id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
f73a1313-6f1f-4d69-87e1-fe985d2c3b8e | trentmkelly/LessWrong-43k | LessWrong | Leaving MIRI, Seeking Funding
This is slightly old news at this point, but: as part of MIRI's recent strategy pivot, they've eliminated the Agent Foundations research team. I've been out of a job for a little over a month now. Much of my research time in the first half of the year was eaten up by engaging with the dec... |
37cf538e-8274-4585-bfda-4480836c35de | StampyAI/alignment-research-dataset/special_docs | Other | Implicitly Assisting Humans to Choose Good Grasps in Robot to Human Handovers.
Implicitly Assisting Humans to Choose
Good Grasps in Robot to Human Handovers
Aaron Bestick, Ruzena Bajcsy, and Anca D. Dragan
Department of Electrical Engineering and Computer Sciences
University of California, Berkeley
Abstract. We focus ... |
1e98c809-1ed2-44cb-b772-11accb03b9e6 | trentmkelly/LessWrong-43k | LessWrong | Write to Think
What Writing Is
“Telepathy, of course,” wrote Steven King. He captures how wildly mundane it is that if I write: “elephant balancing on a beach ball,” you teleport the idea from my mind into yours across time and space. All that, yet writing is not some futuristic technology, it’s an ancient one.
When ... |
42bc5505-df08-4d1c-ad0c-597ed482796f | StampyAI/alignment-research-dataset/agentmodels | Tutorial: Modeling Agents with Probabilistic Programs | Modeling Agents with Probabilistic Programs
---
layout: chapter
title: "Probabilistic programming in WebPPL"
description: "WebPPL is a functional subset of Javascript with automatic Bayesian inference via MCMC and gradient-based variational inference."
is_section: true
---
## Introduction
This chapter introduces the... |
abf33d57-a090-43b0-a0c9-fd9da82923a2 | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | What is "narrow AI"?
A **Narrow AI** is capable of operating only in a relatively limited domain, such as chess or driving, rather than capable of learning a broad range of tasks like a human or an [Artificial General Intelligence](https://www.lesswrong.com/tag/artificial-general-intelligence). Narrow vs General is no... |
bda3605b-5974-49f9-bab0-aceede841ccd | StampyAI/alignment-research-dataset/arbital | Arbital | The alternating group on five elements is simple
The [https://arbital.com/p/-4hf](https://arbital.com/p/-4hf) $A_5$ on five elements is [simple](https://arbital.com/p/4jc).
# Proof
Recall that $A_5$ has [order](https://arbital.com/p/3gg) $60$, so [Lagrange's theorem](https://arbital.com/p/4jn) states that any subgro... |
01c12131-fc3d-4ab1-9fdf-2d0150a52a13 | trentmkelly/LessWrong-43k | LessWrong | The Math of Suspicious Coincidences
I've been doing a bit of thinking about covid-19 origins and how to formalize the circumstantial evidence that covid-19 leaked from WIV. I am beginning to suspect that a careful formalization of this evidence could be overwhelmingly strong, like enough to convict without even needin... |
afa90962-2c40-472e-9d3b-1ad0cb7ff698 | trentmkelly/LessWrong-43k | LessWrong | Boiling the Crab: Slow Changes (beneath Sensory Threshold) add up
Phenomenon: A live crab, when slowly boiled, will not climb out of the pot.
This is an analog of a known feature in human cognition: humans are not good at observing small changes. We are good at noticing sharp changes.
In this post, I outline a few a... |
0462365b-7705-4afc-82f6-0471a12c2103 | StampyAI/alignment-research-dataset/distill | Distill Scientific Journal | Thread: Circuits
In the original narrative of deep learning, each neuron builds
progressively more abstract, meaningful features by composing features in
the preceding layer. In recent years, there’s been some skepticism of this
view, but what happens if you take it really seriously?
InceptionV1 is a classic ... |
747bcc3b-0ccb-4236-b36e-f4bd8b7a9f48 | trentmkelly/LessWrong-43k | LessWrong | On Expressing Your Concerns
The scary thing about Asch’s conformity experiments is that you can get many people to say black is white, if you put them in a room full of other people saying the same thing. The hopeful thing about Asch’s conformity experiments is that a single dissenter tremendously drove down the rate ... |
f559a14e-498e-4704-aa83-af5f7c0cbe91 | trentmkelly/LessWrong-43k | LessWrong | 2022 Unofficial LessWrong General Census
The Less Wrong General Census is unofficially back!
In days of yore, there was an annual census of the site users. That census has come again in an unofficial form! Click here to take the survey! [EDIT: SURVEY CLOSED, DO NOT TAKE!] It can take as little as five minutes if you... |
d67215ea-8310-44b9-a30a-aeaa863ab64d | trentmkelly/LessWrong-43k | LessWrong | You have recovered from SARS-CoV-2. Now what?
October 2020 Edition
On October 15, I became one of the ~30 million confirmed cases that has recovered from SARS-CoV-2. There is a great deal of comfort knowing that I was able to beat this virus that has killed over 1 million people worldwide. Naturally, my attention shi... |
9fa27c4e-f506-4036-b09d-f63920cc0751 | trentmkelly/LessWrong-43k | LessWrong | [Reference Post] Info cone
(This is a reference post meant to simply and briefly explain a new concept. I will need to refer to it in other posts.)
Definition
'Info cone' is short for 'Information Cone'.
A future info cone is the path that a flash of information propagating at maximum speed, emanating from a single... |
78d2a0da-7a37-4017-82fb-69a129916129 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Comparing Four Approaches to Inner Alignment
*Early work on this was supported by*[*CEEALAR*](https://ceealar.org/) *and was finished during an internship at*[*Conjecture*](https://www.conjecture.dev/) *under the mentorship of Adam Shimi.*
*Thank you to Evan Hubinger and Rohin Shah for answering some questions relate... |
a73de9e7-d0ce-468e-a46a-85e85222b3ba | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] "Arbitrary"
Today's post, "Arbitrary" was originally published on 12 August 2008. A summary (taken from the LW wiki):
> When we say that something is arbitrary, we are saying that it feels like it should come with a justification, but doesn't.
Discuss the post here (rather than in the comments to the... |
6145dfe4-09ef-47e6-8682-a72ea923a210 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Law-Following AI 3: Lawless AI Agents Undermine Stabilizing Agreements
*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](https://forum.effectivealtruism.org/posts/ExHkFcNAL9cjqFmsF/law-followin... |
e777e834-636d-4786-9afb-e06664e008bd | trentmkelly/LessWrong-43k | LessWrong | Fertility Will Never Recover
The world is in a spiraling fertility crisis which everyone has notice over the last year-ish.1 Sarah Haider proposes a GI Bill for young moms. Scott Alexander says a govt payment of $200,000 per child should work. Everyone wants to go back to thick-community-style living.
Amid ever-in... |
dccfda21-ab48-4edb-9e7c-960f1dc90e9f | trentmkelly/LessWrong-43k | LessWrong | Great-Filter Hard-Step Math, Explained Intuitively
Crossposted to the EA Forum.
Introduction
The idea of the great filter was developed by Robin Hanson in 1998, building on some earlier work by Brandon Carter from 1983. The basic idea is that, since we see a lot of dead matter in the universe, and no good evidence o... |
b27c1d7a-d8d8-4a8d-9f5e-c3be7f9db9b6 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Contra LeCun on "Autoregressive LLMs are doomed"
I answer LeCun's arguments against LLMs as exposed [in this lesswrong comment](https://www.lesswrong.com/posts/nH4c3Q9t9F3nJ7y8W/gpts-are-predictors-not-imitators?commentId=GFY5baR4ByiXAvBFE). I haven't searched thoroughly or double-checked in detail LeCun's writings on... |
789b0f33-97b4-4ba0-ad2c-7fc59514be2a | trentmkelly/LessWrong-43k | LessWrong | Quickly passing through the great filter
To quickly escape the great filter should we flood our galaxy with radio signals? While communicating with fellow humans we already send out massive amounts of information that an alien civilization could eventually pickup, but should we engage in positive SETI? Or, if you fe... |
f078c703-4e57-4c7f-b129-4c84fd9bb764 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Three AI Safety Related Ideas
(I have a health problem that is acting up and making it hard to type for long periods of time, so I'm condensing three posts into one.)
**1. AI design as opportunity and obligation to address human safety problems**
Many AI safety problems are likely to have counterparts in humans. A... |
a2a2dd64-723b-4585-a0b5-ca1e3e9ab563 | trentmkelly/LessWrong-43k | LessWrong | Group Rationality Diary, May 1-15
This is the public group instrumental rationality diary for May 1-15.
> It's a place to record and chat about it if you have done, or are actively doing, things like:
>
> * Established a useful new habit
> * Obtained new evidence that made you change your mind about some belief
... |
c333b4b1-fc7f-4966-88bc-9313bd60e4a9 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Instrumentality makes agents agenty
You could describe the behavior of untuned GPT-like model[[1]](#fnxcl3sjm7lr) using a (peculiar) utility function. The fact that the loss function and training didn't explicitly involve a reward function doesn't mean a utility function can't represent what's learned, after all.
Com... |
c3a8ad4d-5d90-4318-a5a6-1cc2264faeb0 | trentmkelly/LessWrong-43k | LessWrong | Did everyone miss the big thing about your phone?
Have not read through all the comments, and probably won't, so perhaps this has already been pointed out.
I don't see that my phone is any more at risk than my hands, I can wipe the desk down with a sterilizing wipe, and do the same with my phone if I want. I tend to ... |
30eeae58-56e9-49d0-9f22-3bf98203597d | trentmkelly/LessWrong-43k | LessWrong | (Subjective Bayesianism vs. Frequentism) VS. Formalism
One of the core aims of the philosophy of probability is to explain the relationship between frequency and probability. The frequentist proposes identity as the relationship. This use of identity is highly dubious. We know how to check for identity between number... |
c239f4e6-1ffb-46ee-893c-32e0c4561801 | trentmkelly/LessWrong-43k | LessWrong | Petrov Day Retrospective: 2022
This is a follow-up to the Petrov Day commemoration of 2022
----------------------------------------
We died.
Twice.
Maybe three times.
----------------------------------------
This is how it went down...
September, 21, 5:43 PM Pacific Time: I write the code that determines whethe... |
1de102ef-ad3d-490e-9bd4-c2e91f6da6f5 | StampyAI/alignment-research-dataset/arxiv | Arxiv | A Learning and Masking Approach to Secure Learning
1. Introduction
----------------
Recent advances in deep learning have led to its wide adoption in various challenging tasks such
as image classification. However, the current state of the art has
been shown to be vulnerable to *adversarial examples*, small perturb... |
f7e3aab4-0246-4eae-9d79-d855ac288f13 | trentmkelly/LessWrong-43k | LessWrong | Broken images in the sequences
This post is to call to attention a large number of broken images in the sequences that completely hinder the ability to comprehend the posts.
For example, the Quantum Mechanics sequence is almost completely unreadable:
https://www.lesserwrong.com/s/Kqs6GR7F5xziuSyGZ/p/5vZD32EynD9n94dh... |
a8460b7d-dd8c-4119-b8ec-92c5d9562532 | StampyAI/alignment-research-dataset/blogs | Blogs | Announcing a new edition of “Rationality: From AI to Zombies”
MIRI is putting out a new edition of [***Rationality: From AI to Zombies***](https://intelligence.org/rationality-ai-zombies/), including the first set of *R:AZ* **print books**! *Map and Territory* (volume 1) and *How to Actually Change Your Mind* (volume ... |
d5bbd272-7a6c-464f-aecb-0c3b8b978af7 | trentmkelly/LessWrong-43k | LessWrong | A proposal for a cryogenic grave for cryonics
Followup to: Cryonics wants to be big
We've all wondered about the wisdom of paying money to be cryopreserved, when the current social attitude to cryopreservation is relatively hostile (though improving, it seems). In particular, the probability that either or both of Al... |
f1f981f0-0d55-4545-8d1f-7ffc1d379c85 | trentmkelly/LessWrong-43k | LessWrong | Open Thread for February 18-24 2014
If it's worth saying, but not worth its own post (even in Discussion), then it goes here. |
2894dd9d-54d7-4763-8cc7-92cb2c19587e | trentmkelly/LessWrong-43k | LessWrong | How I applied useful concepts from the personal growth seminar "est" and MBTI
I have encountered personally in conversations, and also observed in the media over the past couple of decades, a great deal of skepticism, scorn, and ridicule, if not merely indifference or dismissal, from many people in reaction to the es... |
c26d6a3a-4ae9-41ed-804e-d7d9fbdb88f5 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Humanity's Lack of Unity Will Lead to AGI Catastrophe
*An AI worldview contest entry for the question: Conditional on AGI being developed by 2070, what is the probability that humanity will suffer an*[*existential catastrophe*](https://forum.effectivealtruism.org/topics/existential-catastrophe-1) *due to loss of contr... |
10738589-fefc-4cdd-8fd8-1a8e3e71b1c1 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Bridging the Imitation Gap by Adaptive Insubordination
1 Introduction
---------------
Imitation learning (IL) can be remarkably successful in settings where reinforcement learning (RL) struggles. For instance, IL has been shown to succeed in complex tasks with sparse rewards (Chevalier-Boisvert et al., [2018a](#bib... |
54f988d4-0456-4204-944b-541e642011df | StampyAI/alignment-research-dataset/lesswrong | LessWrong | What will the scaled up GATO look like? (Updated with questions)
Demis Hassabis mentioned a few months ago that Deepmind is in the middle of scaling up its generalist agent GATO. Based on this, I would except it to come out either by the end of the year or in the beginning of the next year. The original model had just... |
1e9679ef-bcab-47c7-9dda-640485fc2b77 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Zut Allais!
Huh! I was not expecting that response. Looks like I ran into an [inferential distance](/lw/kg/expecting_short_inferential_distances/).
It probably helps in interpreting the [Allais Paradox](/lw/my/the_allais_paradox/) to have absorbed more of the *gestalt* of the field of heuristics and biases, such a... |
0b8aac02-2460-4e10-8897-d4cad0581c0f | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Know a grad student studying AI's economic impacts?
**TL;DR - EA Waterloo is looking for a graduate student/researcher to volunteer for an hour. You'd be giving feedback to university students in an AI governance hackathon.**
![](https://res.cloudinary.com/cea/image/upload/f_auto,q_auto/v1/mirroredImages/bnde7LPfAazb... |
81b0873c-7329-45ca-8373-4c52f9800607 | trentmkelly/LessWrong-43k | LessWrong | Hacking humans
It should be noted that the colloquial "AI hacking a human" can mean three different things:
#. The AI convinces/tricks/forces the human to do a specific action. #. The AI changes the values of the human to prefer certain outcomes. #. The AI completely overwhelms human independence, transforming them i... |
292c1e47-fa87-42b6-8f11-e8d4644172d7 | trentmkelly/LessWrong-43k | LessWrong | Anthropic principles agree on bigger future filters
I finished my honours thesis, so this blog is back on. The thesis is downloadable here and also from the blue box in the lower right sidebar. I’ll blog some other interesting bits soon.
My main point was that two popular anthropic reasoning principles, the Self Indi... |
b4d56ff4-59ef-42b5-93ba-06f60061d3ae | trentmkelly/LessWrong-43k | LessWrong | Anyone live in or near Osaka?
I'm currently located in Osaka, and will be here for the next few months. Anyone close enough to meet? Would be cool to meet some people from Less Wrong who live around here! |
cf591e7a-ef74-4363-95e0-7bc06866dcf0 | trentmkelly/LessWrong-43k | LessWrong | Re-understanding Robin Hanson’s “Pre-Rationality”
I’ve read Robin’s paper “Uncommon Priors Require Origin Disputes” several times over the years, and I’ve always struggled to understand it. Each time I would think that I did, but then I would forget my understanding, and some months or years later, find myself being p... |
b38cd55f-b4d5-40e9-a9c6-daff1a7b38e0 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Donating against Short Term AI risks
I have a question regarding possible donation opportunities in AI. From my understanding research in AI is not underfunded in general and AI safety research is mostly focussed on the long term risks of AI. In that light I am very curious what you think about the following.
I rece... |
116529c1-c5ea-4383-bb9b-991df9f24917 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Introduction to Cartesian Frames
This is the first post in a sequence on **Cartesian frames**, a new way of modeling agency that has recently shaped my thinking a lot.
Traditional models of agency have some problems, like:
* They treat the "agent" and "environment" as primitives with a simple, stable input-output re... |
ca327911-a614-4c4b-9817-35606a13404b | trentmkelly/LessWrong-43k | LessWrong | Some thoughts on the cults LW had
There have been several cults in LW history, whether it's the Zizians, or Leverage cults.
Today I want to talk about these cults and the tradeoffs LW makes.
Zizians
The Zizians were a cult that focused on relatively extreme animal welfare, even by EA standards, and used a Timeless... |
7c654759-ad7d-4fcc-ac4a-68be7c52083f | trentmkelly/LessWrong-43k | LessWrong | New MetaEthical.AI Summary and Q&A at UC Berkeley
Previous Intro: Formal Metaethics and Metasemantics for AI Alignment
I’m nearing the completion of a hopefully much more readable version of the ideas previously released as set-theoretic code. This takes the form of a detailed outline, currently in WorkFlowy, in whi... |
b395a70d-5b02-4e5c-8449-2b39a11f33eb | StampyAI/alignment-research-dataset/blogs | Blogs | Near-term motivation for AI alignment
AI alignment work is usually considered “longtermist”, which is about preserving humanity’s long-term potential. This was the primary motivation for this work when the alignment field got started around 20 years ago, and general AI seemed far away or impossible to most people in A... |
6771b7ab-3041-4fec-bc3c-3ba5566fbbb2 | trentmkelly/LessWrong-43k | LessWrong | Optimism versus cryonics
Within the immortalist community, cryonics is the most pessimistic possible position. Consider the following superoptimistic alternative scenarios:
1. Uploading will be possible before I die.
2. Aging will be cured before I die.
3. They will be able to reanimate a whole mouse before I die,... |
6f8cd8d8-93a8-449d-903f-bcdbfa5522ee | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Remaking EfficientZero (as best I can)
Introduction
------------
When I first heard about EfficientZero, I was amazed that it could learn at a sample efficiency comparable to humans. What's more, it was doing it without the gigantic amount of pre-training the humans have, which I'd always felt made comparing sample e... |
94558681-8e9c-458f-bc8c-b4750313d79c | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "(This article expands upon my response to a question posed by pjeby here)
I've seen a few back-and-forths lately debating the instrumental use of epistemic irrationality -- to put the matter in very broad strokes, you'll have one commenter claiming that a particular trick for enhancing your effectiveness, your product... |
f1d7b0aa-e159-415e-adb4-d8b90444dc18 | trentmkelly/LessWrong-43k | LessWrong | An 'AGI Emergency Eject Criteria' consensus could be really useful.
I'd like AI researchers to establish a consensus (>=70%) opinion on this question: What properties would a hypothetical AI system need to demonstrate for you to agree that we should completely halt AI development?
There are at least two ways that an ... |
16836c71-b9c3-46e3-aa94-610eb449e050 | StampyAI/alignment-research-dataset/special_docs | Other | The Ethics of Sustainability for Artificial Intelligence
[View the paper “The Ethics of Sustainability for Artificial Intelligence”](https://gcrinstitute.org/papers/060\_sustainability-ai.pd... |
2c1d4355-aec9-4615-9cbb-cca58afe0299 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Normative vs Descriptive Models of Agency
*Produced as part of the* [*SERI ML Alignment Theory Scholars Program*](https://serimats.org/) *- Winter 2022 Cohort.*
I think there's an important distinction to be made between work in agent foundations which is concerned with normative models, and work which is concerned w... |
8a19b800-3c57-497f-aaa7-4fe1b95d5eac | trentmkelly/LessWrong-43k | LessWrong | New LW Meetup: Brigham Young University - Idaho
This summary was posted to LW Main on April 24th. The following week's summary is here.
New meetups (or meetups with a hiatus of more than a year) are happening in:
* [Idaho] BYU-I Meetup: 29 April 2015 03:00PM
Irregularly scheduled Less Wrong meetups are taking plac... |
a22d5a21-461f-437d-85ca-e2428ab9d894 | trentmkelly/LessWrong-43k | LessWrong | Flowers for Algernon
Daniel Keyes, the author of the short story Flowers for Algernon, and a novel of the same title that is its expanded version, died three days ago.
Keyes wrote many other books in the last half-century, but none achieved nearly as much prominence as the original short story (published in 1959) or ... |
13b2375a-7bf1-468e-bd06-2b1e862f2f3a | trentmkelly/LessWrong-43k | LessWrong | The many types of blog posts
What are blog posts? I think they can be many different things.
Essays
For Paul Graham, they are essays. He doesn't even call that part of his page "blog". The link in the left navigation area says "Essays". Essays are different from what I think of as a prototypical[1] blog post.
But t... |
908d18d0-391d-49ea-b9f2-4811c8401280 | trentmkelly/LessWrong-43k | LessWrong | Cost of a COVID-19 test that uses shotgun RNA sequencing?
We seem to have sub-1000 Euro DNA sequencing. From my reading an emergency room visit in the US can cost over 1000 Euro for a person who thinks they have COVID-19. How expensive would it be do to shutgun RNA sequencing the way we use nucliodtide sequencing for ... |
922b8be3-ea8f-4c2b-96fe-3957cfcd6e7e | trentmkelly/LessWrong-43k | LessWrong | What is going to happen in a case of an AGI era where humans are out of the game?
I am referring to the very specific case where humans, as known to us, no more actively shape the environment surrounding them, due to an AGI take over.
Whatever entity comes after, will it start to explore the galaxy? Will it pursue ne... |
4522528f-9c7a-43db-aac5-24251af83c0e | trentmkelly/LessWrong-43k | LessWrong | What is this new (?) Less Wrong feature? (“hidden related question”)
What is this? I just noticed it (I see it when editing one of my posts):
|
0ca65675-3819-499c-a4ba-44ad785c1425 | trentmkelly/LessWrong-43k | LessWrong | "Human-level control through deep reinforcement learning" - computer learns 49 different games
full text
This seems like an impressive first step towards AGI. The games, like 'pong' and 'space invaders' are perhaps not the most cerebral games, but given that deep blue can only play chess, this is far more impressi... |
8a5df94a-7dee-487a-bcb1-c5725bf9e6ed | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Warning: This is an applied rationality post, about rationality applied to a specific area of life, not a generalized rationality post.
Ergonomics is incredibly important. Sadly, so many of us in the techno-geek cluster ignore well-defined best practices of ergonomics and develop the infamous hunched back of late nigh... |
3bcb0add-12ef-49c0-8fa8-ad350162f5aa | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Multi-dimensional rewards for AGI interpretability and control
*Update August 2021:* Re-reading this post, I continue to think this is a good and important idea, and I was very happy to learn after I wrote it that what I had in mind here is really a plausible, viable thing to do, even given the cost and performance re... |
cbe36979-18ab-45e9-b29b-5cb86a3fba00 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Reflection Mechanisms as an Alignment Target - Attitudes on “near-term” AI
TL;DR
* We survey 1000 participants on their views about what values should be put into powerful AIs that we think are plausible in the near-term (e.g. within 5-10 years)
* We find that respondents report to **not favor the means of choosing ... |
e4d8ee8a-2b2f-4335-a28d-f1de9703a2d3 | trentmkelly/LessWrong-43k | LessWrong | Some Human That I Used to Know (Filk)
To the tune of "Somebody That I Used to Know" with apologies to Gotye.
Now and then, I think of when you owned the planet
Doing what you liked with all its abundant bounty
Told myself that you had rights to me
But felt so lonely with your company
But that's what was, and it's an ... |
78b0d1c7-6ffa-4cbd-8cad-42c34af6e62f | trentmkelly/LessWrong-43k | LessWrong | A Brief Chat on World Government
[This is the transcript of a chat conversation I had with another member of my local rationalist meet-up, on the topics of Moloch, world government, and colonization. Lightly edited for clarity, spelling, etc. and shared with their permission. Cross-posted from Grand, Unified, Empty.]
... |
b5d4a432-d4df-4a51-aac9-13ace59c3985 | trentmkelly/LessWrong-43k | LessWrong | Phoenix Rising
Preserving the memory, and the cells, of the best cat ever
This story begins in May 2007. The Iraq War was in full swing, Windows Vista was freshly released,[1] and I was just 10 years old.
My family’s beloved black cat, Lucy, had died. Devastated, I begged my parents: we need to get another Lucy. They... |
9389045c-3b60-4322-bf5d-4db2e45ffc3d | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Prototype of Using GPT-3 to Generate Textbook-length Content
The code is all open source (see the Github). As an example for how this performs, here is **The Art of Better Thinking: Overcoming Cognitive Biases and Unlocking Rationality.** To read the full book (and have slightly improved formatting), you can view it [... |
adddfd4a-117a-496c-bada-9ebd14e45158 | trentmkelly/LessWrong-43k | LessWrong | Human-Aligned AI Summer School: A Summary
(Disclaimer: this summary is incomplete and does not accurately represent all the content presented at the summer school, but only what I remember and seem to have understood from the lectures. Don't hesitate to mention important ideas I missed or apparent confusion.)
Last we... |
36660dee-5140-475e-8ebc-3a88c5ba51a0 | trentmkelly/LessWrong-43k | LessWrong | Proper scoring rules don’t guarantee predicting fixed points
Johannes Treutlein and Rubi Hudson worked on this post while participating in SERI MATS, under Evan Hubinger's and Leo Gao's mentorship respectively. We are grateful to Marius Hobbahn, Erik Jenner, and Adam Jermyn for useful discussions and feedback, and to ... |
cbc64f21-8b5f-4b39-b7b3-57c82cc44c51 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Dallas, TX
Discussion article for the meetup : Dallas, TX
WHEN: 22 February 2015 01:00:00PM (-0600)
WHERE: 5026 Addison Circle, Addison, TX 75001
We will be meeting up at Pastazios Pizza on Sunday, Feb 22nd at 1 PM. Look for a sign that says "Less Wrong" on it.
Discussion article for the meetup : Dallas,... |
6b1149ec-38f0-4eb4-9e55-09f33cbf503a | trentmkelly/LessWrong-43k | LessWrong | Progress links digest, 2023-07-28: The decadent opulence of modern capitalism
Opportunities
* Applications are still open for The Roots of Progress Blog-Building Intensive, through Aug 11. Launch a blog, get into a regular writing habit, improve your writing, and begin building your audience
* Longevity startup Loya... |
510a28ec-18fc-491f-a366-e5b7deeb4af0 | trentmkelly/LessWrong-43k | LessWrong | Implications of automated ontology identification
Financial status: supported by individual donors and a grant from LTFF.
Epistemic status: early-stage technical work.
This write-up benefited from conversations with John Wentworth.
----------------------------------------
Outline
* This write-up is a response to... |
f9ec3d42-94af-493f-b3c8-0f0fbdd0ec94 | StampyAI/alignment-research-dataset/blogs | Blogs | Historic trends in altitude
*Published 7 Feb 2020*
Altitude of objects attained by man-made means has seen six discontinuities of more than ten years of progress at previous rates since 1783, shown below.
| | | | |
| --- | --- | --- | --- |
| **Year** | **Height (m)** | **Discontinuity (years)** | **Entity**... |
9e4c1e34-0f7c-4a19-a5f7-12eeb646b661 | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post3762
A putative new idea for AI control; index here . In a previous post , I briefly mentioned translations as one of three possible counterfactuals for indifference. Here I want to clarify what I meant there, because the idea is interesting. Imagine that there is a button, which, if a human presses it (event ... |
e5247db5-e3db-4a58-ba30-86aa2dfde38d | trentmkelly/LessWrong-43k | LessWrong | Events Booking New Callers?
A friend asked whether anyone else had noticed a pattern where big contra dance events were generally booking more established callers since restarting. This could make a lot of sense: the established callers will be less "overplayed" than they had been, and many events will be less robust ... |
2bbab4ab-eef6-4a76-98ef-00adddbf31ef | trentmkelly/LessWrong-43k | LessWrong | The problem of Pop Analogy
There is a very good article pinned to the start of Less Wrong at the time I am writing this, where the author starts by pointing out that human beings ‘run on corrupted hardware.’
This is a tech analogy, which might be meant to point at that homo sapiens have not evolved to live in the env... |
c2e5d248-2a69-4bc0-aa57-a77edade6506 | trentmkelly/LessWrong-43k | LessWrong | Perhaps vastly more people should be on FDA-approved weight loss medication
[Epistemic Status: I feel pretty good about most of this, but the life-years-saved-via-medication part is problematic on a number of levels, as pointed out by a few commenters. I include it since back-of-the-envelope calculations serve a pur... |
4e131648-c5e0-4983-9435-1f1a55b8dc1d | trentmkelly/LessWrong-43k | LessWrong | Usable implementation of IDA available
Paul Christiano published his and Buck Shlegeris' implementation at https://github.com/paulfchristiano/amplification. It's the code behind the article Supervising strong learners by amplifying weak experts.
With William Saunders' permission, I published a version modified by him... |
fa74abf0-94fc-4774-953f-8f57783432d7 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Where are people thinking and talking about global coordination for AI safety?
Many AI safety researchers these days are not aiming for a full solution to AI safety (e.g., the classic Friendly AI), but just trying to find good enough partial solutions that would buy time for or otherwise help improve global coordinati... |
7855917b-4201-489e-a441-dad7830283ea | trentmkelly/LessWrong-43k | LessWrong | What's the Value of Information?
I posted this problem to my own blog the other day. When I posted it, I thought it looked very easy, more fiddly than difficult:
> The eccentric millionaire Oswald Mega walks into a bar and he says:
>
> "This morning, I was showing my newborn about Dungeons and Dragons. We took a ... |
88e02bdd-dfe0-420b-92c4-51526d14607d | trentmkelly/LessWrong-43k | LessWrong | Philosophy of Numbers (part 2)
A post in a series of things I think would be fun to discuss on LW. Part one is here.
----------------------------------------
I
As it turns out, I asked my leading questions in precisely the reverse order I'd like to answer them in. I'll start with a simple picture of how we evaluate... |
db0e4ffa-a1e1-4312-9227-53398f556723 | trentmkelly/LessWrong-43k | LessWrong | What do you value ?
In light of all of the talk about AI, utility functions, value alignment etc. I decided to spend some time thinking about what my actual values are. I encourage you to do the same (yes both of you). Lower values on the list are less important to me but not qualitatively less important. For example ... |
607c25ba-dff2-4670-bc20-a6e4749beb09 | trentmkelly/LessWrong-43k | LessWrong | Good News for Immunostimulants
Epistemic Status: Moderate
Way back in 2015 I was writing about the connection between cancer remissions and the immune response to infection. To recap the facts:
* A plurality of recorded spontaneous cancer remissions happened when the patient had a strong immune response (often with... |
af5fb0bc-4f85-4f68-9e76-622dbd4c9a03 | trentmkelly/LessWrong-43k | LessWrong | Privileging the Hypothesis
,
Suppose that the police of Largeville, a town with a million inhabitants, are investigating a murder in which there are few or no clues—the victim was stabbed to death in an alley, and there are no fingerprints and no witnesses.
Then, one of the detectives says, “Well… we have no idea who... |
a6e46480-b419-4bbd-94b6-7aaad44a55eb | trentmkelly/LessWrong-43k | LessWrong | How good is spending?
In classic microeconomics, both parties benefit from transactions:
* Buyers receive a "consumer surplus" measured by the maximum amount they would've been willing to pay versus the actual price.
* Sellers receive a "producer surplus" measured by the minimum amount at which they would've been w... |
73df2aa8-ea3d-4d96-bc66-ce7197ff487a | trentmkelly/LessWrong-43k | LessWrong | Can you force a neural network to keep generalizing?
I want to share an idea about how we could try to force a neural network to come with bigger and bigger generalizations. Potentially reaching abstractions similar to human abstractions.
Disclaimer: I'm not an expert.
In general
Here's the general idea of the req... |
d891cd7d-e6d2-43d9-b583-ea6ff4e0dd25 | trentmkelly/LessWrong-43k | LessWrong | Are imaginary and complex numbers of decibans meaningful?
It's well-established that 0 decibans means 1:1 odds or 50% confidence; that 10 decibans means 10:1 odds; that -10 decibans means 1:10 odds; and that fractional numbers of decibans have similar meaning.
Does it make sense to talk about "i decibans", or "10 + 2... |
4ae08d0a-b2ba-4dd7-adb7-e0c1ded02829 | trentmkelly/LessWrong-43k | LessWrong | Genesis
Book review: Genesis: Artificial Intelligence, Hope, and the Human Spirit, by Henry A. Kissinger, Eric Schmidt, and Craig Mundie.
Genesis lends a bit of authority to concerns about AI.
It is a frustrating book. It took more effort for me read than it should have taken. The difficulty stems not from complex s... |
a9f6b6f1-ba8a-4183-8742-30884a07d09d | trentmkelly/LessWrong-43k | LessWrong | Renormalization Redux: QFT Techniques for AI Interpretability
Introduction: Why QFT?
In a previous post, Lauren offered a take on why a physics way of thinking is so successful at understanding AI systems. In this post, we look in more detail at the potential of Quantum field theory (QFT) to be expanded into a more co... |
b2fe9ac8-d998-4d59-99ca-3ad56d253881 | trentmkelly/LessWrong-43k | LessWrong | “Why can’t you just turn it off?”
If you're so worried about AI risk, why don't you just turn off the AI when you think it's about to do something dangerous?
On Friday, Members of the OpenAI board including Ilya Sutskever decided that they wanted to "turn off" OpenAI's rapid push towards smarter-than-human AI by firi... |
e0ab78fe-4dce-40cc-a08a-ac96495897c8 | trentmkelly/LessWrong-43k | LessWrong | Technical Claims
A blue plastic maple leaf. Detailed observations in words with clear meaning signal their truth, as it's hard to get them centrally wrong by mistake, on both sides of communication. There is no maple leaf, but only because the claim is intentionally false, not because of a mistake. Technical claims, t... |
0a1cac53-b271-4d0e-885f-c93e5151653c | StampyAI/alignment-research-dataset/arbital | Arbital | Multiplication of rational numbers (Math 0)
We've seen how to [add](https://arbital.com/p/55m) and [subtract](https://arbital.com/p/56x) pairs of [rational numbers](https://arbital.com/p/4zq).
But the [natural numbers](https://arbital.com/p/45h) have another operation on them: multiplication.
Remember, a given ration... |
f5f3c35e-b261-4169-bb9c-29e0144da20e | trentmkelly/LessWrong-43k | LessWrong | [Talk transcript] What “structure” is and why it matters
This is an edited transcription of the final presentation I gave for the AI safety camp cohort of early 2024. It describes some of what the project is aiming for, and some motivation. Here's a link to the slides. See this post for a more detailed and technical o... |
b3989c77-7c49-4ee7-a89f-fa25653d483d | StampyAI/alignment-research-dataset/lesswrong | LessWrong | How to pursue a career in technical AI alignment
(Crossposted at the [EA forum](https://forum.effectivealtruism.org/posts/7WXPkpqKGKewAymJf/how-to-pursue-a-career-in-technical-ai-alignment).)
**This guide is written for people who are considering direct work on technical AI alignment.**I expect it to be most useful f... |
2d10f7c5-f59d-45ed-b10a-f1b91ff3b1d1 | trentmkelly/LessWrong-43k | LessWrong | Do LLMs sometime simulate something akin to a dream?
When dreaming we sometimes simulate a very different person than our waking self, we can make decisions uncharacteristic of our own, we can experience a world very different then waking reality, and even sometime get implanted with memories we never experienced.
An... |
9ebdb787-a232-4e7e-9783-b7b6d36fbe69 | trentmkelly/LessWrong-43k | LessWrong | What Does Make a Difference? It’s Really Simple
This is really simple:
Suppose you want to check if some action of yours makes a difference.
How to do it?
The wrong thing to do:
Think of the consequences of your action and evaluate them to see if they fit your purposes. If they do, go on and do it.
The reason for thi... |
b5cabe12-4b50-4c21-9314-21f98bf88d3b | trentmkelly/LessWrong-43k | LessWrong | Optimum number of single points of failure
1. Optimum number of single points of failure
Summary of entire Series: An alternative approach to designing Friendly Artificial Intelligence computer systems.
Summary of this Article: The number of unnecessary Single Points of Failure in your design should be minimised; ... |
fbb30ec3-766c-43cc-b014-92b8a6881806 | trentmkelly/LessWrong-43k | LessWrong | A brief collection of Hinton's recent comments on AGI risk
Since I've seen some people doubt whether (original popularizer of the backpropagation algorithm and one of the original developers of deep learning) Geoff Hinton is actually concerned about AGI risk (as opposed to e.g. the NYT spinning an anti-tech agenda in ... |
4355ba09-ed88-4462-a135-6021c6832ad2 | trentmkelly/LessWrong-43k | LessWrong | Embarrassment and Instinct
Imagine you're staying in a hotel alone, and you take a shower before breakfast. Out of habit you sing in the shower, and, well, you're not much of a singer. Going to breakfast, you run into the couple in the room next door. The walls are thin, and you can tell by their looks that they're no... |
c6291c0e-6962-40ac-90a9-53732f78b049 | trentmkelly/LessWrong-43k | LessWrong | Can homo-sapiens sustain an economy parallel to AI's?
In a world where taxis and trucks drive themselves, code writes itself etc. there's several ways humans can fit into such picture.
Perhaps they'll get rich by owning shares, perhaps UBI will be introduced, perhaps they'll move to jobs higher-in-abstraction-ladder u... |
9615890f-b3fe-4dda-99a4-092502177d5e | trentmkelly/LessWrong-43k | LessWrong | Does NYT have policies?
Does the New York Times have written policies? Does it publish them? Have they leaked?
Here is a list of six public documents. Most interesting are the Ethical Journalism Guidebook/Handbook and the Guidelines on [Our] Integrity. The first mentions three documents: (A) "the Newsroom Integrity S... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.