id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
0cb13b61-33d7-495b-a6a5-3dd6416ce164 | trentmkelly/LessWrong-43k | LessWrong | Diseased disciplines: the strange case of the inverted chart
Imagine the following situation: you have come across numerous references to a paper purporting to show that the chances of successfully treating a disease contracted at age 10 are substantially lower if the disease is detected later: somewhat lower at age 2... |
0eddf5d7-adb9-4ce6-addd-4c483c94d055 | trentmkelly/LessWrong-43k | LessWrong | Intent alignment should not be the goal for AGI x-risk reduction
> P(misalignment x-risk | AGI) is high.
Intent alignment should not be the goal for AGI x-risk reduction. If AGI is developed, and we solve AGI intent alignment, we will not have lowered x-risk sufficiently, and we may have even increased it higher th... |
d1578155-3d5b-4cff-b37f-33293f9f5a08 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | What exactly is GPT-3's base objective?
*[Probably a noob question]*
I'm thinking about what an inner alignment failure might look like for GPT-3. This would have to involve some deployment context in which GPT-3 performs significantly worse (by the standards of the base objective) than it did in training. (It would ... |
603d1220-b5f6-48b9-9533-058381e9c04a | trentmkelly/LessWrong-43k | LessWrong | Matching game
Have you have read the overview of this blog? If so, I would be pleased if you would tell me which of the following styles of thought you think closest to that manifested in it:
Take Our Poll
|
3df266d7-6f53-4ceb-88de-70585c1c6c0b | trentmkelly/LessWrong-43k | LessWrong | Sazen
Purpose of post: describe and (hopefully) popularize a concept I've found highly useful.
----------------------------------------
Last year, my partner Logan Strohl wrote a sequence to introduce the "naturalism" concept they've been developing and teaching for the past decade or so.
That sequence was structur... |
92a22f23-3cec-4b09-9d62-5aea8a6b3569 | StampyAI/alignment-research-dataset/arbital | Arbital | Lattice (Order Theory)
A **lattice** is a [https://arbital.com/p/-3rb](https://arbital.com/p/-3rb) that is closed under binary [joins and meets](https://arbital.com/p/3rc).
Let $L$ be a lattice. Then for all $p,q,r \in L$ the following properties are necessarily satisfied.
* [Associativity](https://arbital.com/p/3h... |
6b0bd126-2a22-4bb7-974b-f6696071f0b3 | StampyAI/alignment-research-dataset/special_docs | Other | Mapping the AI Investment Activities of Top Global Defense Companies
October 2021
Mapping the AI Investment
Activities of Top Global
Defense Companies
CSET Issue Brief
AUTHOR S
Ngor Luong
Rebecca Gelles
Melissa Flagg
Center for Security and Emerging Technology | 1 Executive Summary
As a dual -use techno... |
9052a8a3-415a-44e1-ba97-bf0074332197 | StampyAI/alignment-research-dataset/arxiv | Arxiv | CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery
1 Introduction
---------------
Figure 1: This work deals with unsupervised skill discovery through mutual information maximization. We introduce Contrastive Intrinsic Control (CIC) – a new u... |
7e040b78-19a7-487c-814b-5ad8f5692818 | trentmkelly/LessWrong-43k | LessWrong | Finland Museum Tour 1/??: Tampere Art Museum
I haven’t really been to museums as an adult; not because I’d have been particularly Anti-Museum, but just because museums never happened to become a Thing That I Do. I vaguely recall having been to a few museums with my parents when I was little, an occasional Japan exhibi... |
c19ca966-fe06-4751-a4e4-39b2b2a738b3 | trentmkelly/LessWrong-43k | LessWrong | Overcoming the Curse of Knowledge
[crossposted at Measure of Doubt]
What is the Curse of Knowledge, and how does it apply to science education, persuasion, and communication? No, it's not a reference to the Garden of Eden story. I'm referring to a particular psychological phenomenon that can make our messages backf... |
ac000173-d3f4-4bd4-86dc-aea80245180b | trentmkelly/LessWrong-43k | LessWrong | AI alignment researchers may have a comparative advantage in reducing s-risks
I believe AI alignment researchers might be uniquely well-positioned to make a difference to s-risks. In particular, I think this of alignment researchers with a keen interest in “macrostrategy.” By that, I mean ones who habitually engage in... |
f57400d2-ba60-4ad1-aedd-aead6eb15bfe | trentmkelly/LessWrong-43k | LessWrong | Blinded by Insight
Insight is often dangerous to the intellect because we may be so captivated by what we have discovered that we take it too far or bundle it with other falsehoods. We can be so focused on the strength behind this nugget of wisdom, that we fail to realise other claims sneaking their way in there.
Exa... |
7cab6038-0105-4986-895f-7aadfb0f42d6 | trentmkelly/LessWrong-43k | LessWrong | Future of Moral Machines - New York Times [link]
http://opinionator.blogs.nytimes.com/2011/12/25/the-future-of-moral-machines/ |
a1374b5d-ff01-40c8-89e7-25dc9a9b676c | StampyAI/alignment-research-dataset/arxiv | Arxiv | Challenges of Context and Time in Reinforcement Learning: Introducing Space Fortress as a Benchmark
1 Introduction
---------------
Recentadvancesincomputervision[[Krizhevsky,Sutskever,andHinton2012](#bib.bibx13)]andnaturallanguageprocessing[[Sutskever,Vinyals,andLe2014](#bib.bibx27)]canbeattributedtotheadventofdeep... |
bd23232b-4ed1-4257-97b6-c30c4465c136 | trentmkelly/LessWrong-43k | LessWrong | Workshop (hackathon, residence program, etc.) about for-profit AI Safety projects?
Reading posts like "This might be the last AI Safety Camp" makes me feel very sad. The degree to which AI Safety is currently funding-constrained is clearly inadequate on the national and civilisational levels.
Maybe let's try to make ... |
6e10671c-de93-4084-9ea5-a53df21a6894 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Melbourne Social Meetup: August
Discussion article for the meetup : Melbourne Social Meetup: August
WHEN: 19 August 2016 06:30:00PM (+1000)
WHERE: Bull & Bear Tavern, 347 Flinders Lane, Melbourne, Australia 3000
This month's Social Meetup is on as scheduled!
Facebook event page: https://www.facebook.com/e... |
4f02d698-4076-4338-960e-f11502c471c0 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Misalignment and misuse: whose values are manifest?
*Crossposted from [world spirit sock puppet](https://worldspiritsockpuppet.com/meteuphoric.html).*
AI related disasters are often categorized as involving misaligned AI, or misuse, or accident. Where:
* misuse means the bad outcomes were wanted by the people invo... |
54a3f509-cd77-429f-8588-8e64e94776f5 | trentmkelly/LessWrong-43k | LessWrong | Will the ems save us from the robots?
At the FHI, we are currently working on a project around whole brain emulations (WBE), or uploads. One important question is if getting to whole brain emulations first would make subsequent AGI creation
1. more or less likely to happen,
2. more or less likely to be survivable.
... |
88495308-70fb-4792-8395-2908bbe42e9e | trentmkelly/LessWrong-43k | LessWrong | Open Thread, November 23-30, 2013
If it's worth saying, but not worth its own post (even in Discussion), then it goes here. |
a62974c0-392b-499a-b666-96453ca31f19 | trentmkelly/LessWrong-43k | LessWrong | The Sanity Waterline Bulges at the Middle
Ideas have consequences. A subset of ideas — we’ll call it ideology — has consequences on material life. Naturally, this means that ideology is subject to a selective pressure.
Which means we need to consider slack. Just as with intermediary adaptions in the stylized case of ... |
35588a4a-6257-4a68-82d8-81b4b48de9bb | trentmkelly/LessWrong-43k | LessWrong | Reframing the evolutionary benefit of sex
Automatically crossposted from https://sideways-view.com
From the perspective of an organism trying to propagate its genes, sex is like a trade: I’ll put half of your DNA in my offspring if you put half of my DNA in yours. I still pass one copy of my genes onto the next gener... |
1b21ada2-3f85-4e34-864c-a416028d0efe | trentmkelly/LessWrong-43k | LessWrong | Introduction to Local Interpretable Model-Agnostic Explanations (LIME)
|
d7a864fb-4703-41b5-9a91-e52efb264c82 | trentmkelly/LessWrong-43k | LessWrong | Generalization, from thermodynamics to statistical physics
Summary
In 2018, Zhang et al. showed that deep neural networks can achieve perfect training loss on randomly labeled data.
This was a Big Deal.
It meant that existing generalization theory couldn't explain why deep neural networks generalize. That's because ... |
b180af43-deab-4b62-b43b-de2d17966367 | trentmkelly/LessWrong-43k | LessWrong | Book Summary: Consciousness and the Brain
One of the fundamental building blocks of much of consciousness research, is that of Global Workspace Theory (GWT). One elaboration of GWT, which focuses on how it might be implemented in the brain, is the Global Neuronal Workspace (GNW) model in neuroscience. Consciousness an... |
0ab3a71e-76b2-4848-b290-afb25993d696 | trentmkelly/LessWrong-43k | LessWrong | Friendlier AI through politics
David Brin suggests that some kind of political system populated with humans and diverse but imperfectly rational and friendly AIs would evolve in a satisfactory direction for humans.
I don't know whether creating an imperfectly rational general AI is any easier, except that limited per... |
70c4d2a4-10fd-43ee-8232-8b418b0b67b3 | trentmkelly/LessWrong-43k | LessWrong | Radical Probabilism
This is an expanded version of my talk. I assume a high degree of familiarity with Bayesian probability theory.
Toward a New Technical Explanation of Technical Explanation -- an attempt to convey the practical implications of logical induction -- was one of my most-appreciated posts, but I don't r... |
24aeaba6-19d7-45be-832c-aa48d14ef7f9 | trentmkelly/LessWrong-43k | LessWrong | Antidepressant Pharmacogenomics: Much More Than You Wanted To Know
[Epistemic status: very uncertain. Not to be taken as medical advice. Talk to your doctor before deciding whether or not to get any tests.]
I.
There are many antidepressants in common use. With a few exceptions, none are globally better than any othe... |
8b74b1ea-6117-4a6d-8f2f-f6b9dd80554f | trentmkelly/LessWrong-43k | LessWrong | The AI Agent Revolution: Beyond the Hype of 2025
A deep dive into the transformative potential of AI agents and the emergence of new economic paradigms
Introduction: The Dawn of Ambient Intelligence
Imagine stepping into your kitchen and finding your smart fridge not just restocking your groceries, but negotiating c... |
58e461e6-840f-44fc-8af3-e43383121359 | trentmkelly/LessWrong-43k | LessWrong | MATS Spring 2024 Extension Retrospective
Introduction and summary
This retrospective focuses on the 4-month MATS extension phase (referred to as "MATS 5.1") that ran from April 1 to July 25, 2024, and presents findings gathered from an end-of-extension survey as well as follow-up interviews and surveys ~5 months after... |
8cbd1709-5eae-427c-856e-436dde7b4a0a | trentmkelly/LessWrong-43k | LessWrong | Weekly LW Meetups
Irregularly scheduled Less Wrong meetups are taking place in:
* [Zurich] March Rationality meetup: 04 March 2017 05:00PM
The following meetups take place in cities with regular scheduling, but involve a change in time or location, special meeting content, or simply a helpful reminder about the mee... |
dd8354f9-0f15-41f9-8f26-fed114cefcd6 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Phoenix (Tempe) Less Wrong Meetup
Discussion article for the meetup : Phoenix (Tempe) Less Wrong Meetup
WHEN: 18 October 2013 02:00:00PM (-0700)
WHERE: 300 E Orange Mall, Tempe, AZ
We will be meeting up in Hayden Library at ASU, probably to casually (causally? :P) discuss decision theory.
Text me at 602-5... |
bec908a7-5329-46f3-bbd8-5e43c7a9ff3a | trentmkelly/LessWrong-43k | LessWrong | Would solving logical counterfactuals solve anthropics?
One of the key problems with anthropics is establishing the appropriate reference class. When we attempt to calculate a probability accounting for anthropics, do we consider all agents or all humans or all humans who understand decision theory?
If a tree falls o... |
444b5e68-2437-482e-8066-954a8e253e29 | trentmkelly/LessWrong-43k | LessWrong | Shut Up and Calculate: Gambling, Divination, and the Abacus as Tantra
THERE ARE LAKES at the bottom of the ocean. I saw it in a nature documentary. You get a weird mineral deposit on the seafloor and it makes these brine pools, water so salty it doesn't mix with the sea water around it. Because it has no oxygen, any u... |
0e8083e0-c365-4cdc-b53e-57782a9a803d | trentmkelly/LessWrong-43k | LessWrong | XOR Blackmail & Causality
[Cross-posted from IAFF.]
I edited my previous post to note that I’m now much less optimistic about the direction I was going in. This post is to further elaborate the issue and my current position.
Counterfactual reasoning is something we don’t understand very well, and which has so many f... |
fa791f36-f8f4-4da8-aa5a-7162951fbec5 | trentmkelly/LessWrong-43k | LessWrong | 23andme genome analysis - $99 today only
I suspect this might interest some people here: for today only, 23andme is offering their full-package DNA testing for only 99 dollars (the normal price is $499).
23andme uses a genotyping process, which differs from a full gene-sequencing. From their website:
> The DNA chi... |
9bddf0d3-13e7-45d7-88cd-9772b122369c | trentmkelly/LessWrong-43k | LessWrong | AI #106: Not so Fast
This was GPT-4.5 week. That model is not so fast, and isn’t that much progress, but it definitely has its charms.
A judge delivered a different kind of Not So Fast back to OpenAI, threatening the viability of their conversion to a for-profit company. Apple is moving remarkably not so fast with Si... |
65b93a0e-3f8d-4057-940b-c16ffb25f22d | trentmkelly/LessWrong-43k | LessWrong | Graphical Representations of Paul Christiano's Doom Model
Paul gives some numbers on AI doom (text below). Here they are in graphical forms, which I find easier to understand. Please correct me if wrong.
Michael Trazzi's Probability Flow Diagram
I really like this one. I can really easily read how he thinks future w... |
890a9ac5-4734-479a-b7e8-6ac1d1cc9a48 | trentmkelly/LessWrong-43k | LessWrong | Plans / prepping for possible political violence from upcoming US election?
The US presidential election is now just 2 months away! There's a (IMO) plausible argument that we might have a disputed election that leads to large-scale political violence; for details see
* Vox: "Will He Go? A law professor fears a meltd... |
e4b9f974-1a37-4b3c-97f3-e0e24e5f7764 | trentmkelly/LessWrong-43k | LessWrong | Better debates
[Crossposted from https://tsvibt.blogspot.com/2023/05/better-debates.html.]
When two people disagree about a proposition even though they've thought about it alot, the disagreement is often hard to resolve. There's a gulf of data, concepts, intuitions, experiences, inferences. Some of this gulf has to ... |
e1f3f2c9-3034-4340-bd85-18966bf88a3b | trentmkelly/LessWrong-43k | LessWrong | What proportion of US companies would agree to this gross pay deduction / direct donation if asked by an employee?
This is not the most eloquent title, and it is not even that precise. Here is some more context. Find the words "main question " for my main question. I figured I would say that to avoid berrying the lead... |
442dee98-a8d4-4de5-8e4a-1bb081fe8c1a | trentmkelly/LessWrong-43k | LessWrong | Preface
You hold in your hands a compilation of two years of daily blog posts. In retrospect, I look back on that project and see a large number of things I did completely wrong. I’m fine with that. Looking back and not seeing a huge number of things I did wrong would mean that neither my writing nor my understanding ... |
f90c7c00-7562-45c5-ba9f-02c206d84486 | trentmkelly/LessWrong-43k | LessWrong | Imitation learning considered unsafe?
ETA: This post can basically be read as arguing that imitating human decisions, or any other outputs from an (approximate) planning process, seems especially likely to produce mesa-optimization, since a competent imitator should recover an (approximate) planning (i.e. optimization... |
dd8fc61e-4e49-4e3d-9cf6-897cc2442edf | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | What is "Constitutional AI"?
[Constitutional AI](https://www.anthropic.com/index/claudes-constitution) is a method developed by [Anthropic](https://www.anthropic.com/) and an essential part of their [strategy](https://www.anthropic.com/index/core-views-on-ai-safety) for building AIs that are safe and aligned with huma... |
3edb7642-0cc8-4c31-a233-cbc50cb7991b | trentmkelly/LessWrong-43k | LessWrong | LINK: Human Bio-engineering and Coherent Extrapolated Volition
This article has some interesting commentary on how humans might modify themselves to combat global warming, including the use of drugs that would increase empathy, increase willpower, or increase aversion to meat. The interviewer points out that such tech... |
80249e16-677a-444a-9dac-32136255de5c | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Environments for Measuring Deception, Resource Acquisition, and Ethical Violations
Models are rapidly being deployed in the real world. How do we evaluate models, especially ones as complex as GPT-4, to ensure that they behave safely in pursuit of their objectives? Can we design models that robustly avoid any harms wh... |
efa91409-c6f4-4b7c-8c69-cd76cd952c79 | trentmkelly/LessWrong-43k | LessWrong | What Are Some Alternative Approaches to Understanding Agency/Intelligence?
Apparently, MIRI has given up on their current mainline approach to understanding agency and are trying to figure out what to do next. It seems like it might be worthwhile to collect some alternative approaches to the problem -- after all, inte... |
4a25f7a9-c626-4a1b-a068-eeeed40396e5 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | [ASoT] Policy Trajectory Visualization
*Written during SERI MATS, 2022 Winter cohort, at a little prodding from sensei* [*Trout*](https://lesswrong.com/users/turntrout)*.*
If you're trying to understand a policy, viewing how it changes over time is valuable even if you aren't interested in the training process direct... |
aa092567-9485-4f73-bdb9-b7f74408eafe | trentmkelly/LessWrong-43k | LessWrong | Book Review: Righteous Victims - A History of the Zionist-Arab Conflict
I originally entered this to the ACX Book Review competition. Since it has not been selected as a finalist I'm now free to post it here. In truth it's a followup to my review of Morris's history of Israel's War of Independence.
In the wake of the... |
4f58aaa3-7e74-4ef7-b72e-41f7f92a2d65 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | You’re Measuring Model Complexity Wrong
**TLDR**: We explain why you should care about *model complexity*, why the *local learning coefficient* is arguably the correct measure of model complexity, and how to estimate its value.
In particular, we review [a new set of estimation techniques introduced by Lau et al. (202... |
cab7731b-5da4-4f9e-9b42-a1e7427a033f | trentmkelly/LessWrong-43k | LessWrong | There is No Akrasia
I don’t think akrasia exists.
This is a fairly strong claim. I’m also not going to try and argue it.
What I’m really here to argue are the two weaker claims that:
a) Akrasia is often treated as a “thing” by people in the rationality community, and this can lead to problems, even though ... |
01f6a13b-7b8c-424d-88f1-071528161e46 | trentmkelly/LessWrong-43k | LessWrong | Cryonics costs: given estimates are low
One of the sticking points for cryonics is how expensive it is. Unfortunately, the estimates on LW (eg. in Normal Cryonics) are likely to be low as they are current costs. This is starting to come to a head for Alcor, with Alcor's low growth rate meaning it faces a rising tide o... |
5609e20b-a029-4370-9cd9-009aa941e09e | trentmkelly/LessWrong-43k | LessWrong | Capability Phase Transition Examples
None |
d1c96c71-cdc7-4974-8ce7-68c64adf8769 | trentmkelly/LessWrong-43k | LessWrong | Using ChatGPT for memory reconsolidation?
I just tried a IFS bot based on GPT3.5 and I actually enjoyed it! Didn't make a breakthrough as I've done it on my own in the past, but definitely felt similar to my experiences.
Another use case I can think of is using ChatGPT to help me with memory reconsolidation. I had a ... |
274f3f00-9ffd-4d70-8c69-9859fec9d013 | trentmkelly/LessWrong-43k | LessWrong | Strong Evidence is Common
Portions of this are taken directly from Three Things I've Learned About Bayes' Rule.
One time, someone asked me what my name was. I said, “Mark Xu.” Afterward, they probably believed my name was “Mark Xu.” I’m guessing they would have happily accepted a bet at 20:1 odds that my driver’s lic... |
d7ef76b9-37c2-4fac-b27d-dda44a8d77ae | trentmkelly/LessWrong-43k | LessWrong | [EAForum xpost] A breakdown of OpenAI's revenue
We estimate that, as of June 12, 2024, OpenAI has an annualized revenue (ARR) of:
$1.9B for ChatGPT Plus (7.7M global subscribers),
$714M from ChatGPT Enterprise (1.2M seats),
$510M from the API, and
$290M from ChatGPT Team (from 980k seats)
(Full report in https:/... |
87582a37-cde6-4b01-b9f2-dc575a2c6892 | trentmkelly/LessWrong-43k | LessWrong | Model of human (ir)rationality
A putative new idea for AI control; index here.
This post is just an initial foray into modelling human irrationality, for the purpose of successful value learning. Its purpose is not to be full model, but have enough details that various common situations can be successfully modelled. ... |
51b3092b-20fb-4f35-a9e1-45b0fe35ee0b | trentmkelly/LessWrong-43k | LessWrong | Let's create a market for cryonics
My uncle works in insurance. I recently mentioned that I'm planning to sign up for cryonics.
"That's amazing," he said. "Convincing a young person to buy life insurance? That has to be the greatest scam ever."
I took the comment lightly, not caring to argue about it. But it got me ... |
7743d0a5-d7e5-47d6-b3a2-79b09d9eb678 | StampyAI/alignment-research-dataset/special_docs | Other | The Evolved Radio and its Implications for Modelling the Evolution of Novel Sensors
The Evolved Radio and its Implications for Modelling the Evolution of Novel Sensors
Jon Bird1 and Paul Layzell2
1Centre for Computational Neuroscience and Robotics
School of Biological Sciences
University of Sussex
Brighton BN1 ... |
dd6600cb-be73-49fe-ba02-39ed3e521bd0 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | [Link Post] Cyber Digital Authoritarianism (National Intelligence Council Report)
**Disclaimer**: The U.S. government selectively declassified this report for unknown reasons, and anti-Chinese-Communist-Party sentiment is high in Washington D.C. While I doubt this means the contents are factually inaccurate, it is lik... |
b8b4c607-0119-4799-a5fe-21ad17df53a0 | trentmkelly/LessWrong-43k | LessWrong | Ignoring Country Cohorts
I assume that many of you have been watching the "total coronavirus cases outside of China" number. If you look at them on a log chart, they appear to be growing perfectly exponentially and doubling every 4-5 days.
This perfect straight line is obscuring a very, very important underlying fact... |
159f323c-bacf-4e70-9e66-b99993b828af | trentmkelly/LessWrong-43k | LessWrong | Bad reductionism
I've been becoming more of a nature person recently.
* I moved into an apartment about a mile from the mountains and there's something really cool to me about being on the outskirts of town, crossing the line from "society" into "nature".
* A few weeks ago I went on a trip to the Grand Canyon. We a... |
dcd99e85-0e9b-4561-a8ef-f89e97f8954c | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Emily Brontë on: Psychology Required for Serious™ AGI Safety Research
*Subtitled: [Prolegomena](https://en.wikipedia.org/wiki/Prolegomena_to_Any_Future_Metaphysics) to Any Future*
**[No Coward Soul Is Mine](https://www.poetryfoundation.org/poems/43712/no-coward-soul-is-mine)**
*By Emily Brontë*
No coward soul is m... |
06ea054a-9ded-4fb5-bb3a-ac65e741df93 | trentmkelly/LessWrong-43k | LessWrong | Launch & Grow Your University Group: Apply now to OSP & FSP!
TL;DR
* Applications have opened for CEA’s Organizer Support Program (OSP), a mentorship program for both new and experienced organizers of EA university groups.
* We have combined our earlier group accelerator program (UGAP) into OSP, so students looking ... |
86bc1601-d1b0-4b1f-8be6-cc7f92af99df | trentmkelly/LessWrong-43k | LessWrong | Go Grok Yourself
That title is Elon Musk’s fault, not mine, I mean, sorry not sorry:
TABLE OF CONTENTS
1. Release the Hounds.
2. The Expectations Game.
3. Man in the Arena.
4. The Official Benchmarks.
5. The Inevitable Pliny.
6. Heart in the Wrong Place.
7. Where Is Your Head At.
8. Individual Reactions.
... |
5ac263cf-db37-43e7-a9d1-849bfbe63f93 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | "Do Nothing" utility function, 3½ years later?
In [AI Alignment: Why It's Hard and Where To Start](https://www.youtube.com/watch?v=EUjc1WuyPT8), at [21:21](https://www.youtube.com/watch?v=EUjc1WuyPT8&t=21m21s), Yudkowsky says:
>
> If we want to have a robot that will let us press the suspend button—just suspend it... |
19f75484-4971-4236-b24c-50f1b7401f9b | StampyAI/alignment-research-dataset/lesswrong | LessWrong | AI Box Experiment: Are people still interested?
I have a novel plan for the AI player that I believe will work against most gatekeeper players. Even knowing how it works, it would work against me! It isn't quite ready, but I'd like to know if there is still interest around the topic before finishing work on the prepar... |
a913f3d0-6f4b-4d69-b05e-886a010584a4 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | AI Safety Reading Group (Session 44)
so hello and welcome to the 44th session
of the AI safety reading group today we
are going to have a look at the ATI
safety solutions map made by Alexei
Turchin elected Turchin here is an
author from Russia who works at the
science for longer life foundation which
is also founded a... |
445716a5-54a9-4676-b412-54808da533ab | trentmkelly/LessWrong-43k | LessWrong | Brain-over-body biases, and the embodied value problem in AI alignment
Note: This essay was published here on EA Forum on Sept 21, 2022. The description of the brain-over-body biases in the EA subculture may or may not apply to the Rationalist subculture in LessWrong. This essay builds upon this essay on the heterog... |
4715b9c0-fcd1-478b-99d4-714e903f335f | trentmkelly/LessWrong-43k | LessWrong | Juneberry Puffs
I only learned about Juneberries a few years ago, and they're a bit tricky. Eaten fresh, right off the tree, they have a bunch of subtle flavors that remind me of peach ice tea. If I bake them, though, these flavors mostly go away, leaving an almondy flavor. Which isn't terrible, but also isn't better ... |
4b6627d2-2715-48c3-a70a-55806a069310 | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post1468
Various people propose some variant of “align AGI by making it sufficiently uncertain about whether it’s in the real world versus still in training”. (The idea being that, insofar as it's in training, betraying the apparent-operators predictably gets high loss; so if the AGI is uncertain about which situa... |
16ba73a8-e213-4f01-964f-7a0692edcd0c | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Abstract concepts and metalingual definition: Does ChatGPT understand justice and charity?
Our conceptual worlds are filled with abstract concepts, such as truth, love, beauty, and justice. Such concepts cannot be defined in physical terms. You can’t see them, taste them, hear them, touch them, or smell them. And yet... |
f3e7d1a1-9d12-40c6-b747-fb56e9d6a712 | trentmkelly/LessWrong-43k | LessWrong | Gender Exploration
The rationalist community has been discussing whether ‘AGP males’ should try hormones or not. Eneaz Brodsky says Transitioning Is Harmful To Most AGP Males. Ozy has a thoughtful, but paywalled, reply. Regardless of the benefits of transitioning you would think the main downside would be the costs in... |
48698e79-d7ad-483a-a677-577ff7b4707c | trentmkelly/LessWrong-43k | LessWrong | Neuroscience basics for LessWrongians
The origins of this article are in my partial transcript of the live June 2011 debate between Robin Hanson and Eliezer Yudkowsky. While I still feel like I don't entirely understand his arguments, a few of his comments about neuroscience made me strongly go, "no, that's not right.... |
cba9082d-c64e-4490-b376-34e6a905732e | trentmkelly/LessWrong-43k | LessWrong | Biological Anchors: The Trick that Might or Might Not Work
This post originally posted on Astral Codex Ten on Feb 23 2022.
It was printed in The Carving of Reality, the third volume of the Best of LessWrong book series. It was included as a (shorter) replacement for Ajeya Cotra's Draft report on AI timelines, and El... |
bdbe9709-a45a-455d-85c2-e3a9a269adb0 | trentmkelly/LessWrong-43k | LessWrong | Translations Should Invert
Suppose that Alice is arguing for ZFC set theory as the proper foundation of mathematics. Bob is arguing for some specific intuitionistic type theory. Alice uses classical logic, and Bob uses intuitionistic logic; this is a big part of their difference in thinking, but not the whole disagree... |
ed78460d-b731-45e2-9168-e55ea0bf76f2 | trentmkelly/LessWrong-43k | LessWrong | Ruining an expected-log-money maximizer
Suppose you have a game where you can bet any amount of money. You have a 60% chance of doubling your stake and a 40% chance of losing it.
Consider agents Linda and Logan, and assume they both have £11. Linda has a utility function that's linear in money (and has no other terms... |
f15dea47-58d2-4fb8-846d-2b08d39ce520 | trentmkelly/LessWrong-43k | LessWrong | Disentangling Our Terminal and Instrumental Values
Disagreements related to what we value seem to explain maybe 10% of the disagreements over AI safety. This post will try to explain how I think about which values I care about perpetuating to the distant future.
Robin Hanson helped to clarify the choices in Which Of ... |
704842e8-60ad-44de-aa98-30ff4c24fddc | trentmkelly/LessWrong-43k | LessWrong | Bay Area Meetup Wed 12/10 @8pm
Reminder: the second regular Overcoming Bias meetup is tomorrow, Wednesday at 8pm, at Techshop in Menlo park. Please RSVP so they know how many people are coming.
If you're hearing about this for the first time, sign up for the Meetup group so you get future announcements! And please ... |
f6478dab-c6d6-4f4b-91ca-d62e411e0c1b | trentmkelly/LessWrong-43k | LessWrong | All-pay auction for charity?
While in a standard auction you have to pay your bid only if you win, in an all-pay auction you pay whether or not you win. The standard example is a dollar auction where you're selling a dollar. Bidding a penny to get a dollar seems reasonable, but someone else then might bid two cents. T... |
d45b7bee-b386-4315-8b5e-9698cda7b5fa | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | A (EtA: quick) note on terminology: AI Alignment != AI x-safety
I think the terms "AI Alignment" and "AI existential safety" are often used interchangeably, leading the ideas to be conflated.
In practice, I think "AI Alignment" is mostly used in one of the following three ways, and should be used exclusively for... |
8c522dbf-7965-4707-97cb-0f826eb22b80 | trentmkelly/LessWrong-43k | LessWrong | Mandatory Obsessions
Cross-posted from Putanumonit.
The Worst is to Care a Little
At a party the other day, a woman expressed her displeasure at men who “pretend to be allies of gay rights but don’t really care about it”. Did she mean men who proclaimed their progressive attitudes on LGBTQ but voted Republican on Tu... |
8e0024b1-fd8e-46b4-8022-590f4fac6d53 | trentmkelly/LessWrong-43k | LessWrong | Why people reject science
From the NYTimes. The central point:
> Humans, he argues, are hard-wired to reject scientific conclusions that run counter to their instinctive belief that someone or something is out to get them.
|
611982e2-10b1-49a5-b536-8b4602da42e5 | trentmkelly/LessWrong-43k | LessWrong | The North Oakland LessWrong Meetup
The mission of the North Oakland LessWrong meetup is to provide a fun, low-key social space with some structured interaction, where new and non-new community members can mingle and have interesting conversations. Everyone is welcome. Yes, that includes you, if you're reading this. Ev... |
59fc294e-3f9c-45fa-a602-5c223a4b35a3 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Canberra: Intro to Anthropic Reasoning
Discussion article for the meetup : Canberra: Intro to Anthropic Reasoning
WHEN: 25 July 2014 06:00:00PM (+1000)
WHERE: 108 North Road, Acton, ACT
I Think Therefore I Am; I Am, Therefore The World Is About To Be Destroyed!
Nick will be talking about anthropic reasoni... |
bb62e8c3-1810-4454-9dea-edf77cc5b8d8 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Phoenix, Arizona
Discussion article for the meetup : Phoenix, Arizona
WHEN: 15 June 2012 07:00:00PM (-0700)
WHERE: 2502 E. Camelback Road Phoenix,AZ,85016
The meetup will take place at the Paradise Bakery & Cafe in Biltmore Fashion Park. We will be discussing chapter I-V of Gödel, Escher, Bach: an Eternal G... |
78500e64-f264-4630-a06b-2b13e6117d04 | trentmkelly/LessWrong-43k | LessWrong | Meetup : San Jose Start of College Meetup
Discussion article for the meetup : San Jose Start of College Meetup
WHEN: 27 August 2011 02:00:00PM (-0700)
WHERE: San Jose State University
I head up to school this week and i wanted to gauge the interest in a meetup in the area :) I have a couple viable ideas for locatio... |
8922b991-7536-43a1-8ba4-0364f0d3d490 | StampyAI/alignment-research-dataset/arbital | Arbital | Odds: Refresher
Let's say that, in a certain forest, there are 2 sick trees for every 3 healthy trees. We can then say that the odds of a tree being sick (as opposed to healthy) are $(2 : 3).$
Odds express *relative* chances. Saying "There's 2 sick trees for every 3 healthy trees" is the same as saying "There's 10 s... |
b790a489-2e94-40ee-81e2-c0b7aaa4176e | trentmkelly/LessWrong-43k | LessWrong | Meetup : Saint Petersburg meetup - "with probable lectures"
Discussion article for the meetup : Saint Petersburg meetup - "with probable lectures"
WHEN: 14 November 2014 07:00:00PM (+0300)
WHERE: Россия, Санкт-Петербург, Московский пр. 65
We will gather for at least three hours, in the same free venue.
There is a ... |
f0b722a1-0d7c-4ccd-8d45-8148c8da97e3 | trentmkelly/LessWrong-43k | LessWrong | Answer to a question: what do I think about God's communication patterns?
This started as a comment on Book Review: How Minds Change, but it got so long and off the original topic that I felt it didn't belong in that comments feed. People would have to scroll past a large block of text that doesn't have much to do wit... |
8a2eacf6-800c-451b-b732-a7a489fac596 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Shallow evaluations of longtermist organizations
*Epistemic status*: Fairly uncertain. May contain errors, probabilities might not be calibrated.
Introduction
------------
This document reviews a number of organizations in the longtermist ecosystem, and poses and answers a number of questions which would have to b... |
ef27300e-0b39-4bc6-8d3b-08e1f237ea4c | trentmkelly/LessWrong-43k | LessWrong | Focus on the places where you feel shocked everyone's dropping the ball
Writing down something I’ve found myself repeating in different conversations:
If you're looking for ways to help with the whole “the world looks pretty doomed” business, here's my advice: look around for places where we're all being total idiots... |
727baa55-425b-4c92-9822-6fa6f5729920 | trentmkelly/LessWrong-43k | LessWrong | Playing with Otamatones
A couple months ago Nora (3y) got very into Otamatones. She wanted to watch lots of videos, primarily TheRealSullyG. She asked for one for Christmas, and so did I:
They're a lot of fun, but I haven't yet figured out if it's an instrument I'll ever be able to reliably play in tune.
The ... |
554c0174-702c-43a9-b283-04716148745a | StampyAI/alignment-research-dataset/arxiv | Arxiv | Correct-by-Construction Runtime Enforcement in AI -- A Survey
1 Introduction
---------------
Safety of learning-based or learned controllers is a major concern when using them in physical systems and in the proximity of humans.
Particularly during the exploration phase of learning, when an agent chooses random
acti... |
a3e34c7d-cd6a-4657-9150-6183dd37240f | trentmkelly/LessWrong-43k | LessWrong | The latest in preference elicitation and preference learning in AI [links]
'Preference elicitation' or 'preference extraction' or 'preference learning' is a key step in CEV. Most work on preference elicitation has been done by economists. The state of the art in AI is summarized here and here. |
d93c2a3a-8cee-41a7-95fd-bfaf4e5e4e9b | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Bind Yourself to Reality
Today's post, Bind Yourself to Reality was originally published on 22 March 2008. A summary (taken from the LW wiki):
> There are several reasons why it's worth talking about joy in the merely real in a discussion on reductionism. One is to leave a line of retreat. Another is t... |
0cd8f99f-9c8d-44f6-a147-0604439d3c21 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Interactive Learning from Policy-Dependent Human Feedback
I Introduction
---------------
Programming robots is very difficult, in part because the real world is inherently rich and—to some degree—unpredictable. In addition, our expectations for physical agents are quite high and often difficult to articulate. Never... |
cd22a543-a351-43a8-b849-43c6e1b593a5 | trentmkelly/LessWrong-43k | LessWrong | Privileging the Question
Related to: Privileging the Hypothesis
> Remember the exercises in critical reading you did in school, where you had to look at a piece of writing and step back and ask whether the author was telling the whole truth? If you really want to be a critical reader, it turns out you have to step ba... |
7405f5c5-3f46-4e9a-8cde-4cb1e0ecc18e | trentmkelly/LessWrong-43k | LessWrong | Meetup : Durham Meetup: Article discussions
Discussion article for the meetup : Durham Meetup: Article discussions
WHEN: 25 October 2012 07:00:00PM (-0400)
WHERE: Francesca's 706B 9th St Durham, NC 27705
We'll be discussing some articles over coffee and pastries. In particular:
Generalizing From One Example
It's ... |
e44d1b85-2d9c-45ee-81aa-07d34c1662c8 | trentmkelly/LessWrong-43k | LessWrong | My Thoughts on the Apperception Engine
Epistemic status: I am writing mainly to clarify my own thoughts on this, but I think it is definitely worth sharing what I have here. This is not meant to be a review of the paper itself, rather a discussion of its implications.
So:
> We note in particular that in the sequence... |
36e84970-cfff-458c-99e8-510e98140436 | StampyAI/alignment-research-dataset/arbital | Arbital | Value-laden
An intuitive human category, or other humanly intuitive quantity or fact, is *value-laden* when it passes through human goals and desires, such that an agent couldn't reliably determine this intuitive category or quantity without knowing lots of complicated information about human goals and desires (and ho... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.