oracle
Oracles are a subtype of [Genies](https://arbital.com/p/6w) putatively designed to safely answer questions, and *only* to answer questions. Oracles are often assumed to be [Boxed](https://arbital.com/p/6z) and the study of Oracles is sometimes taken to be synonymous with the study of Boxed Oracles. |
7c6bb259-a266-4a53-b492-37881b82d49a | trentmkelly/LessWrong-43k | LessWrong | Open Thread: January 2010
And happy new year to everyone. |
ea967075-af62-44c6-a05a-516cdbfca53d | trentmkelly/LessWrong-43k | LessWrong | The epistemic virtue of scope matching
I keep noticing a particular epistemic pitfall (not exactly a “fallacy”), and a corresponding epistemic virtue that avoids it. I want to call this out and give it a name, or find out what its name is, if it already has one.
The virtue is: identifying the correct scope for a phen... |
27ea695e-931c-4f4f-aa11-48782c446b99 | trentmkelly/LessWrong-43k | LessWrong | The Dunbar Playbook: A CRM system for your friends
Thanks to Dakota Quackenbush from Authentic Bay Area for an earlier version of this tool.
So far, the main motivation for my work as a community builder and authentic relating facilitator was meeting my own need for connection.
I think that was a mistake.
First, it... |
10af425b-8ecd-46cd-b066-7404f338d388 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Publication decisions for large language models, and their impacts
*This post is one part of the sequence* [*Understanding the diffusion of large language models*](https://forum.effectivealtruism.org/s/8rYkpiFhbb4HsbzFc)*. As context for this post, I strongly recommend reading at least the* [*5-minute summary*](https... |
114f4e3b-b5a3-4091-8127-e1febe581530 | trentmkelly/LessWrong-43k | LessWrong | Writing On The Pareto Frontier
I have a personal rule: don’t write something which someone else has already written better.
This is easier than it sounds. For instance, suppose I’m writing an intro to systems biology. I don’t need it to be the most comprehensive intro ever written, or the most accessible intro. I jus... |
c4385a9f-2460-492e-af4d-fed34bc0e37a | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Quantilizers and Generative Models
*Thanks to Evan Hubinger for discussions about quantilizers, and to James Lucassen for discussions about conditioned generative models. Many of these ideas are discussed in Jessica Taylor's* [Quantilizers: A Safer Alternative to Maximizers for Limited Optimization](https://intelligen... |
c54d9385-0e08-457e-9b8e-52e5a415318b | trentmkelly/LessWrong-43k | LessWrong | Mosh
I remember when mosh first came out and thinking "that sounds like a great idea, maybe I'll set it up sometime" and then never getting around to it. Several times over the years I've thought similarly, but it never seemed worth it. A week ago a coworker asked if there were good tools for handling remote terminal ... |
a81b04fd-b594-4013-874e-a340dc780f62 | StampyAI/alignment-research-dataset/arbital | Arbital | Concept
Add this tag to pages which represent a concept. A concept page doesn't have an explanation, it merely describes what the concept is. Take a look at the text that comes before the table of contents on any Wikipedia page to see what a good example of a concept page might contain. Concepts are also expected to b... |
95b88bf8-8cb9-46cc-979e-48b0fbe9ae1e | StampyAI/alignment-research-dataset/arxiv | Arxiv | BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
1 Introduction
---------------
![Approaches to backdooring a neural network. On the left, a clean network correctly classifies its input. An attacker could ideally use a separate network (center) to recognize the backdoor trigger, but is... |
f3a4fad1-cc3e-4766-92ab-4a2d8ccfd83d | trentmkelly/LessWrong-43k | LessWrong | You don't need Kant
Related to: Comments on Degrees of Radical Honesty, OB: Belief in Belief, Cached Thoughts.
> "Nothing worse could happen to these labours than that anyone should make the unexpected discovery that there neither is, nor can be, any a priori knowledge at all.... This would be the same thing as if on... |
7db19d5b-cdd0-4b7d-a256-c6110e14e4c8 | trentmkelly/LessWrong-43k | LessWrong | The Control Problem: Unsolved or Unsolvable?
td;lr
No control method exists to safely contain the global feedback effects of self-sufficient learning machinery. What if this control problem turns out to be an unsolvable problem?
Where are we two decades into resolving to solve a seemingly impossible problem?
If... |
946aa378-6a38-4b4a-8662-d60bfe8b33d7 | trentmkelly/LessWrong-43k | LessWrong | A thought on gym membership models and from there the whole world…
I read somewhere that gyms are designed to maximize members and minimize users. This makes sense when one thinks about it. Members pay money, whether they use the gym services or not. Users require equipment and employees to manage the equipment. Users... |
6f208de8-b134-4bcc-b525-cc4bfe822703 | trentmkelly/LessWrong-43k | LessWrong | Learn A New Language!
The following protocol is very dumb, and relies on a lot of mental brute force, but I find that it works very well indeed.
First, learn the alphabet. the most basic survival phrases, the phonetics, the basic grammar. This may be the steepest part of the learning curve. I recommend that you get a... |
b86f9f4c-2a34-442f-9bcb-0bc5cc787831 | trentmkelly/LessWrong-43k | LessWrong | [Link/crosspost] [US] NTIA: AI Accountability Policy Request for Comment
> The Department of Commerce’s National Telecommunications and Information Administration (NTIA)[1] has launched an inquiry into what policies will help businesses, government, and the public be able to trust that Artificial Intelligence (AI) sys... |
6d4cda30-ad05-4293-bae3-7d1f28666e60 | trentmkelly/LessWrong-43k | LessWrong | Shapes of Mind and Pluralism in Alignment
This post is part of the work done at Conjecture.
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.
I have recently presented my model behind the ... |
90030ef4-c370-402b-9c29-80277751f254 | StampyAI/alignment-research-dataset/special_docs | Other | Human-aligned artificial intelligence is a multiobjective problem
Introduction Recent years have seen dramatic improvements in the capabilities of artificial intelligence (AI) systems, with AI agents demonstrating human or even superhuman levels of performance across a variety of tasks (Ferrucci 2012; Mnih et al. 2015... |
76a29655-ff14-4f24-933e-e665fd20679f | trentmkelly/LessWrong-43k | LessWrong | Peter Thiel/Eric Weinstein Transcript on Growth, Violence, and Stories
I’ve recently been through a spate of listening to podcasts. When I listened to the first ninety minutes of a three-hour conversation between Eric Weinstein and Peter Thiel, I was surprised to hear echoed a lot of ideas we've discussed on LessWrong... |
61ce48b9-e654-4e77-8cff-ec77f2ed88cb | trentmkelly/LessWrong-43k | LessWrong | When do you start looking for a Boston apartment?
A huge fraction of Boston-area apartments are on a September 1st to September 1st lease cycle. This is driven by college student rentals, but the whole city has ended up on the same pattern. So you might expect to see the most apartment listings in August or maybe July... |
dca5ae0f-dd0b-451d-bbac-7ee78a984a14 | trentmkelly/LessWrong-43k | LessWrong | Measuring up to incredible potential
Yesterday I wrote that people often talk as if events are basically determined by people’s values and capabilities, ignoring the difficulty of figuring out which opportunities to take, or even noticing opportunities.
I think one reason to have a better model is that this one doesn... |
87300be9-538c-467d-85d0-4525b49c69f7 | trentmkelly/LessWrong-43k | LessWrong | A single principle related to many Alignment subproblems?
I want to show a philosophical principle which, I believe, has implications for many alignment subproblems. If the principle is valid, it might allow to
* connect the study of abstractions, Shard Theory and Mechanistic Anomaly Detection;
* obtain multiple po... |
c44f88bc-0c2a-4a7b-844d-301942cfc16d | trentmkelly/LessWrong-43k | LessWrong | Chapter 101: Precautionary Measures, Pt 2
Harry stood, panting, in the midst of a brief wasted circle amid the forest, more destruction than a first-year should have been able to reach, by himself. The Severing Charm wouldn't bring down a tree, so he'd started partially Transfiguring cross-sections through the wood. I... |
5d4922cd-b1eb-47fa-8b1b-1a54751b59c9 | trentmkelly/LessWrong-43k | LessWrong | Your Enemies Can Use Your Prediction Markets Against You
It is the year 2525. Earth and Mars are in a state of cold war against each other. Both planets import uranium from Ceres. Ceres' government is pro-Earth…for now. Earth needs to know how likely it is the Ceres government will be overthrown and replaced by a pro-... |
331791b5-92af-4cac-8214-06fc4c7bee48 | trentmkelly/LessWrong-43k | LessWrong | Models of preferences in distant situations
Note: working on a research agenda, hence the large amount of small individual posts, to have things to link to in the main documents.
For X, consider three different partial preferences:
1. If X were poor, they would prioritise consumption over saving.
2. X: If I were p... |
4da7b257-a4a7-4ea3-844b-7568589930ae | trentmkelly/LessWrong-43k | LessWrong | The Purpose of Purpose
1. I often make reference to the category I call variously purpose, care, concern, meaning, norms, or telos (I'll just use "purpose" from here on out to point to it).
1. I've not really explained what I mean by it in great detail.
2. That's a problem because it's the ground of reasoning... |
801bdb8a-1dfb-4b54-888a-b198cbb87f05 | trentmkelly/LessWrong-43k | LessWrong | Is backwards causation necessarily absurd?
In Newcomb's problem an agent picks either one-box or two-box and finds that no matter which option they picked, a predictor predicted them in advance. I've gone to a lot of effort to explain how this can be without requiring backwards causation (The Prediction Problem, Decon... |
3bae3efe-85fb-4be7-b0c7-176b29d24ebd | trentmkelly/LessWrong-43k | LessWrong | Self-Experiment: Does Working More Hours Increase My Output?
This piece is cross-posted on my blog here.
After writing up my research on limits to working, the sheer spread of possibilities amazed me. I genuinely wasn’t sure if I would be able to tell the difference between a day with four hours of deep work and one ... |
bb15e1e9-aba4-4877-a960-9c10c2767227 | trentmkelly/LessWrong-43k | LessWrong | The Mask Comes Off: At What Price?
The Information reports that OpenAI is close to finalizing its transformation to an ordinary Public Benefit B-Corporation. OpenAI has tossed its cap over the wall on this, giving its investors the right to demand refunds with interest if they don’t finish the transition in two years.... |
6a3b05d7-37aa-4747-8464-06dd874fc352 | StampyAI/alignment-research-dataset/blogs | Blogs | AI Safety Seems Hard to Measure
*Click lower right to download or find on Apple Podcasts, Spotify, Stitcher, etc.*
In previous pieces, I argued that there's a real and large risk of AI systems' [developing dangerous goals of their own](https://www.cold-takes.com/why-would-ai-aim-to-defeat-humanity/) and [defeatin... |
d5db790e-4259-4a8b-86b1-adb0f924e9ef | StampyAI/alignment-research-dataset/arxiv | Arxiv | Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising
1. Introduction
----------------
Figure 1. There are five conversion steps with sequential dependence from left to right, and five diff... |
4d999710-1963-4415-8d9e-010a1a53b416 | trentmkelly/LessWrong-43k | LessWrong | Approval-directed bootstrapping
Approval-directed behavior works best when the overseer is very smart. Where can we find a smart overseer?
One approach is bootstrapping. By thinking for a long time, a weak agent can oversee an agent (slightly) smarter than itself. Now we have a slightly smarter agent, who can oversee... |
a647e4c9-b1cc-4193-ad3a-6d4468c8b1c0 | trentmkelly/LessWrong-43k | LessWrong | What are the chances that Superhuman Agents are already being tested on the internet?
I keep seeing odd bits of information from the grapevine about how Superintelligent Agents are on the horizon, with the latest being this Axios article. While I’m still unsure what to think, I started considering the possibility that... |
0ee873a0-67ca-4eec-860e-daa2fc630311 | trentmkelly/LessWrong-43k | LessWrong | Towards deconfusing values
NB: Kaj recently said some similar and related things while I was on hiatus from finishing this post. I recommend reading it for a different take on what I view as a line of thinking generated by similar insights.
One of the challenges with developing a theory of human values is dealing wit... |
e90cf5ab-87e2-4cc1-b588-261567371e91 | trentmkelly/LessWrong-43k | LessWrong | A paradox of existence
Introduction
There is a question in philosophy "why is there something rather than nothing?" I have always thought of this question as completely impossible to answer: either it is a meaningless question, or at least there seems to be no way that we can ever begin to answer it. Yet it has always... |
b8a952c8-fc9f-4817-875d-f28545a20110 | trentmkelly/LessWrong-43k | LessWrong | Rationality is Not an Attractive Tribe
Summary: I wonder how attractive rationality as a tribe and worldview is to the average person, when the competition is not constrained by verifiability or consistency and is therefore able optimize around offering imaginary status superstimuli to its adherents.
> Anti-intell... |
a401975e-a623-416f-b1f9-c2d8a6622823 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Ethan Perez on the Inverse Scaling Prize, Language Feedback and Red Teaming
I talked to [Ethan Perez](https://www.lesswrong.com/users/ethan-perez) about the [Inverse Scaling Prize](https://www.lesswrong.com/posts/eqxqgFxymP8hXDTt5/announcing-the-inverse-scaling-prize-usd250k-prize-pool) (deadline August 27!), [Traini... |
819c9824-1aa3-424d-a24f-e7bbd53032a1 | trentmkelly/LessWrong-43k | LessWrong | Monthly Roundup #7: June 2023
This month’s roundup of non-AI things, with the good, the bad and the uncondoned, along with several additional individual topics. I’m also trying out running some blog-focused surveys near the end, right before the jokes.
BAD NEWS
RIP Doyle Brunson.
Alabama head baseball coach at cent... |
a8c98fd8-d0f4-4ede-b544-5500628e657e | StampyAI/alignment-research-dataset/lesswrong | LessWrong | If you lose enough Good Heart Tokens, will you lose real-world money?
*Please note that the following is satirical, just in case you somehow couldn’t tell.*
With the new Good Hearts system replacing Karma, it appears that those who receive a sufficient number of upvotes will gain actual, physical, real-world money. ... |
fe7207d6-1d77-4f55-8e1a-451aa73c49c3 | trentmkelly/LessWrong-43k | LessWrong | An animated introduction to longtermism (feat. Robert Miles)
EA Forum cross-post
This article is the script of the YT video linked above. It is an animated introduction to the idea of longtermism. The video also briefly covers "The Case for Strong Longtermism" by William MacAskill and then goes over Nick Bostrom's "A... |
099fc8ae-c69a-4526-beba-a832088b2e36 | trentmkelly/LessWrong-43k | LessWrong | Rationalist Scriptures?
I understand that the title sounds like an oxymoron, however, we it seems like we do have scriptures. The Codex, HPMOR, Rationality A-Z, etc are basically required reading so that we can have a community with a fixed starting point, however they don't seem to be well compiled.
HPMOR is a comp... |
15c73326-6847-4bc0-b0f6-644742308480 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Optimization Concepts in the Game of Life
**Abstract:** We define robustness and retargetability (two of Flint’s measures of optimization) in Conway’s Game of Life and apply the definitions to a few examples. The same approach likely works in most embedded settings, and provides a frame for conceptualizing and quantif... |
7fd46bae-0645-43d9-a89d-b9790fb31d86 | trentmkelly/LessWrong-43k | LessWrong | A broad basin of attraction around human values?
Followup to: Morality is Scary, AI design as opportunity and obligation to address human safety problems
In Corrigibility, Paul Christiano argued that in contrast with ambitious value learning, an act-based corrigible agent is safer because there is a broad basin of at... |
427eaf9f-dc3f-4fba-98ec-f1bd3c44ad67 | trentmkelly/LessWrong-43k | LessWrong | Announcing Dialogues
As of today, everyone is able to create a new type of content on LessWrong: Dialogues.
In contrast with posts, which are for monologues, and comment sections, which are spaces for everyone to talk to everyone, a dialogue is a space for a few invited people to speak with each other.
I'm personal... |
e522f767-6ed5-418b-b8a4-82fd6f81dba2 | trentmkelly/LessWrong-43k | LessWrong | Not all signalling/status behaviors are bad
As I've recently been understanding signalling/status behaviors common among humans and how they can cloud reality, I've had a tendency to automatically think of these behaviors as necessarily bad. But it seems to me that signalling behaviors are pretty much a lot of what we... |
1d987962-c068-417d-a6e3-cc6618c725cd | trentmkelly/LessWrong-43k | LessWrong | Beyond Rewards and Values: A Non-dualistic Approach to Universal Intelligence
(This is my first post on Lesswrong, including some thoughts on topics I have read in this year. Please leave your comment on them. Thanks.)
Abstract
Building an AI system that aligns with human values is believed to be a two-step proce... |
f3176e3f-3e46-48fd-a19e-8f8159ab9852 | trentmkelly/LessWrong-43k | LessWrong | Escaping the Löbian Obstacle
Earlier this year, when looking for an inroad to AI safety, I learned about the Löbian Obstacle, which is a problem encountered by 'purely logical' agents when trying to reason about and trust one another. In the original paper of Yudkowsky and Herreshoff [1], they show that a consequence ... |
44593381-0112-4ef8-9012-00860314f70d | trentmkelly/LessWrong-43k | LessWrong | China Covid #4
China has now decided to let Covid take its course, so it makes sense to spin developments there off into their own posts for a bit. It is hard to get a good read on what is happening, because China’s core strategy was to stop controlling the spread of Covid and instead to put tight controls on its Covi... |
be6f25d2-3ea0-409a-b237-ce5d8d3caf91 | trentmkelly/LessWrong-43k | LessWrong | Open Thread, March. 6 - March 12, 2017
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 the list-of-threads page before posting.)
3. Open Threads should start on Monday, and end on Sunday.
4. Unflag ... |
5133297d-c7f0-487f-a4d3-7af657f7c653 | trentmkelly/LessWrong-43k | LessWrong | Extra Tall Crib
A few days ago I came upstairs to:
> Me: how did you get in there?
> Nora: all by myself!
Either we needed to be done with the crib, which had a good chance of much less sleeping at naptime, or we needed a taller crib. This is also something we went through when Lily was little, and that time ... |
e3548f40-ec7a-49b8-937d-7eb0fc1fed08 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | On value in humans, other animals, and AI
*This will be posted also on the EA Forum, and included in a sequence containing some previous posts and other posts I'll publish this year.*
Introduction
============
Humans think critically about values and, to a certain extent, they also act according to their values. To ... |
7f517bf6-5c32-4845-999c-5f668b4bb8e2 | trentmkelly/LessWrong-43k | LessWrong | Combatting perfectionism
Background
Over the past 2 months, I've experienced two of my startups ending - one in euthanasia and one in sale.
During my startup that we ended, I kept my perfectionism under control by the time pressure of building for our customers. I would ask customers what they wanted; consider what t... |
b921aa6f-b204-4c1f-8eb7-4b0a58b48613 | trentmkelly/LessWrong-43k | LessWrong | What makes a probability question "well-defined"? (Part II: Bertrand's Paradox)
See also: What makes a probability question "well-defined"? (Part I), Bertrand's Paradox, More on Bertrand's Paradox, and When (Not) To Use Probabilities
(Follow-up to my last post and cross-posted from my new(ish) blog. Sorry for the ver... |
706df106-36c9-47e7-82e9-c540fa96efe4 | StampyAI/alignment-research-dataset/arbital | Arbital | Posterior probability
"Posterior [probability](https://arbital.com/p/1rf)" or "posterior [odds](https://arbital.com/p/1rb)" refers our state of belief *after* seeing a piece of new evidence and doing a [Bayesian update](https://arbital.com/p/1ly). Suppose there are two suspects in a murder, Colonel Mustard and Miss S... |
95970ee4-0e81-4f03-9fdf-06d3316abea4 | trentmkelly/LessWrong-43k | LessWrong | Laurie Anderson talks
Not rationalist per-se, and much more abstract than legible (it is part of a Poetry lecture series), but Laurie Anderson has long been one of my favorite artists, and this is likely of interest (or of enjoyment or some positive experience) to many people here. 10 minutes into the first lecture, ... |
84049732-edd7-4dee-9141-1f23fe97be49 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Alignment Newsletter #19
**Highlights**
**[OpenAI Five Benchmark: Results](https://blog.openai.com/openai-five-benchmark-results/)** *(OpenAI's Dota Team)*: The OpenAI Five benchmark happened last Sunday, where OpenAI Five won two matches against the human team, and lost the last one when their draft was adversariall... |
81e3939b-7cef-481f-bd13-76d0a59ce0ff | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Logical Probability of Goldbach’s Conjecture: Provable Rule or Coincidence?
*Epistemic status: some thoughts about a complex problem*
TL;DR: Goldbach conjecture – that any even number could be presented as a sum of two primes – is more likely to be a random coincidence than a provable rule, because for large numbers ... |
428a74c5-f264-4195-9fd3-1c5565ef490e | StampyAI/alignment-research-dataset/lesswrong | LessWrong | The Fixed Sum Fallacy
(**Update:** Patrick points out the subject of this post is already well-known as the [gambler's fallacy](http://en.wikipedia.org/wiki/Gambler's_fallacy). I really should have read Tversky and Kahneman before posting.)
You're flipping a coin 100 times, the first five throws came up heads, what ... |
82b88f0d-f06f-4fb3-8049-9e8a08f3d241 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Southern Arizona meetup
Discussion article for the meetup : Southern Arizona meetup
WHEN: 05 July 2011 06:00:00PM (-0700)
WHERE: Coffee X Change 2443 North Campbell Avenue, Tucson, AZ 85719
I've decided to try and put together a stronger rationalist community here in Arizona; I know there have already been... |
478a6b16-c101-4250-94c8-8abf520f893e | StampyAI/alignment-research-dataset/arxiv | Arxiv | A Constructive Prediction of the Generalization Error Across Scales
Published as a conference paper at ICLR 2020
A C ONSTRUCTIVE PREDICTION OF THE
GENERALIZATION ERROR ACROSS SCALES
Jonathan S. Rosenfeld1Amir Rosenfeld2Yonatan Belinkov13Nir Shavit145
fjonsr,belinkov,shanir g@csail.mit.edu amir@cse.yorku.ca
1Massachuse... |
b1edc8ca-a884-4147-9f03-29fe7947aaa0 | trentmkelly/LessWrong-43k | LessWrong | The lesswrong slack - an introduction to our regulars
About us
The lesswrong slack has been active for 2-3 years now. It’s a garden in as much as I try to keep it peaceful.
A new member joined the slack recently. He asked: What are the moderation rules here?
I wrote the brief rules, but then I also was feeling parti... |
8c601727-e7ef-4d81-bc67-814ad5795ef8 | trentmkelly/LessWrong-43k | LessWrong | Why Productivity? Why Gratitude?
I recently did a series of online seminars where productivity guru Jason Womack tried to apply his advice for academics.
The productivity advice was good but not especially new after having read a lot of anti-akrasia posts on LW; EverydayUtilitarian recently wrote a great summary of t... |
f6790de9-6c85-4d02-9662-b4c08b19e8e5 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Generative Exploration and Exploitation
Introduction
------------
Deep reinforcement learning (RL) has achieved great success in many sequential decision-making problems, such as Atari games [[16](#bib.bib1 "Human-level control through deep reinforcement learning")], Go [[25](#bib.bib2 "Mastering the game of go wit... |
991306da-13ab-45a6-a6cc-44c35a9d447b | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Expanding the domain of discourse reveals structure already there but hidden
*[Metadata: crossposted from <https://tsvibt.blogspot.com/2022/05/expanding-domain-of-discourse-reveals.html>. First completed May 15, 2022. This essay is more like research notes than exposition, so context may be missing, the use of terms m... |
65b197d3-a874-4701-9072-d2e810befee0 | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | What is Encultured working on?
See [Encultured AI: Building a Video Game](https://www.alignmentforum.org/posts/ALkH4o53ofm862vxc/announcing-encultured-ai-building-a-video-game).
Encultured is making a multiplayer online video game as a test environment for AI: an aligned AI should be able to play the game without rui... |
7d8c80c9-e38b-406f-a0f0-23cf3c609c7a | trentmkelly/LessWrong-43k | LessWrong | Marvel Snap: Phase 2
[NOTE: This is a pure gaming post, if you’re not into that please do skip it.]
Previously: Marvel Snap Review: Phase 1
At the end of my Phase 1 review, I removed Marvel Snap from my phone.
I am very happy with that decision.
I did then continue to play the game on my computer, via Steam.
I am... |
f290c097-64e9-4b9a-be26-a375585ae3aa | trentmkelly/LessWrong-43k | LessWrong | Why don't we have self driving cars yet?
1) Is it because of regulations?
2) Is it because robustness in the real world (or just robustness in general) turns out to be very hard for current AI systems, and robustness is much more important for self driving cars than other areas where we have seen more rapid AI progre... |
c91c6ccb-fb7c-4183-a866-ba01eaff5b2d | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Lonely Dissent
Today's post, Lonely Dissent was originally published on 28 December 2007. A summary (taken from the LW wiki):
> Joining a revolution does take courage, but it is something that humans can reliably do. It is comparatively more difficult to risk death. But is is more difficult than either... |
b188f9bd-36d3-4a8e-89e3-3ad40f7634e5 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Agentic GPT simulations: a risk and an opportunity
*Epistemic status: highly speculative, I would love it if someone could flesh out these ideas more.*
I think it's fair to characterise GPT as an adaptation executor rather than a fitness maximizer. It doesn't appear to be intrinsically agentic or to plan anything to ... |
cb994625-5925-47be-a25f-cd622ef1880c | trentmkelly/LessWrong-43k | LessWrong | Sexual self-acceptance
I have noticed very often that I can't predict how my brain reacts towards women. I often expect that nothing special will happen, compared to talking to males. However very often sexual thoughts come to mind that seems out of place to me. Normally they are very short (1-5s) and visual, but with... |
6e493171-be96-42a4-b352-66f905514106 | StampyAI/alignment-research-dataset/special_docs | Other | Pervasive Spurious Normativity
Pervasive Spurious Normativity
Gillian K. Hadfield Dylan Hadfield-Menell
Abstract
This paper proposes a mathematical model for a simplified version of the game defined in Hadfield
and Weingast [2012] which proposes that legal order can be described as an equilibrium in third-
party decentrali... |
40b232c0-e6b2-4f2f-9f94-6cc77f1959df | trentmkelly/LessWrong-43k | LessWrong | Scaling laws for dominant assurance contracts
(note: this post is high in economics math, probably of narrow interest)
Dominant assurance contracts are a mechanism proposed by Alex Tabarrok for funding public goods. The following summarizes a 2012 class paper of mine on dominant assurance contracts. Mainly, I will be... |
54cd4a0e-09f1-49e0-a125-31ef85c26baa | trentmkelly/LessWrong-43k | LessWrong | Hunger can make you stupid
When I originally wrote "When to scream 'Error!'", I was mainly thinking of bad patterns of thought or bad problem-solving strategies as being the source of the error. Since then, I've come to realize that my own most common source of stupidity is because I've neglected some comfort. I may b... |
df7b9a5b-72d1-466c-8e5b-6798785713b2 | StampyAI/alignment-research-dataset/arbital | Arbital | Compressing multiple messages
How many [bits of data](https://arbital.com/p/3p0) does it take to encode an [$n$-message](https://arbital.com/p/3v9)? Naively, the answer is $\lceil \log_2(n) \rceil$ ([why?](https://arbital.com/p/n_message_bit_length)): For example, it takes 5 bits to encode a 21-message, because 4 bits... |
e8ecb1a9-14bc-42fe-bbe1-7ba6d0a17d2f | trentmkelly/LessWrong-43k | LessWrong | [LINK] Cholesterol and mortality
Discussion of a Norwegian study looking at 50,000 people who didn't have pre-existing heart disease for ten years. http://drmalcolmkendrick.files.wordpress.com/2012/09/mortality-and-cholesterol1.png?w=600&h=309
> As you can see, for women the story is very straightforward indeed. T... |
3dd3ede5-252d-44cd-8bf9-80ded893df87 | trentmkelly/LessWrong-43k | LessWrong | December 2012 Media Thread
This is the monthly thread for posting media of various types that you've found that you enjoy. I find that exposure to LW ideas makes me less likely to enjoy some entertainment media that is otherwise quite popular, and finding media recommended by LWers is a good way to mitigate this. Post... |
e16d5645-ffd2-4518-a77c-8df7f0c8002d | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | The universal prior is malign
|
c6b2878a-0e75-4991-8806-764b78c889c2 | trentmkelly/LessWrong-43k | LessWrong | Monthly Roundup #3
It’s that time again.
Bad News
Guardian analyzes projects from world’s biggest carbon offset provider, finds ‘94% of the credits had no benefit to the climate.’ Bloomberg found something similar in 2020, changing nothing. Carbon offsets are not about carbon. Very little that is said or done in the... |
0e03318e-f07b-4393-98f0-2221c9be69f0 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | AI-Plans.com - a contributable compendium
Hello, we’re working on <https://ai-plans.com> .
Ideas behind the site:
======================
Right now, alignment plans are spread all over the place and it’s difficult for a layperson, or someone unfamiliar with the field to get an idea of what is the current plan ... |
dc1184e1-86d8-4624-b121-e3debf7b75f0 | trentmkelly/LessWrong-43k | LessWrong | Sustainability of Human Progress
John McCarthy, the inventor of LISP and one of the founders of the study of AI, died earlier this week. McCarthy was actually the person who came up with the phrase "Artificial Intelligence", in 1955. I find it likely that one day, not very soon, the first thinking self-aware machines ... |
cea87c08-efc5-4871-9d9d-24e596de3250 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Epistemological Framing for AI Alignment Research
Introduction
============
You open the Alignment Forum one day, and a new post stares at you. By sheer luck you have some time, so you actually read it. And then you ask yourself the eternal question: how does this fit with the rest of the field? If you’re like me, yo... |
0b63a898-43f5-4ae8-9241-0638d2081084 | trentmkelly/LessWrong-43k | LessWrong | Surviving Seveneves
Contains spoilers for the first couple of chapters of Seveneves
Highly speculative on my part, I know very little about most of these topics
In Seveneves Neal Stephenson does the classic sci-fi trick of assuming that exactly one thing in the universe is different, and seeing where that takes us. ... |
e4761b3d-b25f-43aa-90cf-3ce45ab78a1a | trentmkelly/LessWrong-43k | LessWrong | Meetup : Atlanta - Game night!
Discussion article for the meetup : Atlanta - Game night!
WHEN: 22 April 2012 06:30:00PM (-0400)
WHERE: marietta, ga
Our LessWrong meetup group will be getting together to play a variety of games (rationality-related or not) at a private residence in Marietta, this Sunday April 22nd a... |
0b0d58e9-23ac-47ba-95c0-52a9a0734399 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | Life is like a game - DeepMind: The Podcast (S1, Ep3)
[Music]
artificial intelligence is slowly
appearing in every aspect of our modern
lives it's in our smartphones of central
heating on our side boards and in our
cars but what about artificial general
intelligence that is the real quest the
aim to build an agent an ... |
11874002-4d0c-49fb-bfb4-90f8d32f896f | trentmkelly/LessWrong-43k | LessWrong | Zibbaldone With It All
Less Zettelkasten! More Zibbaldone!
A Zettelkasten requires you to intricately interconnect and crosslink your thoughts, figuring out exactly how each concept relates to every other concept. A Zibbaldone is writing down whatever random thing comes to mind - an omnisubject diary of sorts. That's... |
87177cbd-151d-4c24-bfb1-9f30c98ff1ad | trentmkelly/LessWrong-43k | LessWrong | "Taking your environment as object" vs "Being subject to your environment"
I think there's a key rationalist skill of being able to take your environment as object, rather than being subject to it.
There's a kind of wisdom people get when they leave environments. Today I talked to a friend of mine who has moved out o... |
79df42af-7de0-47e0-93c0-43971546bc07 | trentmkelly/LessWrong-43k | LessWrong | Minds are magic
As we know, brains are incredibly complex connections of neurons. If physics is deterministic so are our brains. But that's not how we think about brains. We think about them as MINDS. And minds are neat and consistent.
There are a lot of benefits to thinking about brains as minds:
* Studies ... |
7ee171bf-0b4a-4ab1-9862-c4c6bb2437fe | trentmkelly/LessWrong-43k | LessWrong | On Sleep Procrastination: Going To Bed At A Reasonable Hour
Who Would Find This Article Most Helpful
* Those who find going to bed at a reasonable hour a major bottleneck to getting enough sleep and maintaining a healthy sleep schedule
* Those interested in thinking more deeply about their mindset with respect to sl... |
1a78f369-3451-4743-86fd-e2dff74e7192 | StampyAI/alignment-research-dataset/blogs | Blogs | Final fundraiser day: Announcing our new team
Today is the final day of MIRI’s [summer fundraising drive](https://intelligence.org/2015/07/17/miris-2015-summer-fundraiser/), and as of this morning, our total stands at $543,373. Our donors’ efforts have made this fundraiser the biggest one we’ve ever run, and we’re hug... |
fed3cdb8-baa6-4ce4-8128-afef25c75b4f | trentmkelly/LessWrong-43k | LessWrong | Could there be "natural impact regularization" or "impact regularization by default"?
Specifically, imagine you use general-purpose search procedure which recursively invokes itself to solve subgoals for the purpose of solving some bigger goal.
If the search procedure's solutions to subgoals "change things too much",... |
d8bff76b-8eca-4539-8931-4dc71517c904 | trentmkelly/LessWrong-43k | LessWrong | Less Wrong: Open Thread, September 2010
This thread is for the discussion of Less Wrong topics that have not appeared in recent posts. If a discussion gets unwieldy, celebrate by turning it into a top-level post. |
e8e931de-39a8-4b0b-9720-f5a5982495cd | trentmkelly/LessWrong-43k | LessWrong | Review: Good Strategy, Bad Strategy
I used to think that all generic strategy advice was pointless. After all, the point of a strategy is to achieve a thing, and to achieve a thing you just think hard about how to best do it and then work hard to do it. I said this to my friend Dewi, who said that this is mostly true,... |
09434cc0-3e24-4e02-abf9-070d1d90c59d | trentmkelly/LessWrong-43k | LessWrong | Bioweapons, and ChatGPT (another vulnerability story)
Epistemic status: experimentally confirmed.
Certain details redacted for infohazard reasons.
It's no secret that ChatGPT can be made to give harmful output, with trivial difficulty. I became curious what would happen if it is prompted to make a biological weapon... |
c208019b-5f58-4d0f-a767-9615c34c0d79 | trentmkelly/LessWrong-43k | LessWrong | Year 1 Redux – Poseur
I try to maintain equanimity regarding most bitter conflicts raging in the world, but I do get quite worked up regarding proper statistical methodology in psychology research. Hey, we all need our hobbies. When I wrote a post about it, I tried to focus on constructive advice on how to do science ... |
ead4821e-b151-48c1-b468-dbd75254b9a4 | trentmkelly/LessWrong-43k | LessWrong | Furry Rationalists & Effective Anthropomorphism both exist
(cross-posted on EA Forum and my website)
Hi!
I’m Rai and I’m a furry (specifically, dragon). The last couple years, I’ve been running a Furry Rationalists Telegram group. It looks like we exist, and not everyone who should know we exist does yet, so I wante... |
0f55bc18-3101-4afd-aeec-47dd587b9ba3 | StampyAI/alignment-research-dataset/arxiv | Arxiv | AI Can Stop Mass Shootings, and More
Introduction
------------
No one reading this sentence is unaware of tragic mass shootings in
the past. Can future carnage of this kind be forestalled? If so,
how? Many politicians of all stripes confidently answer the first
question in the affirmative, but unfortunately then a ... |
b380289f-956e-47d2-846d-793bb187a9fd | trentmkelly/LessWrong-43k | LessWrong | Physicists say simulation hypothesis is impossible in principle
https://cosmosmagazine.com/physics/physicists-find-we-re-not-living-in-a-computer-simulation
If these results are right, our universe being a simulation would require an impossibly big computer. They conclude the simulation hypothesis is impossible in pr... |
8434254f-c7fd-4614-a77e-0ffe50a366c4 | trentmkelly/LessWrong-43k | LessWrong | A Short Note on My Value Notion
Value of something
When I have $100 to spend, I can buy ~50 cups of coffee, ~10 regular meals, or a 1-night stay at a hotel, etc. Accordingly it feels like the value of $100 should be ~50 cups of coffee, or ~10 meals, or a one-night stay at a hotel. If I can’t put this $100 into any usa... |
49a872cb-8062-45c9-a396-42169463f6b9 | trentmkelly/LessWrong-43k | LessWrong | An Easily Overlooked Post on the Automation of Wisdom and Philosophy
This week for Wise AI Wednesdays, I'll be sharing something a bit different - the announcement post of a competion that is already over (the AI Impacts Essay competition on the Automation of Wisdom and Philosophy). If you're wondering why I'm sharing... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.