id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
53d2ba5d-85ff-49f0-91f1-36949c61ba6d | trentmkelly/LessWrong-43k | LessWrong | How do open AI models affect incentive to race?
I see it said sometimes that open models contribute to AI race dynamics. My guess is that they don't, and if anything, reduce AI race dynamics.
I will consider a simplified model that only takes into account the cost of training a model, not the cost to deploy it (which... |
71069049-5424-4aac-88fb-d9e3b2927ac0 | trentmkelly/LessWrong-43k | LessWrong | Link: Gizmodo discusses SIAI, matches donations
Gizmodo, a popular technology blog, posted this artice about SIAI. It's partly tongue-in-cheek, but also apparently thinks well of the Singularity Institute, claiming they are "a research organization that's as forward-thinking as most Gizmodo readers (read: sci-fi nerds... |
dd8dc258-fd16-43ac-a4ea-bda5dc0d5fde | trentmkelly/LessWrong-43k | LessWrong | Meetup : Less Wrong Ottawa
Discussion article for the meetup : Less Wrong Ottawa
WHEN: 07 July 2011 07:00:07PM (-0400)
WHERE: 283 Elgin Street, Ottawa, ON
Come and meet fellow truth-seekers on the second floor of the Fox and Feather. We'll be in back room #1 if it's free.
Recently we've decided to try discussing o... |
29936238-b6de-404c-878a-fbb4a71a1d8d | trentmkelly/LessWrong-43k | LessWrong | The case for lifelogging as life extension
Those in the cryonics community want to be frozen upon legal death, in order to preserve the information content in their brain. The hope is that, given good protocol, damage incurred during the freezing process will not destroy enough information about you to prevent people ... |
188f2b16-87cf-4f9e-a46a-c1d8f8e9c6e0 | trentmkelly/LessWrong-43k | LessWrong | Announcing Trajectory Labs - A Toronto AI Safety Office
TL;DR
* We’re announcing Trajectory Labs, an AI safety coworking and events space in downtown Toronto.
* We support local AI safety efforts through three core programs:
* Workspace - a shared office space for ~30 AI safety practitioners;
* Events - more-t... |
6205e081-758f-4a5d-bca7-0b69f09da9bc | trentmkelly/LessWrong-43k | LessWrong | Intercellular competition and the inevitability of multicellular aging
|
ca1e4c49-3fbe-435c-88f0-e286b02b56d5 | trentmkelly/LessWrong-43k | LessWrong | Harper’s Fishing Nets: a review of Plato’s Camera by Paul Churchland
Harper’s Fishing Nets: a review of Plato’s Camera by Paul Churchland
Eli Sennesh
July 1, 2015
Abstract
Paul Churchland published Plato’s Camera to defend the thesis that abstract objects and properties are both real and natural, consisting in lear... |
243b8f11-b2bd-464a-b0d2-1e550d7055c7 | trentmkelly/LessWrong-43k | LessWrong | Law-Following AI 2: Intent Alignment + Superintelligence → Lawless AI (By Default)
This post is written in my personal capacity, and does not necessarily represent the views of OpenAI or any other organization. Cross-posted to the Effective Altruism Forum.
In the first post of this sequence, I defined "law-following ... |
16ddb6ec-c13e-4618-b58e-88179393a88e | trentmkelly/LessWrong-43k | LessWrong | Sam Altman's sister claims Sam sexually abused her -- Part 6: Timeline, continued
Previous posts (which you should read first)
This post is the 6th post in a series of 11 posts about the claims of Sam Altman's sister, Annie Altman. Annie has claimed that Sam sexually abused her for about 9 years as a child, and that s... |
1c41f5f8-4bc0-4fc2-bade-c37ef743ccf5 | trentmkelly/LessWrong-43k | LessWrong | The wisdom of the Crowd
I'm looking for people to be part of my facebook group named The wisdom of the of the crowd to help with the initial structure building of the group. developers would be awesome, but if you would like to just be part of the experiment you're welcome too. If there are any of you who are familiar... |
744bf292-7cd8-41e0-9a74-fa325ef38526 | trentmkelly/LessWrong-43k | LessWrong | Moral AI: Options
Epistemic status: One part quotes (informative, accurate), one part speculation (not so accurate).
One avenue towards AI safety is the construction of "moral AI" that is good at solving the problem of human preferences and values. Five FLI grants have recently been funded that pursue different lines... |
ca5aff5b-e521-4015-9132-fbefaee8afc2 | trentmkelly/LessWrong-43k | LessWrong | Measuring Coherence of Policies in Toy Environments
This post was produced as part of the Astra Fellowship under the Winter 2024 Cohort, mentored by Richard Ngo. Thanks to Martín Soto, Jeremy Gillen, Daniel Kokotajlo, and Lukas Berglund for feedback.
Summary
Discussions around the likelihood and threat models of AI ... |
454ae8ef-554e-4098-be00-f1b543149064 | StampyAI/alignment-research-dataset/special_docs | Other | Diminishing Returns and Recursive Self Improving Artificial Intelligence
Chapter 7
Diminishing Returns and Recursive Self
Improving Arti ficial Intelligence
Andrew Majot and Roman Yampolskiy
7.1 Introduction
The concept of a recursively self-improving intelligence has been around for quite a
while (Good 1965 ). At its ... |
00454359-eeab-47f5-93af-12b76b201888 | trentmkelly/LessWrong-43k | LessWrong | Covid-19: My Current Model
The post will be a summary of my current key views on various aspects what is going on, especially in places where I see many or most responsible-looking people getting it importantly wrong.
This post is not making strong evidence-based arguments for these views. This is not that post. This... |
35b4b62f-0d18-48ed-9070-99d2d0ae1711 | trentmkelly/LessWrong-43k | LessWrong | patio11's "Observations from an EA-adjacent (?) charitable effort"
patio11, following up on his longer-form article detailing the story of VaccinateCA (linked on LW) posts some observations of interest to the EA community, with some nods at the rationality community.
> Hiya folks! I'm Patrick McKenzie, better known o... |
a63f69e1-4e92-4c08-b41b-3989015c31c8 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | EIS X: Continual Learning, Modularity, Compression, and Biological Brains
Part 10 of 12 in the [Engineer’s Interpretability Sequence](https://www.alignmentforum.org/s/a6ne2ve5uturEEQK7).
The science of interpretability is part of a larger picture.
============================================================
The prev... |
2f3b36e0-595b-4184-a49d-a2470bf0d6ac | trentmkelly/LessWrong-43k | LessWrong | You will crash your car in front of my house within the next week
I'm not writing this to alarm anyone, but it would be irresponsible not to report on something this important. On current trends, every car will be crashed in front of my house within the next week. Here's the data:
Until today, only two cars had crash... |
976ce6cd-3906-4429-a1d8-7fdb5e7fb384 | trentmkelly/LessWrong-43k | LessWrong | Personalized Medicine For Real
I was part of the founding team at MetaMed, a personalized medicine startup. We went out of business back in 2015. We made a lot of mistakes due to inexperience, some of which I deeply regret.
I’m reflecting on that now, because Perlara just went out of business, and they got a lot fa... |
1c1ee4c5-cc90-4514-bb4c-26df225e24fe | trentmkelly/LessWrong-43k | LessWrong | Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities
This blog was published by Jonathan Ng, Andrey Anurin, Connor Axiotes, Esben Kran.
Apart Research's newest paper, Catastrophic Cyber Capabilities Benchmark (3cb): Robustly Evaluating LLM Agent Cyber Offense Capab... |
2fb1852d-34a0-43a2-9f74-23bfb91e56b5 | trentmkelly/LessWrong-43k | LessWrong | The Overlap Paradigm: Rethinking Data's Role in Weak-to-Strong Generalization (W2SG)
Note: This post summarizes my capstone project for the AI Alignment course by BlueDot Impact. You can learn more about their amazing courses here and consider applying!
Introduction
Recent research in weak-to-strong generalization (... |
86d53aef-f719-43d8-8e03-a36573524a88 | trentmkelly/LessWrong-43k | LessWrong | Discuss: Have you experimented with Pavlovian conditioning?
I want to do some quick-and-dirty productivity hacks, along the lines of this or this. My simplified methodology is something like this: at the end of every 20 minutes of hard-ish labor (like writing Less Wrong posts or taking over African countries), I will ... |
131d1fb8-b64e-4db1-b8d1-74c0f602da94 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | [AN #116]: How to make explanations of neurons compositional
HIGHLIGHTS
==========
**[Compositional Explanations of Neurons](https://arxiv.org/abs/2006.14032)** *(Jesse Mu et al)* (summarized by Robert): Network dissection is an interpretability technique introduced in 2017, which uses a dataset of images with dense ... |
f57e4aa1-7a55-411a-9797-72d1eb913dd7 | trentmkelly/LessWrong-43k | LessWrong | Against Victimhood
Cross-posted, as always, from Putanumonit.
----------------------------------------
I have written many posts in the shape of giving life advice. I hear back from readers who take it and those who refuse it. Either is good — I’m just a guy on the internet, to be consumed as part of a balanced diet... |
49710a03-635c-4d02-929e-692bf6c81b86 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | If you don't design for extrapolation, you'll extrapolate poorly - possibly fatally
.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; wor... |
65aa7f41-dc11-4c72-a0a5-f4d10ec5ff2c | trentmkelly/LessWrong-43k | LessWrong | Harper's Magazine article on LW/MIRI/CFAR and Ethereum
Cover title: “Power and paranoia in Silicon Valley”; article title: “Come with us if you want to live: Among the apocalyptic libertarians of Silicon Valley” (mirrors: 1, 2, 3), by Sam Frank; Harper’s Magazine, January 2015, pg26-36 (~8500 words). The beginning/end... |
cefa5362-ba17-4831-a408-1296d160ab6b | trentmkelly/LessWrong-43k | LessWrong | How much is known about the "inference rules" of logical induction?
Context: Logical Induction is a framework that makes sense of intuitively plausible statements like "the probability that the 10101010th digit of π is odd is about 0.5".
People often do this sort of informal reasoning about mathematical conjectures. ... |
17fc6567-b32a-4820-a2ee-448f0b4fb6b2 | trentmkelly/LessWrong-43k | LessWrong | Which way should we update about uncertain events, over time?
If we're uncertain about the probability of an event x occurring (in virtue of the fact that x has occurred none or just a few times), how should we update our probability of x occurring in the future, in the face of x not occurring over a period of time?
... |
b2b9b988-d480-40a8-9ced-1676ede8f43f | trentmkelly/LessWrong-43k | LessWrong | A Framework For Cognitive Biases: What Types Of Cognitive Biases Are Out There?
|
cddbff1b-b9d4-48d4-949f-668c096a66f7 | trentmkelly/LessWrong-43k | LessWrong | Integral versus differential ethics
In population ethics...
Most people start out believing that the following are true:
1. That adding more happy lives is a net positive.
2. That redistributing happiness more fairly is not a net negative.
3. That the repugnant conclusion is indeed repugnant.
Some will baulk on t... |
fc5fdd05-ac74-402f-acba-fa05c6872a80 | trentmkelly/LessWrong-43k | LessWrong | Solving the Mechanistic Interpretability challenges: EIS VII Challenge 2
We solved* the second Mechanistic Interpretability challenge (Transformer) that Stephen Casper posed in EIS VII. We spent the last Alignment Jam hackathon attempting to solve the two challenges presented there, see here for our solution to the fi... |
536a362a-6457-4eca-ae7c-5006cbe5bc23 | trentmkelly/LessWrong-43k | LessWrong | Overhead of MessageChannel
The Channel Messaging API gives you a way to pass information asynchronously between different origins on the web, such as cross-origin iframes. Traditionally you would use window.postMessage(), but the a MessageChannel has the advantage of being clearer, only requiring validating origins on... |
ff5db145-add1-4b6d-896b-d9c08344e6da | trentmkelly/LessWrong-43k | LessWrong | Reading recommendations on social technology: looking for the third way between technocracy and populism
I broadly see the situation as follows
populism is the failure mode that I can characterize as the two wolves and a sheep problem (voting on what's for dinner), adversarial dynamics between majorities and minoriti... |
639bab2d-7f2d-4c31-aa3f-d6f5422dbeac | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Fermi estimation of the impact you might have working on AI safety
I tried doing a Fermi estimation of the impact I would have if I worked on AI safety, and I realized it wasn't easy to do with only a calculator. So I build a website which does this Fermi estimation given your beliefs about AGI, AI safety, and your im... |
36b82552-ffd8-41e8-9883-76032bdccabc | trentmkelly/LessWrong-43k | LessWrong | Making decisions in a real computer - an argument for meta-decision theory research
Decision theory is being used as the basis for AI safety work. This currently involves maximising expected utility of specific actions. Maximising expected utility is woefully inefficient for performing very rapid paced unimportant dec... |
d6b85d99-524f-4db4-a573-68f89c619e85 | trentmkelly/LessWrong-43k | LessWrong | Call for Personal Volunteers
Those who wish to volunteer some of their time toward reducing existential risk and increasing our chances of a positive singularity can follow the directions on SingularityVolunteers.org.
And as a freshly hired Singularity Institute researcher, I also have my own list of tasks that, if c... |
6ec0b5b1-a1e9-41e0-a066-a6685cc1617f | trentmkelly/LessWrong-43k | LessWrong | Can the House Legislate?
The US government is in a less functional position than usual:
* Legislation requires (among other things) a plurality vote of the House of Representatives.
* This requires the Speaker of the House to call a vote.
* This requires a Speaker of the House.
* The House removed its Speake... |
68b37d32-d6e9-4c9a-befa-284b60097120 | trentmkelly/LessWrong-43k | LessWrong | Rationality Quotes: May 2011
WARNING WARNING YE HAIRY GODS THIS IS A WARNING:
This is not the proper quotes thread for this month. The correct page is here. Sorry about the confusion!
I will leave this post up for a day or so to let the few people who've already posted here move their quotes over, then I'll delete i... |
0fca9593-8f13-445d-ad06-d36cffe7e78f | trentmkelly/LessWrong-43k | LessWrong | What are your favorite posts, podcast episodes, and recorded talks, on AI timelines, or factors that would influence AI timelines?
Especially ones that do an attempt to make things pretty specific |
9c12e066-1cd1-49dc-b09a-3d06189baa9e | trentmkelly/LessWrong-43k | LessWrong | Examples of Causal Abstraction
I’m working on a theory of abstraction suitable as a foundation for embedded agency and specifically multi-level world models. I want to use real-world examples to build a fast feedback loop for theory development, so a natural first step is to build a starting list of examples which cap... |
d8b17132-de8f-4f03-8775-2eb2c27e5674 | trentmkelly/LessWrong-43k | LessWrong | The Politics of Age (the Young vs. the Old)
Few days ago I've read an article in the local newspaper about Switzerland considering to lower the voting age to 16.
The reason I found it interesting was that it was not one of the old tired political discussions supported by the same old tired arguments that you typicall... |
18adbccd-5ce6-4f66-915c-687a63e0aa30 | trentmkelly/LessWrong-43k | LessWrong | Shock Levels are Point Estimates
This is a post from my blog, Space and Games. Michael Vassar has requested that I repost it here. I thought about revising it to remove the mind projection fallacy, but instead I left it in for you to find.
Eliezer Yudkowsky1999 famously categorized beliefs about the future into discr... |
54582fbb-7898-4e30-a5a0-1067caf25ce4 | StampyAI/alignment-research-dataset/blogs | Blogs | Wolf Kohn on hybrid systems control
 [Dr. Wolf Kohn](http://depts.washington.edu/ie/people/kohn) is the Chief Scientist at [Atigeo, LLC](http://atigeo.com/), and a Research Professor in Industrial and Systems Engineering at the Uni... |
8d13dfff-e2a8-4ad0-9f73-51c2cfb1d0f1 | trentmkelly/LessWrong-43k | LessWrong | Notes on Psychopathy
> This is some old work I did for SI. See also Notes on the Psychology of Power.
Deviant but not necessarily diseased or dysfunctional minds can demonstrate resistance to all treatment and attempts to change their mind (think No Universally Compelling Arguments; the premier example are probably p... |
589fe945-adf0-4db3-a548-1c0bd29059a0 | trentmkelly/LessWrong-43k | LessWrong | Nerve Blisters: A Stoic Response
The chickenpox virus waited for decades, attacking the moment my immune system wobbled.[1] It advanced down my nerves, spreading blisters along its path. Known as shingles, this kind of viral attack is generally considered a very bad time.
The blisters make nerves go haywire. They sta... |
b44a9d2e-42a3-41b7-b222-4f9f1c89071b | trentmkelly/LessWrong-43k | LessWrong | Open thread, 25-31 August 2014
Previous open thread
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.
3. Open Threads should be posted i... |
d35a6177-b9d0-4916-8a3b-93e3322e254f | trentmkelly/LessWrong-43k | LessWrong | Don't Influence the Influencers!
This post was written under Evan Hubinger’s direct guidance and mentorship, as a part of the Stanford Existential Risks Institute ML Alignment Theory Scholars (MATS) program.
TL;DR: AGI is likely to turn out unsafe. One likely way that can happen is that it fools us into thinking it i... |
ff543624-3f5b-49e8-9db6-ac7a26e9723c | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Trace README
Trace is a tool for writing programs which read, write and reason about programs.
You can find it [here](https://github.com/johnswentworth/tracelang). I wrote it as a tool for my own research, and I expect that others in this space may find the ideas interesting/useful as well. I'd be especially intereste... |
741502de-74a9-4f95-8731-4f80be66519d | trentmkelly/LessWrong-43k | LessWrong | Civility Is Never Neutral
[Crossposted from my blog with minor edits, mostly to get rid of culture war stuff.]
There are a lot of people I know who say something like “the free market of ideas is really important and we need to seek truth. It’s important to let everyone have their fair say and share the evidence that... |
1186a9d0-7a78-4d97-8199-6c789e290315 | trentmkelly/LessWrong-43k | LessWrong | Another Calming Example
In reading about parenting I often feel like there's a bit too much theory vs examples, so here's walking through a recent interaction that others later commented went surprisingly well.
At a recent Tuesday Family Dinner, one of the kids (~6y) served themself an absurd amount of pasta. They we... |
eaf4e7c3-e369-48d5-996c-d4f44aee5fdc | trentmkelly/LessWrong-43k | LessWrong | Double Illusion of Transparency
Followup to: Explainers Shoot High, Illusion of Transparency
My first true foray into Bayes For Everyone was writing An Intuitive Explanation of Bayesian Reasoning, still one of my most popular works. This is the Intuitive Explanation's origin story.
In December of 2002, I'd been se... |
61983a36-bbf2-436d-9668-6caa4f5be77c | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | 257. Where I agree and Disagree with Eliezer 3
hello and welcome to session 257 in the
AI safety.com reading group tonight
we'll be finishing up where I agree and
disagree with Elisa by Paul Cristiano
there
um Paul Cristiano is still a researcher
in in the alignment Research Center and
hold on
um and this is uh starti... |
c3b05143-5599-4713-872a-8b96da69fb70 | trentmkelly/LessWrong-43k | LessWrong | Rationality Dojo
Last night, here in Portland (OR), some friends and I got together to try to start Rationality Dojo. We talked about it for a while and came up with exactly 4 exercises that we could readily practice:
1. Play Paranoid Debating
2. Play the AI-Box experiment
3. Read Harry Potter and the Methods of R... |
f6d87b88-8e02-4acc-8e21-91b0ec16b11d | StampyAI/alignment-research-dataset/arxiv | Arxiv | Quantifying Local Specialization in Deep Neural Networks
1 Introduction
---------------
Modularity is a common property of complex systems, both natural and artificial (Clune et al., [2013](#bib.bib53 "The evolutionary origins of modularity"); Baldwin and Clark, [2000](#bib.bib54 "Design rules: the power of modular... |
ac3290f5-de58-4e47-994b-43a3c23e9cf7 | StampyAI/alignment-research-dataset/arbital | Arbital | Other-izing (wanted: new optimization idiom)
The open "other-izer" problem is to find something besides maximizing, satisificing, meliorizing, and several other existing but unsatisfactory idioms, which is actually suitable as an optimization idiom for [bounded agents](https://arbital.com/p/bounded_agent) and is [refl... |
7dba044f-a53e-4e54-b79e-079a35a35007 | trentmkelly/LessWrong-43k | LessWrong | Tap Water and Filtration
I've been wondering about the safety and quality of the tap water in my city. I've always been assured that it's clean right out the tap. But I spent this past year living rurally with a groundwater well on-site, and when I visited the city I was struck by how bad the tap water tasted to me.
... |
1a42c16f-3cf5-49ae-bb9b-4e7bc9e1e21f | StampyAI/alignment-research-dataset/arxiv | Arxiv | A Composable Specification Language for Reinforcement Learning Tasks
1 Introduction
---------------
Reinforcement learning (RL) is a promising approach to learning control policies for robotics tasks Collins et al. ([2005](#bib.bib6 "Efficient bipedal robots based on passive-dynamic walkers")); Silver et al. ([2014... |
be8d0b9f-923c-40ae-b21b-544618fdf6d8 | trentmkelly/LessWrong-43k | LessWrong | Crash problems for total futarchy
Futarchy holds great promise for dealing with all the morass of poor decision making in our governments and corporations. For those who haven't heard of it, the main concept is to use betting markets, where people place bets on the expected outcome of a policy, and the decision-makers... |
e3b8a3c5-372a-4f83-964e-3dddb90a3b44 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Language Agents Reduce the Risk of Existential Catastrophe
*This post was written by* [*Simon Goldstein*](https://www.simondgoldstein.com/)*, associate professor at the Dianoia Institute of Philosophy at ACU, and* [*Cameron Domenico Kirk-Giannini*](http://www.cd.kg/)*, assistant professor at Rutgers University, for su... |
cb91e81f-8f31-4cb2-b697-866e30d24df3 | trentmkelly/LessWrong-43k | LessWrong | The dangers of dialectic
I'm reading The Last Intellectuals: American culture in the age of academe by Russell Jacoby (1987). It contains many interesting and important observations and insights, but also much stupidity. By the last chapter, I was as interested in the question of how a person can be so smart and stupi... |
e3954c9d-3ced-4477-9cbb-cea004c91fb4 | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post2716
Epistemic status: speculative brainstorming. Follow-up to this post on AGIs as collectives . Note that I've changed the term population AGI to collective AGI for consistency with Bostrom's use in Superintelligence . One safety measure we might want to use on AGIs is (sand)boxing: limiting their access to ... |
109fa129-b4ef-4fa9-a3ce-1fcacdde9a87 | trentmkelly/LessWrong-43k | LessWrong | Defining a limited satisficer
A putative new idea for AI control; index here.
EDIT: The definition of satisficer I'm using here is the informal one of "it tries to achieve a goal, without making huge changes on the universe" rather than "it's an agent that has utility u and threshold t". If you prefer the standard no... |
2885eaef-331f-4589-8b0e-182b799e8ae4 | trentmkelly/LessWrong-43k | LessWrong | Approaching Infinity
[This is from a very neat example my real analysis professor used some years ago. While I'm fairly confident it's neat, I'm not certain it's top-level-post-worthy. The general point is about problems with applying concepts involving infinity to reality; any advice on content (or formatting!) would... |
785c5446-70f8-47b6-83ce-1eace28c910b | trentmkelly/LessWrong-43k | LessWrong | New paper: Long-Term Trajectories of Human Civilization
Long-Term Trajectories of Human Civilization (free PDF). Foresight, forthcoming, DOI 10.1108/FS-04-2018-0037.
Authors: Seth D. Baum, Stuart Armstrong, Timoteus Ekenstedt, Olle Häggström, Robin Hanson, Karin Kuhlemann, Matthijs M. Maas, James D. Miller, Markus Sa... |
811b0dd1-f7ac-4a3d-b011-72ec78343f9d | trentmkelly/LessWrong-43k | LessWrong | [LINK] Slashdot interview with David Ettinger of the Cryonics Institute
http://science.slashdot.org/story/13/08/19/1834210/the-cryonics-institute-offers-a-chance-at-immortality-video |
e73ff99f-c9d9-492e-a7fd-4d518883d732 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Modelling Continuous Progress
I [have previously argued](https://www.alignmentforum.org/posts/5WECpYABCT62TJrhY/will-ai-undergo-discontinuous-progress) for two claims about AI takeoff speeds. First, almost everyone agrees that if we had AGI, progress would be very fast. Second, the major disagreement is between those ... |
3e98fd3e-725a-4c2a-9222-8ea858b0394c | trentmkelly/LessWrong-43k | LessWrong | A Disciplined Way to Avoid Wireheading
This is a crosspost of a post from my blog, Metal Ivy. The original is here: A Disciplined Way To Avoid Wireheading.
What is wireheading?
The term wireheading comes from the observation that if you put a wire in someone’s brain such that it is near their brain’s pleasure (or cr... |
11e685f9-c562-40b3-b69a-853e4a9f586e | trentmkelly/LessWrong-43k | LessWrong | (misleading title removed)
An article by AAAI president Tom Dietterich and Director of Microsoft Research Eric Horvitz has recently got some media attention (BBC, etc) downplaying AI existential risks. You can go read it yourself, but the key paragraph is this:
> A third set of risks echo the tale of the Sorcerer... |
06e4e828-3e2d-4f83-919d-e5a7edd510dd | StampyAI/alignment-research-dataset/blogs | Blogs | Making or breaking a thinking machine
*By Katja Grace, 18 January 2015*
Here is a superficially plausible argument: the brains of the slowest humans are almost identical to those of the smartest humans. And thus—in the great space of possible intelligence—the ‘human-level’ band must be very narrow. Since all humans ... |
22fea1fa-d1d6-413b-9410-779fa29db4e0 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Edit: contest closed now, will start assessing the entries.
The contest
I'm offering $1,000 for good questions to ask of AI Oracles. Good questions are those that are safe and useful: that allows us to get information out of the Oracle without increasing risk.
To enter, put your suggestion in the comments below. The c... |
01687299-523e-4281-8de9-e0728f482783 | trentmkelly/LessWrong-43k | LessWrong | Why are people unkeen to immortality that would come from technological advancements and/or AI?
Nearly everyone with whom I have talked about the mindblowing possibilities of a friendly ASI -people that hadn't heard about it before-, I have seen the same reaction: the person is skeptical and rejects the idea of immort... |
125d5e50-3cd0-478f-b237-9d08499d6d1c | trentmkelly/LessWrong-43k | LessWrong | CogSci books
Cognitive psych is ovbiously important to people here, so I want to point out a CogSci book thread over from reddit/r/cogsci.
http://www.reddit.com/r/cogsci/comments/bmbaq/dear_rcogsci_lets_construct_a_musthave_library_of/
I would be interested in an extension of this thread here, since LW has somewhat ... |
0a4cefae-66f6-4774-bb7d-2156f3621d43 | trentmkelly/LessWrong-43k | LessWrong | Newcomb's Grandfather
In front of you are two boxes.
Box A contains $1000.
If Omega predicted you would just take Box B, Box B contains $1,000,000.
If Omega predicted you would take both boxes, Box B contains nothing. Omega will also go back in time and kill your grandfather.
Nobody has any idea how accurate Omega... |
e946af43-bd8d-40c8-96a2-d4751f58937b | trentmkelly/LessWrong-43k | LessWrong | Recent Less Wrong downtime
Many users may have noticed that Less Wrong experienced about 6 hours of downtime on 16/7/2011.
CAUSE: The server was put under an unusual amount of load and started up a new instance to load-balance the traffic. Unfortunately, there was a bug in the script that starts the new instance tha... |
bface2f1-2593-45eb-8dd6-3bb732304f1d | StampyAI/alignment-research-dataset/arbital | Arbital | Conceivability
A hypothetical scenario is 'conceivable' or 'imaginable' when it is not *immediately* incoherent, although it may still contain some subtle flaw that makes it [logically impossible](https://arbital.com/p/). If you haven't yet checked for factors, it's conceivable to you that 91 is either a [prime numbe... |
93d54744-8520-4cce-adce-806a1425639c | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Epistemic status: fairly confident based on my accumulated experience of debates and disagreements. I wrote this for myself as much as others.There is a conversational dynamic which I think is extremely common, a failure mode which is all too easy to fall into. Alice and Bob are debating some course of action, e.g. sh... |
134c4ba8-36f2-44be-882c-668edfb4d782 | trentmkelly/LessWrong-43k | LessWrong | What's the simplest concrete unsolved problem in AI alignment?
In your preferred area of AI alignment, what is the simplest concrete unsolved problem?
By "simplest", ideally the problem has been solved when any of the conditions are weakened. However, this isn't always possible, so a simpler solved version of the pro... |
993beb59-b54f-4ce5-9b51-ff2de3d436fd | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Catastrophic Regressional Goodhart: Appendix
This is a more technical followup to the [last post](https://www.lesswrong.com/posts/fuSaKr6t6Zuh6GKaQ/when-is-goodhart-catastrophic), putting precise bounds on when regressional Goodhart leads to failure or not. We'll first show conditions under which optimization for a pr... |
0d86cf26-1566-49d6-80c7-5dea84a555c0 | trentmkelly/LessWrong-43k | LessWrong | Open thread, Aug. 10 - Aug. 16, 2015
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... |
8446b928-84c0-4ab6-bd46-b4673faf4f62 | trentmkelly/LessWrong-43k | LessWrong | Open Thread: August 2009
Here's our place to discuss Less Wrong topics that have not appeared in recent posts. If something gets a lot of discussion feel free to convert it into an independent post. |
671e0f80-b7a4-4181-a3a2-09a0961ad1c7 | trentmkelly/LessWrong-43k | LessWrong | Retracting on Facebook
Sometimes I'm in a Facebook discussion and someone says something they wish they hadn't. Maybe it turns out to be wrong, or misleading, or insensitive. One way I've seen this poorly handled is posting a follow-up comment:
The problem is that the top-level post is still there, and Facebook wil... |
3fe1b708-1ca9-4201-ba0f-178085bb3850 | trentmkelly/LessWrong-43k | LessWrong | Ubiquitous Far-Ultraviolet Light Could Control the Spread of Covid-19 and Other Pandemics
Roko Mijic, Alexey Turchin
Epistemic status: Many different uncertainties here, but the idea has some good evidence in favor of it and a high potential payoff.
Tl;dr: We should urgently investigate putting special human-safe Fa... |
12eb65a5-8e12-48a9-a500-938aa7160ce7 | trentmkelly/LessWrong-43k | LessWrong | [Book Review] Evolution of Sex
I was prompted to write this book review after reading Paul Christiano’s post on the evolution of sex and George’s response to Paul Christiano’s post on the evolution of sex. Those two posts are quite interesting! Paul Christiano points out that “sex slightly lowers the average [fitness]... |
bd756091-a00f-475f-a02b-8df351974ecb | trentmkelly/LessWrong-43k | LessWrong | Age gaps and Birth order: Failed reproduction of results
Summary
I attempted to reproduce Scott’s analysis of Birth order effect vs Age gap. I found that:
1. There appeared to be an error in graphs 2 & 3 where people with one sibling were counted when they shouldn’t have been (graph 2) or were counted twice (graph 3)... |
d935b8cb-4e91-4dca-a61a-2696c81b8988 | trentmkelly/LessWrong-43k | LessWrong | How More Knowledge is Making Us Dumber
This essay was originally published on my website.
The 21st century da Vinci will be a billionaire who combines science and business seamlessly. He is also a master of the latest technology, creating the most surprising companies that look like masterpieces. The 21st century Mon... |
b4579c0e-d7b1-49c5-a2dc-72301e6d9112 | StampyAI/alignment-research-dataset/blogs | Blogs | Price performance Moore’s Law seems slow
*By Katja Grace, 26 November 2017*
When people make predictions about AI, they often assume that computing hardware will carry on getting cheaper for the foreseeable future, at about the same rate that it usually does. Since this is such a common premise, and whether reality ... |
4b9b6376-eb22-4c4f-b52c-43fa8705b300 | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post1647
This post is part of my hypothesis subspace sequence, a living collection of proposals I'm exploring at Refine. Followed by ideological inference engines . Thanks Adam Shimi for advice on putting more legible content out there. Thanks Eric Winsor, Leo Grinsztajn, Linda Linsefors, Lucas Texeira, Tammy Leak... |
ed1900e9-a4a0-4a62-ae04-2e0e26139694 | trentmkelly/LessWrong-43k | LessWrong | Competent Preferences
I - Obvious answers to obvious questions
"Why do I think I know what I do about Goodhart's law?"
There's an obvious answer (or at least an obvious outer layer of the answer-onion): we use Goodhart's law because we usually model humans as if we have values. Not necessarily True Values over the w... |
12662f26-bc94-4cfa-8757-85b9930a9cf5 | trentmkelly/LessWrong-43k | LessWrong | AGI-2011 conference videos
Google tech talks published a bunch of video from AGI (Artificial General Intelligence) 2011 today, they're all linked from the conference site. I haven't watched any of them yet but the titles sound interesting.
http://agi-conf.org/2011/conference-schedule/#vp
(Via Patrick Hahn @OB-NYC.) |
07053c97-c073-4f32-a51e-449f72bfd5a6 | trentmkelly/LessWrong-43k | LessWrong | But Butter Goes Rancid In The Freezer
I broached the subject of cryonics with a family member today. He offered almost none of the normal objections and I've been happy all day about the way the conversation went. One interesting issue that he raised that I'd like to find an answer for is the question in the title.
... |
c8ce4356-621b-4a03-b489-5d0066740418 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Morality is Scary
I'm worried that many AI alignment researchers and other LWers have a view of how human morality works, that really only applies to a small fraction of all humans (notably moral philosophers and themselves). In this view, people know or at least suspect that they are confused about morality, and are ... |
d66c3a0c-0647-414b-97e1-2174cb50446d | trentmkelly/LessWrong-43k | LessWrong | Concepts Don't Work That Way
Part of the sequence: Rationality and Philosophy
Philosophy in the Flesh, by George Lakoff and Mark Johnson, opens with a bang:
> The mind is inherently embodied. Thought is mostly unconscious. Abstract concepts are largely metaphorical.
>
> These are three major findings of cognitive s... |
412f9274-3bc7-47d9-b392-8e567fac7a6f | trentmkelly/LessWrong-43k | LessWrong | A critical agential account of free will, causation, and physics
This is an account of free choice in a physical universe. It is very much relevant to decision theory and philosophy of science. It is largely metaphysical, in terms of taking certain things to be basically real and examining what can be defined in terms... |
de4d0b66-1ea1-41a3-994a-e899b6d32690 | trentmkelly/LessWrong-43k | LessWrong | Fascists and Rakes
Cross-posted from my blog
It feels like most people have a moral intuition along the lines of "you should let people do what they want, unless they're hurting other people". We follow this guideline, and we expect other people to follow it. I'll call this the permissiveness principle, that behaviou... |
161b9233-8500-4c85-a4c1-b78882b419e6 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Problems of people new to AI safety and my project ideas to mitigate them
### TL DR
I talked to people who got interested in AI safety recently to discuss their problems. The interviewees reported that the field is hard to navigate for those who start their way into it. It is also hard to advance a career after the i... |
1603a15b-b32a-48ee-9645-1fee93116f9e | trentmkelly/LessWrong-43k | LessWrong | Unnecessary Boredom Bias
Crossposted from my own blog FunctionalNoise
Boredom has felt like an enemy to me for a long time. When I am bored it seems like I am wasting my time, being useless and inefficient and meaningless. I hate being bored and I've tried fighting boredom, avoiding boredom and ignoring boredom. But ... |
49c1150f-2d3c-4397-bac9-762383a5c117 | trentmkelly/LessWrong-43k | LessWrong | so you have a chronic health issue
(dump of highish agency ideas to suffer less)
Disclaimer: Not medical advice, don’t be stupid. Possibly only applicable to bio autists (gf wants me to impress that unless you know enough about bio you should not do this!!). This post does NOT recommend trying anything illegal.
Note... |
66a1aaaf-c64c-4969-833e-1fdd04efece0 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions.
1 Introduction
---------------
When artificial intelligence was first studied in the 1950s, researchers have sought to find the solution to the question “How to build an agent with perfect rationality". The term “perfect rationality" ([carna... |
017d3190-2fb0-4058-ab26-1e351c8a9f6f | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Term/Category for AI with Neutral Impact?
Is there any commonly known term on LessWrong to describe an AGI that does not significantly increase or decrease human value? (For instance, an AGI that stops all future attempts to build AGI, but otherwise tries to preserve the course of human history as if it had never exis... |
89c63423-71b0-431d-b8c7-d531aa817a36 | trentmkelly/LessWrong-43k | LessWrong | Comments on "AI 2027"
I find the decision to brand the forecast as "AI 2027" very odd. The authors do not in fact believe this; they explicitly give 2028, 2030, or 2033 for their median dates for a superhuman coder.
The point of this project was presumably to warn about a possible outcome; by the authors' own beliefs... |
b0daddf7-af8b-48c8-b687-66b28aa7a2db | trentmkelly/LessWrong-43k | LessWrong | Spay or Neuter Your Irrationalities
No human person has, so far as I am aware, managed to eradicate all irrationalities from their thinking. They are unavoidable, and this is particularly distressing when the irrationalities are lurking in your brain like rats in the walls and you don't know what they are. Of course... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.