id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
4354c385-d694-4dd3-8fcd-326bba83546f | trentmkelly/LessWrong-43k | LessWrong | DAGGRE group forecasting workshop
Anyone else going? http://blog.daggre.org/
Looks like you can barely get direct roundtrip from LA<->DC for $600 now (probably double that if you wait a week to book). |
58d48e16-a977-48b3-ab2d-25d48f40d942 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | What are some low-cost outside-the-box ways to do/fund alignment research?
The last two years of alignment research were characterized by cheap easy money that is going to dry up soon. There are (were) [~300 alignment researchers on earth](https://what%20are%20some%20ways%20to%20improve%20these%20strategies/?), and th... |
a442f98d-5772-4502-a6b5-94dc58a9a2ad | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Are Generative World Models a Mesa-Optimization Risk?
Suppose we set up a training loop with an eye to get a generative world-model. For concretedness, let's imagine the predictor from [the ELK doc](https://www.lesswrong.com/posts/qHCDysDnvhteW7kRd/arc-s-first-technical-report-eliciting-latent-knowledge). We show the ... |
390f5e7d-b116-40a5-987f-edfcecc486d8 | trentmkelly/LessWrong-43k | LessWrong | Would you take a job making humanoid robots for an AGI?
I just finished reading the transcript from this interview with Carl Shulman, and found these parts particularly interesting.
* “Converting the car industry to making Humanoid Robots.”
* https://youtu.be/_kRg-ZP1vQc?t=6363
* “Where the Human workers are mor... |
0f62c0f8-29cf-4bd0-b177-a4084c0162ab | trentmkelly/LessWrong-43k | LessWrong | This Sunday: Oxford Rationality Meetup
This Sunday there will be a rationality meetup in Oxford.
Where: Entrance to Exeter College, Turl Street (map here)
When: 5-7pm, Sunday January 30th
We'll be discussing artificial intelligence and existential risks. We plan to split into two groups to ensure we have something f... |
f25ae1ab-2e73-4dc0-94ec-e76e16a4881a | trentmkelly/LessWrong-43k | LessWrong | Meetup : Baltimore / UMBC - Unsong Readalong Edition!
Discussion article for the meetup : Baltimore / UMBC - Unsong Readalong Edition!
WHEN: 14 May 2017 08:00:00AM (-0400)
WHERE: Performing Arts and Humanities Building, 1000 Hilltop Cir, Baltimore, MD 21250, United States
Casual discussion group! But this week we w... |
e6e8a7af-0cf5-46e7-bc0a-283873571cac | trentmkelly/LessWrong-43k | LessWrong | Open Thread May 23 - May 29, 2016
If it's worth saying, but not worth its own post (even in Discussion), then it goes here.
----------------------------------------
Notes for future OT posters:
1. Please add the 'open_thread' tag.
2. Check if there is an active Open Thread before posting a new one. (Immediately be... |
554cba03-098a-4a30-9574-203bbdc32333 | trentmkelly/LessWrong-43k | LessWrong | How are Simulators and Agents related?
In this post, I will provide some speculative reasoning about Simulators and Agents being entangled in certain ways.
I have thought quite a bit about LLMs and the Simulator framing for them, and I am convinced that it is a good explanatory/predictive frame for behavior of curre... |
2b653732-fab7-406b-92c0-e03844a04e10 | trentmkelly/LessWrong-43k | LessWrong | The Psychological Diversity of Mankind
The dominant belief on this site seems to be in the "psychological unity of mankind". In other words, all of humanity shares the same underlying psychological machinery. Furthermore, that machinery has not had the time to significantly change in the 50,000 or so years that have p... |
67fe9f74-aaac-456c-b890-25cd36c47c41 | trentmkelly/LessWrong-43k | LessWrong | Bitcoin Bounty: Advice Requested
About a month ago, I started a prize for Cryonics promotional videos published to Youtube during the month of May. There was a fair bit of interest, but nobody actually submitted anything. So the 14.75 bitcoins are thus far unclaimed.
I want to use this money (worth ~$125) to start an... |
ef34c716-6712-4215-b099-86484e08bd69 | trentmkelly/LessWrong-43k | LessWrong | Gaming Democracy
I live in the UK, which has a very similar voting structure to the US for the purposes of this article. Nevertheless, it may differ on the details, for which I am sorry. I also use a couple of real-life political examples which I hope are uncontroversial enough not to break the unofficial rules here. ... |
d8f10405-6f6f-47ea-900c-1b70e4d8e6c5 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities
1 Introduction
---------------
Artificial intelligence (AI) has undergone significant and continuous progress in the past decade, resulting in the increased adoption of its algorithms (e.g., machine learning (ML) algorithm... |
d5c09b6f-90ac-48d6-abff-fd08f734cb77 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Generalised models as a category
Naming the "generalised" models.mjx-chtml {display: inline-block; line-height: 0; text-indent: 0; text-align: left; text-transform: none; font-style: normal; font-weight: normal; font-size: 100%; font-size-adjust: none; letter-spacing: normal; word-wrap: normal; word-spacing: normal; w... |
39bd7e44-4a1f-4f2d-9534-0fed9c47db40 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Paper: Discovering novel algorithms with AlphaTensor [Deepmind]
The authors apply an AlphaZero-like algorithm to discover new matrix multiplication algorithms. They do this by turning matrix multiplication into a one-player game, where the state represents how far from correct the current output is, moves are algorith... |
31e79e6b-8374-4e04-aca8-7485f3bc55fa | trentmkelly/LessWrong-43k | LessWrong | Meetup : Bangalore LW Meetup
Discussion article for the meetup : Bangalore LW Meetup
WHEN: 09 May 2015 09:18:03AM (+0530)
WHERE: Bangalore
Just another LW Bangalore meetup at Cafe Coffee Day, Bangalore Central
Discussion article for the meetup : Bangalore LW Meetup |
348483af-2201-475a-804a-9df7aa379352 | trentmkelly/LessWrong-43k | LessWrong | Grokking illusionism
(Cross-posted from Hands and Cities)
A number of people I know are illusionists about consciousness: that is, they think that the way consciousness seems to us involves some fundamental misrepresentation. On an extreme version of this view (which Frankish (2016) calls “strong illusionism”), pheno... |
72e3e336-65c2-4d41-a846-41258595bd4a | trentmkelly/LessWrong-43k | LessWrong | Coherence of Caches and Agents
There's a lot of confusion about what coherence means for agents, and what "coherence theorems" do and don't say about agents. In this post, I'll talk about some particularly simple notions of coherence in a particularly simple setting. We'll see what nontrivial things coherence has to s... |
f1300d1f-b357-48fe-8cab-168747c631ce | trentmkelly/LessWrong-43k | LessWrong | Deference on AI timelines: survey results
Crossposted to the EA Forum.
In October 2022, 91 EA Forum/LessWrong users answered the AI timelines deference survey. This post summarises the results.
Context
The survey was advertised in this forum post, and anyone could respond. Respondents were asked to whom they defer ... |
ac1b33b9-6bd2-4f57-aad3-a91fba938574 | trentmkelly/LessWrong-43k | LessWrong | Manifund: What we're funding (weeks 2-4)
Overall reflections
* Very happy with the volume and quality of grants we’ve been making
* $600k+ newly committed across 12 projects
* Regrantors have been initiating grants and coordinating on large projects
* Independent donors have committed $35k+ of their own mone... |
36216f47-41d1-4aba-9ab6-ea3aed340181 | trentmkelly/LessWrong-43k | LessWrong | Noticing the World
There are a lot of problems facing the world right now. To decide which to confront, you must know enough about the overall class of problems to say "yes, I want to work on x" because I feel that breakthrough "y" makes it possible to solve this problem and others aren't working on it for so and so r... |
478704e0-3bf3-4c4d-b6cf-35134e30b1ab | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | The odd counterfactuals of playing chicken
.mjx-chtml {display: inline-block; line-height: 0; text-indent: 0; text-align: left; text-transform: none; font-style: normal; font-weight: normal; font-size: 100%; font-size-adjust: none; letter-spacing: normal; word-wrap: normal; word-spacing: normal; white-space: nowrap; f... |
0c7fed09-7dd9-4631-981a-b23d17b7eefc | trentmkelly/LessWrong-43k | LessWrong | Mosaic and Palimpsests: Two Shapes of Research
(Minor update to change Steve's labelling following this comment, and also because I realized that I never added the footnotes...)
This post is part of the work done at Conjecture.
Introduction
In Old Masters and Young Geniuses, economist-turned-art-data-analyst David ... |
6c85e9cf-e739-40d2-bfe3-91acb025e3da | StampyAI/alignment-research-dataset/blogs | Blogs | When do ML Researchers Think Specific Tasks will be Automated?
*By Katja Grace, 26 September 2017*
We asked the ML researchers in our [survey](http://aiimpacts.org/2016-expert-survey-on-progress-in-ai/) when they thought 32 narrow, relatively well defined tasks would be feasible for AI. Eighteen of them were include... |
a6fb0bc1-a4d8-4c8b-beba-db925197ab00 | trentmkelly/LessWrong-43k | LessWrong | Best-Responding Is Not Always the Best Response
Suppose that you are designing a software system to bargain on your behalf. Either side can walk away from negotiations, and we'll use this as our baseline for each side receiving $0 of the possible gains from working together. How should such a system handle a case wher... |
7064461d-7aa4-4615-a475-f2f813cffe57 | trentmkelly/LessWrong-43k | LessWrong | Contra Paul Christiano on Sex
Contra Paul Christiano on Sex
I have come to think that many people don’t understand evolution. Not in the “believe that a sentient deity created the universe after a template” sense. A lot of people seem to “get” the idea of evolution in broad strokes but then fail at explaining its vari... |
6d7f69c1-daca-48eb-94a0-d31d6b9c6ea5 | trentmkelly/LessWrong-43k | LessWrong | Perfectionism as depth-first search
Perfectionism could be generally defined as an approach to solving problems and completing tasks fixated primarily on minimizing perceived imperfection.
Depth-first search, meanwhile, is an algorithm for traversing tree structures, which starts at the root, then goes down a single ... |
a421d956-3cef-41eb-aa21-965fd751fbf0 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Machines vs Memes Part 3: Imitation and Memes
**This is the last in a series of three posts on the interlinkages between Memetics and AI Alignment. It was written as an output from the 2022 AI Safety Camp, for the ‘Impact of Memetics on Alignment’ team, coached by Daniel Kokotajlo and comprising Harriet Farlow, Nate R... |
125bfcc3-ff69-42fa-a560-425f2015101f | trentmkelly/LessWrong-43k | LessWrong | Erroneous Visualizations
Buried somewhere among Eliezer's writings is something essentially the same as the following phrase:
"Intentional causes are made of neurons. Evolutionary causes are made of ancestors."
I remember this quite well because of my strange reaction to it. I understood what it meant pretty well, b... |
ddc96ea3-3a9d-429c-be57-cedacd43c9e4 | trentmkelly/LessWrong-43k | LessWrong | Do you have High-Functioning Asperger's Syndrome?
----------------------------------------
EDIT: To combat nonresponse bias, I'd appreciate it if anyone who looked at this post before and decided not to fill in the poll would go and do so now, but that people who haven't already considered and decided against fill... |
9e2f5def-ce16-41c3-8de6-b61f33b6c48a | trentmkelly/LessWrong-43k | LessWrong | Unlocking Solutions—By Understanding Coordination Problems
The following is a post introducing coordination problems, using the examples of poaching, civilisational development, drug addiction and affirmative action. It draws on my experience as a documentary filmmaker. The post is available for free in its original f... |
58dcf722-45b7-46e2-9790-783306e727fa | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Automatically crosspostedSuppose that a kingdom contains a million peasants and a thousand nobles, and:Each noble makes as much as 10,000 peasants put together, such that collectively the nobles get 90% of the income.Each noble cares about as much about themselves as they do about all peasants put together.Each person... |
7a063288-146d-46ff-b2f2-b9c4d991b51a | trentmkelly/LessWrong-43k | LessWrong | Alignment: "Do what I would have wanted you to do"
Yoshua Bengio writes[1]:
> nobody currently knows how such an AGI or ASI could be made to behave morally, or at least behave as intended by its developers and not turn against humans
I think I do[2]. I believe that the difficulties of alignment arise from trying to ... |
4fcb1bcf-1a96-47e7-ad51-272171f6e8c4 | trentmkelly/LessWrong-43k | LessWrong | What price would you pay for the RadVac Vaccine and why?
I have been following with interest the RadVac team and their synthetic peptide based intranasal vaccine. They have published a protocol for making and taking the vaccine as well as a list of potential risks (on pg. 9 of the white paper).
How much would you pay... |
96eda896-c039-447b-8177-420cc658047d | trentmkelly/LessWrong-43k | LessWrong | A basis for pattern-matching in logical uncertainty
Previous logical uncertainty robot designs (e.g. here, here, here) have relied on proving theorems that relate to the statement (e.g. "the trillionth digit of pi is 5") under inspection (where a useful theorem would be e.g. "there are 10 possible mutually exclusive d... |
52c16501-1898-4431-8289-06bb417377d7 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Breaking the Optimizer’s Curse, and Consequences for Existential Risks and Value Learning
Multi-Armed Bandits Considered Harmful
--------------------------------------
People frequently analyze the process of artificial agents gathering knowledge in the framework of explore/exploit strategies for multi-armed bandits.... |
5608a275-6478-48ec-80bc-2864905af36b | trentmkelly/LessWrong-43k | LessWrong | What is the appropriate way to communicate that we are experiencing a pandemic?
After spending 3 days reading all of Lesswrong's posts and comments (and sources cited) related to coronavirus, I started taking action (summarizing the information collected and planning the least harmful ways to alert my closest peers to... |
2b0f4e88-6297-441c-a773-fab2e029eb43 | trentmkelly/LessWrong-43k | LessWrong | Introduction to Super Powers (for kids!)
And how surprisingly untraumatizing it apparently is when mom feigns amnesia.
----------------------------------------
I’m going to be honest here and say I just did the mental equivalent of a fist pump when my 5 year old responded to a prompt to pick any book in the book sto... |
2bfe4178-ba4f-4206-b7aa-b74d9eff1d63 | trentmkelly/LessWrong-43k | LessWrong | What should we do about network-effect monopolies?
Many large companies today are software monopolies that give their product away for free to get monopoly status, then do the most horrible things once they’ve won. (Previously, previously.) Can we do anything about this?
Unfortunately, “you’re the product” is a popul... |
08cd866d-1577-4ab5-aea7-ef69a48c04c7 | trentmkelly/LessWrong-43k | LessWrong | The potential exploitability of infinite options
You would think that interacting with a fully known, deterministic system, when you have unbounded computing power should be easy, you just pick the series of actions that lead to the highest reward. In cases with finitely many end states, this is the case.
Suppose y... |
e3e31420-d809-4b15-8fcd-23d3e9a8dbce | StampyAI/alignment-research-dataset/arxiv | Arxiv | Reasoning About Beliefs and Actions Under Computational Resource Constraints
I
Abstract Reasoning About Beliefs and Actions
Under Computational Resource Constraints
Eric J. Horvitz
Medical Computer Science Group
Knowledge Systems Laboratory
Stanford University
Stanford, California 94305
Although many investiga... |
177b3d8e-a799-4da1-93c7-27bf306c4d87 | trentmkelly/LessWrong-43k | LessWrong | Where to absolutely start?
Hi there!
I'm a new member and now feeling giddy from the amount of contents presented here on the site. I've read those welcome and FAQ posts, they all point to the library's core reading as material for beginners. BUT... I've just finished the Preface post of R:A-Z, and from the author's ... |
5cd0b15c-95ce-4e57-b106-0a122db31f3f | trentmkelly/LessWrong-43k | LessWrong | Thinking Statistically [ebook]
Uri Bram, a recent Princeton graduate, has just published an ebook called Thinking Statistically. The book is aimed at conveying a few important statistical concepts (selection bias, endogeneity and correlation vs. causation, Bayes theorem and base rate neglect) to a general audience. Th... |
740e6ef4-4b25-4a08-ab6e-d9b63a231a04 | trentmkelly/LessWrong-43k | LessWrong | The Hamming Question
This is a stub post, mostly existing so people can easily link to a post explaining what the Hamming question is. If you would like to write a real version of this post, ping me and I'll arrange to give you edit rights to this stub.
For now, I am stealing the words from Jacobian's event post:
> ... |
7a461543-bd4f-4d77-93f0-4958b25eaf76 | trentmkelly/LessWrong-43k | LessWrong | Linked List
|
3e953874-6705-4170-8fab-c1cb1bad48a4 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Lesswrong can, and should, become a hacker community
80,000 Hours now considers [Information security in high-impact areas](https://80000hours.org/career-reviews/information-security/) to be #4, under AI safety technical research (#1) and AI governance (#2). You can find the career profile and their justification for ... |
23ac0c36-36dc-414b-8679-184993e1d726 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | AXRP Episode 25 - Cooperative AI with Caspar Oesterheld
[YouTube link](https://youtu.be/0JkaOAzDfgE)
Imagine a world where there are many powerful AI systems, working at cross purposes. You could suppose that different governments use AIs to manage their militaries, or simply that many powerful AIs have their own wi... |
edbb3721-8be3-444c-a393-94888e635cd2 | trentmkelly/LessWrong-43k | LessWrong | When AI 10x's AI R&D, What Do We Do?
Note: below is a hypothetical future written in strong terms and does not track my actual probabilities.
Throughout 2025, a huge amount of compute is spent on producing data in verifiable tasks, such as math[1] (w/ "does it compile as a proof?" being the ground truth label) and co... |
77ed8c30-d679-48a0-b30f-cff2e9570d4b | trentmkelly/LessWrong-43k | LessWrong | The Alignment Problems
Epistemic status: A core idea I've seen hinted at in many places, here presented and motivated explicitly.
This was produced during SERI MATS 3.0. Thanks to Vivek Hebbar for related discussion.
There has recently been pushback on the inner/outer alignment conceptualization: it's confused; or i... |
312cd505-6505-47cf-bf4f-d2519a892966 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Execute Order 66: Targeted Data Poisoning for Reinforcement Learning
1 Introduction
---------------
Reinforcement Learning (RL) has quickly achieved impressive results in a wide variety of control problems, from video games to more real-world applications like autonomous driving and cyber-defense (Vinyals et al., [... |
048b238e-d167-457f-a444-125ec8a9f09a | trentmkelly/LessWrong-43k | LessWrong | A reply to Agnes Callard
Agnes Callard says on Twitter:
> Sincerely can't tell which threatens culture of free thought & expression more:
> @nytimes de-anonymizing & destroying a (rightly) treasured blog for no good reason
> @nytimes increasingly allowing external mobs (w/powerful members) influence over what it pu... |
09b1690a-91bc-48b1-841a-6e9a4d92b155 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Preference Aggregation as Bayesian Inference
*Crossposted from* [*my personal blog*](https://www.beren.io/2023-07-13-Preference-Aggregation-as-Bayesian-Inference/)*.*
A fundamental problem in AI alignment, as well as in many social sciences is the problem of *preference aggregation*. Given a number of different actor... |
84ff2539-f43c-4ea4-a4d0-ba1386e7c605 | trentmkelly/LessWrong-43k | LessWrong | Comparing the AirFanta 3Pro to the Coway AP-1512
When I drafted my post on alternatives to masks for infectious aerosols I initially based the air purifier section on the AP-1512. This is a common air purifier that I bought several of on the Wirecutter's recommendation, and I haven't had any trouble with it. When revi... |
5dc25bd7-148b-457f-ae95-38efdd5d2535 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | An upcoming US Supreme Court case may impede AI governance efforts
According to [various](https://www.scotusblog.com/2023/05/supreme-court-will-consider-major-case-on-power-of-federal-regulatory-agencies/) [sources](https://www.politico.com/news/2023/05/01/supreme-court-chevron-doctrine-climate-change-00094670), the ... |
85a8e30c-b511-494d-9dc3-0308fb7847e1 | trentmkelly/LessWrong-43k | LessWrong | Tear Down the Burren
I love the Burren. It hosts something like seven weekly sessions in a range of styles and the back room has hosted many great acts including many of my friends. It's a key space in the Boston folk scene, and it's under threat from developers who want to tear it down.
But after thinking it through... |
9e8aae6b-dcdd-4c1a-9413-9d274be6e343 | trentmkelly/LessWrong-43k | LessWrong | Template For Effective Action
Hey LessWrong -
This community has been extremely beneficial to my life in more ways than I can describe. I'm working on a new company and am in the process of creation documentation before launching, including some project plan templates. I figured I would share one of the templates (s... |
75a167d4-60f1-4ebd-8a6c-cd9740bb49f4 | trentmkelly/LessWrong-43k | LessWrong | Is an Intelligence Explosion a Disjunctive or Conjunctive Event?
(The following is a summary of some of my previous submissions that I originally created for my personal blog.)
> ...an intelligence explosion may have fair probability, not because it occurs in one particular detailed scenario, but because, like the ev... |
3b82c9f5-6098-4d33-94b5-8e250320089c | trentmkelly/LessWrong-43k | LessWrong | Why abandon “probability is in the mind” when it comes to quantum dynamics?
A core tenet of Bayesianism is that probability is in the mind. But it seems to me that even hardcore Bayesians can waffle a bit when it comes to the possibility that quantum probabilities are irreducible physical probabilities.
I don’t know ... |
d6521982-6c97-48e4-9a7d-bb7b7e0dad72 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Debate Minus Factored Cognition
[AI safety via debate](https://www.alignmentforum.org/posts/wo6NsBtn3WJDCeWsx/ai-safety-via-debate) has been, so far, associated with [Factored Cognition](https://www.alignmentforum.org/s/EmDuGeRw749sD3GKd). There are good reasons for this. For one thing, Factored Cognition gives us a p... |
6a49c29a-cde8-4c81-a9b3-dc4f0b7cae50 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Against the Open Source / Closed Source Dichotomy: Regulated Source as a Model for Responsible AI Development
**Context**
===========
This is a short post to illustrate and start testing an idea that I have been playing around with in the last couple of days after listening to a recent [80,000 hours podcast with Must... |
21111035-445e-4837-8901-c99f8b54f764 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Deeper Interpretability of Deep Networks
1 Introduction
---------------
Hierarchical CNNs and their multiple nonlinear projections of visual inputs have become prime intuition pumps to model visual categorization in relation to the hierarchical occipito-ventral pathway in the brain ([[2](#bib.bib2), [4](#bib.bib4),... |
d042ec9c-2bca-4f8d-8608-1e33cbba4c86 | trentmkelly/LessWrong-43k | LessWrong | Formalizing reflective inconsistency
In the post Outlawing Anthropics, there was a brief and intriguing scrap of reasoning, which used the principle of reflective inconsistency, which so far as I know is unique to this community:
> If your current system cares about yourself and your future, but doesn't care about ve... |
a0c63874-c659-43c0-a015-de505862e696 | trentmkelly/LessWrong-43k | LessWrong | My hour of memoryless lucidity
Yesterday, I had a coronectomy: the top halves of my bottom wisdom teeth were surgically removed. It was my first time being sedated, and I didn’t know what to expect. While I was unconscious during the surgery, the hour after surgery turned out to be a fascinating experience, because I ... |
ab026cf5-275f-4438-a698-5366fa98ea3a | trentmkelly/LessWrong-43k | LessWrong | LW Meetup in Nuremberg (Germany)
Hi everyone,
we just reached the staggering number of four interested parties to meetup in Nuremberg. If anyone else is curious just mail me. We are so far working out the time. So no specific plans, just a get to know.
Martin |
e3d8eaa0-b85b-4949-ad7c-02384d21561e | StampyAI/alignment-research-dataset/blogs | Blogs | Conversation with Paul Christiano
AI Impacts talked to AI safety researcher Paul Christiano about his views on AI risk. With his permission, we have transcribed this interview.
**Participants**
----------------
* [Paul Christiano](https://paulfchristiano.com/) — OpenAI safety team
* Asya Bergal – AI Impacts
* Ronn... |
f9574652-7e90-47cd-a62c-44c794c5b93c | trentmkelly/LessWrong-43k | LessWrong | Noting an unsubstantiated belief about the FTX disaster
There is a narrative about the FTX collapse that I have noticed emerging[1] as a commonly-held belief, despite little concrete evidence for or against it. The belief goes something like this:
* Sam Bankman Fried did what he did primarily for the sake of "Effec... |
0c066f05-b58f-43e1-a110-7aecb5dc4b1e | trentmkelly/LessWrong-43k | LessWrong | Predictor schemes with logarithmic advice
We introduce a variant of optimal predictor schemes where optimality holds within the space of random algorithms with logarithmic advice. These objects are also guaranteed to exist for the error space Δ2avg. We introduce the class of generatable problems and construct a unifor... |
e2963d2f-f8ee-4c40-9d04-6eaeb1eecabf | trentmkelly/LessWrong-43k | LessWrong | A few thoughts on my self-study for alignment research
In June, I received a grant from the LTFF for a 6-months period of self-study aimed at mastering the necessary background for AI alignment research. The following is advice I would give to people who are attempting something similar. I have tried to keep it short.... |
6ee13b6e-9ba6-46e3-8496-0500e3d684e9 | StampyAI/alignment-research-dataset/special_docs | Other | An Empirical Investigation of Representation Learning for Imitation.
An Empirical Investigation of
Representation Learning for Imitation
Xin Chen
The University of Hong Kong
cyn0531@connect.hku.hkSam Toyer
UC Berkeley
sdt@berkeley.eduCody Wild
UC Berkeley
codywild@berkeley.edu
Scott Emmons
UC BerkeleyIan Fischer
Go... |
9d8a19fd-b6f8-4889-a2bc-d429b126fd92 | trentmkelly/LessWrong-43k | LessWrong | New LessWrong review winner UI ("The LeastWrong" section and full-art post pages)
(Also announcing: annual review prediction markets & full-height table of contents. If you're looking for this year's review results, you can find them here)
The top 50 posts of each of LessWrong’s annual reviews have a new home: The Le... |
8d7f6fb4-cfcd-4def-a57c-6151910df7cc | trentmkelly/LessWrong-43k | LessWrong | [Thought Experiment] Given a button to terminate all humanity, would you press it?
The rules:
1. Pressing the button will instantly terminate every single human being (including you).
2. Pressing the button is completely anonymous. Nobody will know you did it, now or in the far future.
3. The button cannot malfunc... |
561618bf-f551-4a0c-bb2c-4e7ef7619fee | trentmkelly/LessWrong-43k | LessWrong | College Advice For People Like Me
I'm graduating from UChicago in around 60 days, and I've been thinking about what I've learned these past four years. I figured I'd write it all down while it's still fresh.
This isn't universal advice. It's specifically for people like me (or who want to be like me). High-agency, mo... |
c2c277ca-0442-42b4-b490-3f34161dfffc | StampyAI/alignment-research-dataset/blogs | Blogs | Complexity no Bar to AI
> Computational complexity theory describes the steep increase in computing power required for many algorithms to solve larger problems; frequently, the increase is large enough to render problems a few times larger totally intractable. Many of these algorithms are used in AI-relevant contexts.... |
9841f41e-2cf2-4914-84cd-54fe064c417d | trentmkelly/LessWrong-43k | LessWrong | An Alternative Interpretation of Physics
1. Physics With Minimal Assumptions
“I am this thing”. That is perhaps the most basic fact I know of. It is not a conclusion based on reasoning, but something much more instinctive: “I know how it feels.“. For me, the only subjective experience is from this thing. It’s at ... |
793846ea-009c-4b7b-a6c7-71898809eeb0 | trentmkelly/LessWrong-43k | LessWrong | Saturation, Distillation, Improvisation: A Story About Procedural Knowledge And Cookies
Most propositional knowledge (knowledge of facts) is pretty easy to come by (at least in principle). There is only one capital of Venezuela, and if you wish to learn the capital of Venezuela, Wikipedia will cooperatively inform yo... |
69f94dbc-f864-44ae-ba2b-570ef5d71a86 | StampyAI/alignment-research-dataset/arbital | Arbital | Ability to read logic
This requisite asks whether you can read a sentence that throws in logical ideas and notation, without slowing down too much. If the statement $(\exists v: \forall w > v: \forall x>0, y>0, z>0: x^w + y^w \neq z^w) \rightarrow ((1 = 0) \vee (1 + 0 = 0 + 1))$ makes sense after a bit of staring, yo... |
c0ba12b8-cd8c-4194-86d1-0800de940915 | trentmkelly/LessWrong-43k | LessWrong | Why focus on schemers in particular (Sections 1.3 and 1.4 of “Scheming AIs”)
This is Sections 1.3 and 1.4 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?”. There’s also a summary of the full report here (audio here). The summary covers most of the main points and technical te... |
580291af-1d5e-4f89-a0d0-a9a1829b149b | trentmkelly/LessWrong-43k | LessWrong | Informers and Persuaders
Suppose we lived in this completely alternate universe where nothing in academia was about status, and no one had any concept of style. A universe where people wrote journal articles, and editors approved them, without the tiniest shred of concern for what "impression" it gave - without tryin... |
4dd660c1-de2c-4fb5-aab5-826bdb63eda3 | trentmkelly/LessWrong-43k | LessWrong | A design concept for superintelligent machines (and Popper's critique of induction)
This is my first post on LessWrong and I apologize for the length. I thought it would be possible that someone here is interested in reading or critiquing it.
The blog post is my attempt to explain why we do not yet have AGI and a pos... |
8cff2693-47f4-48ce-81ec-9f854e2c0483 | trentmkelly/LessWrong-43k | LessWrong | AI utility-based correlation
A putative new idea for AI control; index here.
This presents one way of implementing the indifference-based correlations of these posts.
Let u be a utility function, a map from worlds to real numbers. An expected utility maximiser considering whether to produce output Y, looks at the ex... |
1812e375-2f49-4c76-b05a-a10aefc09bf6 | StampyAI/alignment-research-dataset/arbital | Arbital | Methodology of foreseeable difficulties
Much of the current literature about value alignment centers on purported reasons to expect that certain problems will require solution, or be difficult, or be more difficult than some people seem to expect. The subject of this page's approval rating is this practice, considere... |
aa528180-12f9-446d-b550-b6b51ddb0d75 | trentmkelly/LessWrong-43k | LessWrong | Mapping Out Alignment
This week, the key alignment group, we answered two questions, 5-minute timer style:
1. Map out all of alignment (25 minutes)
2. Create an image/ table representing alignment (10 min.)
You are free to stop here, to actually try to answer the questions yourself. Here is a link for a 25 minute ... |
5d4d653e-4a77-4d2c-ad6d-2ac6fcb98871 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Chatbots or set answers, not WBEs
A putative new idea for AI control; index [here](http://lesswrong.com/lw/lt6/newish_ai_control_ideas/).
In a previous post, I talked about using a WBE to define a safe output for a reduced impact AI.
I've realised that the WBE isn't needed. Its only role was to ensure that the AI'... |
3e8fe59c-a759-42cb-9f2a-95d443b34299 | trentmkelly/LessWrong-43k | LessWrong | The Gift We Give Tomorrow, Spoken Word [Finished?]
For reasons that shall remain temporarily mysterious, I wanted a version of the Gift We Give Tomorrow that was designed to be spoken, rather than read. In particular, spoken in a relatively short period of time. It's one of my favorite sequence posts, but when I tried... |
7448cc97-5dc4-454e-8969-3f1879c3131a | trentmkelly/LessWrong-43k | LessWrong | Tachyon neutrinos (again)
In 2012, a large amount of attention was given to the OPERA experiment's apparent sighting of faster than light neutrinos. This turned out to be erroneous due to a faulty cable, and similar experiments confirmed the same results. However, while this was occurring, a distinct point was made: s... |
b2077f2d-1f4c-4572-8270-e4a41b434e3e | trentmkelly/LessWrong-43k | LessWrong | Celtic Knots on a hex lattice
I recently messed about with Celtic knot patterns, for which there are some fun generators online, eg. https://dmackinnon1.github.io/celtic/ or https://w-shadow.com/celtic-knots/. Just as addictive to doodle as the 'cool s' (https://en.wikipedia.org/wiki/Cool_S) but with more cool.
Howev... |
3715fbcd-a92c-4116-8500-0df9388daea5 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Did ChatGPT just gaslight me?
*This post is purely written in my personal capacity, and I do not speak for any organization I am affiliated with.*
*The transcripts below were generated today, November 30th. This was the first exchange I’d had with ChatGPT where I was genuinely trying to see if it could be useful to m... |
98ab494c-2851-49ae-8491-4c8bc377b8e5 | trentmkelly/LessWrong-43k | LessWrong | Gemini modeling
[Metadata: crossposted from https://tsvibt.blogspot.com/2022/08/gemini-modeling.html. First completed 17 June 2022. I'm likely to not respond to comments promptly.]
A gemini model is a kind of model that's especially relevant for minds modeling minds.
Two scenarios
* You stand before a tree. How b... |
fccefda1-be8c-4cb7-8c98-814688e99b79 | trentmkelly/LessWrong-43k | LessWrong | Wireless Outlet Switching
We have lamps in our bedroom, and we were thinking it might be nice to wire up some switchable outlets. Ideally with a three-way switch, one at the doorway and one at our bed. Dimming would be nice too, though not a dealbreaker. This would be quite a lot of work, though, running new wires. An... |
ed722fb1-1b8d-4896-86c7-d3a86b91a1cb | trentmkelly/LessWrong-43k | LessWrong | The Last Number
"...90116633393348054920083..."
He paused for a moment, and licked his recently reconstructed lips. He was nearly there. After seventeen thousand subjective years of effort, he was, finally, just seconds away from the end. He slowed down as the finish line drew into sight, savouring and lengthening th... |
783d093f-b79b-438f-b95b-fc5b595c384a | trentmkelly/LessWrong-43k | LessWrong | My Intuitions on Counterlogical Reasoning
,
Related to: Embedded Decisions.
Epistemic Status
This is the fruit of me thinking on counterlogical reasoning for several minutes. I expect there's nothing revolutionary here, and not much of import, and this post is designed more to help me specify how I think counterlogi... |
2a7e1bb7-d174-46cf-80dc-a02751526cda | trentmkelly/LessWrong-43k | LessWrong | Meetup : San Francisco Meetup: Useful Skill sharing
Discussion article for the meetup : San Francisco Meetup: Useful Skill sharing
WHEN: 16 March 2015 06:15:00PM (-0700)
WHERE: 1061 Market St #4, San Francisco, CA 94103
We'll be meeting to share the most useful skills people have learned, how they're useful, and ho... |
0bead975-72ca-495d-9107-11400b1cea36 | StampyAI/alignment-research-dataset/special_docs | Other | Evaluating models of robust word recognition with serial reproduction.
Cognition 210 (2021) 104553
Available online 19 January 2021
0010-0277/© 2021 Elsevier B.V. All rights reserved.Evaluating models of robust word recognition with serial reproduction
Stephan C. Meylana,*, Sathvik Nairb, Thomas L. Griffithsc
aDepar... |
ee1c6e35-61ee-40bc-8e40-ff1b49335213 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | OpenAI introduces function calling for GPT-4
OpenAI’s latest [update](https://openai.com/blog/function-calling-and-other-api-updates) unlocks function calling for GPT-4 and GPT-3.5 Turbo. This enables developers to "*describe functions to gpt-4-0613 and gpt-3.5-turbo-0613, and have the model intelligently choose to ou... |
7d8da228-61c8-403f-a194-5f8a937e1887 | trentmkelly/LessWrong-43k | LessWrong | Prioritizing Information
So far, we've focused on individual skills involved in a forecast: extrapolating trends, employing reference classes, how to combine estimates, and thinking about alternatives. Next I want to turn to integrating these, and other skills, when making complex forecasts. We'll consider the followi... |
e549f505-e7c4-4beb-8714-0fcdfe41cc77 | trentmkelly/LessWrong-43k | LessWrong | Meetup : LessWrong Meetup August: Correctness Heuristics
Discussion article for the meetup : LessWrong Meetup August: Correctness Heuristics
WHEN: 15 August 2015 07:48:00PM (+0200)
WHERE: Pinakothek der Moderne, Munich
Our next Mostly Monthly Munich Meetup is on August 15.
Please see the announcement on Meetup for... |
9ed74a3e-493d-474d-b239-23952e753cd7 | trentmkelly/LessWrong-43k | LessWrong | The date of AI Takeover is not the day the AI takes over
Instead, it’s the point of no return—the day we AI risk reducers lose the ability to significantly reduce AI risk. This might happen years before classic milestones like “World GWP doubles in four years” and “Superhuman AGI is deployed."
The rest of this post e... |
b9dd2212-418f-4182-8add-6bb7390ca289 | trentmkelly/LessWrong-43k | LessWrong | covid-19 notes, 4/19/20
Brain-dumping some miscellaneous Covid-19 thoughts.
“Mind viruses”
[if you’re skimming, this is the least interesting part of the post IMO]
In late March I wrote this big, long dramatic proclamation about information cascades and stuff.
Back then, it felt like the situation in the US was a... |
5cbb2824-2e44-4fd1-a62c-cfcf8a5a4a37 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Snapshot of narratives and frames against regulating AI
*This is a speculative map of a hot discussion topic. I'm posting it in question form in the hope we can rapidly map the space in answers.*
Looking at various claims at X and at the AI summit, it seems possible to identify some key counter-regulation narrati... |
6f8d4541-7fab-476c-9bae-610a88f673e4 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | (Thought experiment) If you had to choose, which would you prefer?
I don't remember the post's title for a quote, but I believe that in Yudkowsky's [value theory](https://www.lesswrong.com/s/9bvAELWc8y2gYjRav) sequence, he wrote that [most] humans value both subjective experience, and the correspondence of that subjec... |
128c8991-2173-4040-9e23-9db17d190f8a | trentmkelly/LessWrong-43k | LessWrong | Stanford Prison Retrospective
This year is the 40th anniversary of the Stanford Prison Experiment. I found this [retrospective](http://www.stanfordalumni.org/news/magazine/2011/julaug/features/spe.html) interesting. What really caught my eye is that, to some degree, it contradicts the main lesson of the experiment -... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.