id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
5b60c2ef-c2ba-4c8f-b969-f354e1593c64 | trentmkelly/LessWrong-43k | LessWrong | Current thoughts on Paul Christano's research agenda
This post summarizes my thoughts on Paul Christiano's agenda in general and ALBA in particular.
----------------------------------------
(note: at the time of writing, I am not employed at MIRI)
(in general, opinions expressed here are strong and weakly held)
A... |
ad890537-d847-416e-befb-1d7f6fb26e25 | trentmkelly/LessWrong-43k | LessWrong | Reference Classes
Epistemic Status: Just some thoughts off the top of my head
Fake Nous recently featured an article on agent-centered evidence:
> Sue had a premonition about the flight, and then the plane crashed. For Sue, that’s pretty strong evidence of precognition. We would completely understand Sue’s resolutio... |
3b0a3251-305f-4993-ac82-0fa4a04cf608 | trentmkelly/LessWrong-43k | LessWrong | Post Fit Review
My idea here is to have a post where we can discuss thoughts on how well particular posts fit LW without cluttering the post's own comments. StackExchange sites do something similar where reviewers will sometimes post in meta to discuss posts they were unsure if they should perform moderation on, altho... |
75952dba-d24a-445c-8edc-73aee2b3ffc9 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | How Josiah became an AI safety researcher
*Cross-posted from the* [*EA Forum*](https://forum.effectivealtruism.org/posts/wqw5gK2A84By8GxEf/how-josiah-became-an-ai-safety-researcher)*.*
Audio recording of my interview with [Josiah Lopez-Wild](https://josiahlopezwild.com/):
<https://www.youtube.com/watch?v=KODX3pp28QM... |
dff44be7-b1c2-44a3-bdb1-9bccff74efd2 | trentmkelly/LessWrong-43k | LessWrong | Using Prediction Markets to Guide Government Policy
Using Prediction Markets to Guide Government Policy
If you use prediction markets to determine government policy then rational (and irrational) actors will manipulate the prediction markets in order to manipulate government policy. If you use prediction markets to p... |
2e7ccfed-d927-422d-9d44-fd6cab767fdf | trentmkelly/LessWrong-43k | LessWrong | [link] Aubrey de Grey answers Reddit AMA in video
Aubrey de Grey, Chief Science Officer of the SENS Foundation, has posted a video with answers to some of the questions posed at him in a recent Reddit AMA.
Link: http://www.youtube.com/watch?v=6eet44YacRg |
79350703-22d4-4e63-80a6-5afc5d79b831 | trentmkelly/LessWrong-43k | LessWrong | Uninfluenceable learning agents
A putative new idea for AI control; index here.
After explaining riggable learning processes, we can now define influenceable (and uninfluenceable) learning processes.
Recall that the (unriggable) influence problem is due to agents randomising their preferences, as a sort of artificia... |
12a0a785-6276-4b28-8489-30fb7c16c12b | trentmkelly/LessWrong-43k | LessWrong | Efficiency spectra and “bucket of circuits” cartoons
This is “Part I.75” of my series on the memorization-generalization spectrum and SLT.
I’m behind on some posts, so I thought I would try to explain, in a straightforward and nontechnical way, the main takeaway from my previous post for people thinking about and run... |
94a47a29-2533-491e-9b08-158c8d5f9b5c | trentmkelly/LessWrong-43k | LessWrong | Publishing industry contacts, anyone?
I finished a novel last September, did most of the editing over Christmas, and have been procrastinating ever since. My novel has significant rationalist themes and would probably be of interest to a number of people here. Below is a plot synopsis. If you would be interesting in r... |
fb5820d7-bcae-443d-84f6-598b76024937 | trentmkelly/LessWrong-43k | LessWrong | Intuition and Mathematics
While reading the answer to the question 'What is it like to have an understanding of very advanced mathematics?' I became curious about the value of intuition in mathematics and why it might be useful.
It usually seems to be a bad idea to try to solve problems intuitively or use our intuiti... |
081a448f-914c-41e4-885e-5d266b813225 | trentmkelly/LessWrong-43k | LessWrong | Map Of Effective Altruism
In the spirit of my old map of the rationalist diaspora, here’s a map of the effective altruist movement:
Continents are cause areas; cities are charities or organizations; mountains are individuals. Some things are clickable links with title-text explanations. Thanks to AG for helping me ... |
e82346be-abf8-4c0a-96aa-bc1764963c00 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Budapest Meetup
Discussion article for the meetup : Budapest Meetup
WHEN: 21 April 2012 05:30:00PM (+0100)
WHERE: 1061 Budapest, Andrássy út 2.
PLEASE NOTE the changed venue: Costa Coffee, Andrássy út 2. link.
Please come and bring friends. If you have questions, contact katyusha.
BudLW mailing list: lin... |
31ebcddc-744e-47a3-9f5e-723d74a5b894 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | 121 - Artificial Stupidity
I was told you guys have access to it
beforehand so how many of you actually
read it I've written all details ok I
assume some of you didn't read it so
that is still a reason for me to present
about it I know my students never read
anything they don't even buy textbooks
so I assume if it's n... |
a65a0b6f-72f9-484c-a3fb-094a7386a025 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Some Variants of Sleeping Beauty
The Sleeping Beauty problem is a classic conundrum in the philosophy of self-locating uncertainty. From [Elga (2000)](https://www.princeton.edu/~adame/papers/sleeping/sleeping.pdf):
> **Sleeping Beauty**. Some researchers are going to put you to sleep. During the two days that your s... |
659467bb-3815-4a92-8175-13d993f90f38 | trentmkelly/LessWrong-43k | LessWrong | 2016 LessWrong Diaspora Survey Analysis: Part One (Meta and Demographics)
2016 LessWrong Diaspora Survey Analysis
Overview
* Results and Dataset
* Meta
* Demographics (You are here)
* LessWrong Usage and Experience
* LessWrong Criticism and Successorship
* Diaspora Community Analysis
* What it all means... |
ea3ec26d-36f6-4942-b7f0-46a79be9cfa1 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Safe Reinforcement Learning with Natural Language Constraints
1 Introduction
---------------
Although reinforcement learning (RL) has shown promise in several simulated domains such as games [mnih2015dqn](#bib.bib1) ; [silver2007reinforcement](#bib.bib2) ; [branavan2012learning](#bib.bib3) and autonomous navigatio... |
80cf104b-a3c4-447b-9ce3-f2b1000341d6 | trentmkelly/LessWrong-43k | LessWrong | Heading Toward: No-Nonsense Metaethics
Part of the sequence: No-Nonsense Metaethics
A few months ago, I predicted that we could solve metaethics in 15 years. To most people, that was outrageously optimistic. But I've updated since then. I think much of metaethics can be solved now (depending on where you draw the bou... |
7acf8436-ff4e-4eb3-b22a-bacb00f9d736 | StampyAI/alignment-research-dataset/blogs | Blogs | Ruediger Schack on quantum Bayesianism
 [Ruediger Schack](https://www.ma.rhul.ac.uk/rschack) is a Professor at the [Department of Mathematics](https://www.royalholloway.ac.uk/mathematics/home.aspx) at [Royal Holloway, Univer... |
c22f3d6f-cd94-4969-a7eb-eab888099055 | trentmkelly/LessWrong-43k | LessWrong | Are explanations that explain more phenomena always more unlikely than narrower versions?
The classic example of a hypothesis explaining more being less likely would of course be conspiracy theories, where adherents add more and more details under the false assumption that this makes the theory more likely rather than... |
53d962bd-7ab6-4ed8-ba9e-7ecb9e67a8da | trentmkelly/LessWrong-43k | LessWrong | Fun with +12 OOMs of Compute
Or: Big Timelines Crux Operationalized
What fun things could one build with +12 orders of magnitude of compute? By ‘fun’ I mean ‘powerful.’ This hypothetical is highly relevant to AI timelines, for reasons I’ll explain later.
Summary (Spoilers):
I describe a hypothetical scenario that co... |
6559fec8-40fe-4041-bbb8-82fcf0a735df | trentmkelly/LessWrong-43k | LessWrong | Anthropic answers to logical uncertainties?
Suppose that if the Riemann Hypothesis were true, then some complicated but relatively well-accepted corollary involving geometric superstring theory and cosmology means that the universe would contain 10^500 times more observers. Suppose furthermore that the corollary argum... |
894be016-f5f8-4731-a773-025243acb15d | trentmkelly/LessWrong-43k | LessWrong | Deception Strategies
The following is an introductory-level summary of the basic ideas of my “Hive-Mind” paper in the first chapter:
It is a given that society is driven by people who perform various socially-sanctioned jobs. We will refer to these jobs as “tasks.” A task is performed by a group of task-performers. I... |
81ad095a-c393-4d69-b847-758742f0e147 | trentmkelly/LessWrong-43k | LessWrong | Money Pump Arguments assume Memoryless Agents. Isn't this Unrealistic?
I have been reading about money pump arguments for justifying the VNM axioms, and I'm already stuck at the part where Gustafsson justifies acyclicity. Namely, he seems to assume that agents have no memory. Why does this make sense?[1] To elaborate:... |
b4184e64-d645-4a98-9b3c-c8af78a3ef33 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Singapore September 2011
Discussion article for the meetup : Singapore September 2011
WHEN: 03 September 2011 04:00:00PM (+0800)
WHERE: 23 folkstone road, Singapore
Hi, I haven't seen a Singapore meetup posted here and would like to know if any lw-ers in Singapore are interested in meeting up (and why won'... |
f72b4b66-f3f7-4459-b238-0c345c951c02 | trentmkelly/LessWrong-43k | LessWrong | In praise of fake frameworks
Related to: Bucket errors, Categorizing Has Consequences, Fallacies of Compression
Followup to: Gears in Understanding
I use a lot of fake frameworks — that is, ways of seeing the world that are probably or obviously wrong in some important way.
I think this is an important skill. There... |
e6b96219-11d0-4481-a97c-fdde807066a1 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Rationality Meetup Vienna
Discussion article for the meetup : Rationality Meetup Vienna
WHEN: 18 July 2015 03:00:00PM (+0200)
WHERE: Kaisermühlenstraße 24/2
Event with more details on Facebook: https://www.facebook.com/events/1580071008920988/ (Have to be part of Rationality Vienna to see it)
Discussion ... |
d5b3c556-6980-4df7-ab92-804781455207 | trentmkelly/LessWrong-43k | 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... |
cc30a4e6-03f3-434e-bb4c-c475ff8278b3 | trentmkelly/LessWrong-43k | LessWrong | Updates to Open Phil’s career development and transition funding program
(cross-posted from the Effective Altruism Forum)
We’ve recently made a few updates to the program page for our career development and transition funding program (recently renamed, previously the “early-career funding program”), which provides su... |
57d9a26e-897d-4cbd-a855-7795b5dcfed4 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Brain Breakthrough! It's Made of Neurons!
Today's post, Brain Breakthrough! It's Made of Neurons! was originally published on 01 April 2008. A summary (taken from the LW wiki):
> Eliezer's contribution to Amazing Breakthrough Day.
Discuss the post here (rather than in the comments to the original pos... |
56be7cc4-bf10-49ca-95f0-7a80cc07f98d | trentmkelly/LessWrong-43k | LessWrong | Briefly Extending Differential Optimization to Distributions
I've done some work on a definition of optimization which applies to "trajectories" in deterministic, differentiable models. What happens when we try and introduce uncertainty?
Suppose we have the following system consisting of three variables, the past P, ... |
ce239524-4762-4c0d-bd27-e47db0eb1081 | trentmkelly/LessWrong-43k | LessWrong | Alien parasite technical guy
Custers & Aarts have a paper in the July 2 Science called "The Unconscious Will: How the pursuit of goals operates outside of conscious awareness". It reviews work indicating that people's brains make decisions and set goals without the brains' "owners" ever being consciously aware of the... |
b44b5d10-5a66-4066-8e71-002637efbde2 | trentmkelly/LessWrong-43k | LessWrong | Gamified psychiatry
I have been thinking about the gamification of psychiatry and the rise of mental health apps as a means to motivate behaviours that improve mental health and flourishing. I put together some indications and left a diagram here for my good friends Anne Osognosia and Alex Ithemyia who want to upgrade... |
611d0d1c-25bb-45f2-91c0-2950ff77e502 | trentmkelly/LessWrong-43k | LessWrong | Pittsburgh Less Wrong meet-up April 22 7pm
We'll be gathering at the Starbucks at 417 South Craig Street at 7:00 PM. |
5e3063fa-600e-427b-bd27-a5fe61e5ca37 | trentmkelly/LessWrong-43k | LessWrong | Happy paths and the planning fallacy
The other day at work I was talking with my boss about a project I am working on. He wanted an update on what tasks are remaining. I spent some time walking him through this. At the end, he asked, "So just to confirm, these six tasks are all that is remaining for this project?".
I... |
d8681b6c-f972-44fc-aa5f-b6ee1a6e67f4 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Disentangling arguments for the importance of AI safety
*Note: my views have shifted significantly since writing this post. I now consider items 1, 2, 3, and 6.2 to be different facets of one core argument, which I call the "second species" argument, and which I explore in depth in [this report](https://www.alignmentf... |
05c1a551-850a-4bce-83e7-f4696e0fc341 | trentmkelly/LessWrong-43k | LessWrong | Active Recovery
If you believe you've caught the virus, what are some beginning steps to take to start initial recovery? What are there changes to diet, foods to avoid, or supplements to take? At this rate, it feels as though infections will no longer be uncommon so adapting to better safety and lifestyle habits will ... |
7fa45385-74a2-4fe4-85aa-5e6de92d19af | trentmkelly/LessWrong-43k | LessWrong | Robustness to fundamental uncertainty in AGI alignment
Publication cycles are long, so I've talked about some of the ideas in this paper before, but since it's freshly out in print, I thought I'd take the chance to share it and summarize its contents for those who don't want to slog through an entire academic paper. I... |
3d44c432-6a55-487f-8c44-d408bdbee1fa | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Testing Ways to Bypass ChatGPT's Safety Features
[Cross post from my blog at <https://aizi.substack.com/>, links to the original tweets are there]
Last week OpenAI released [ChatGPT](https://openai.com/blog/chatgpt/), which they describe as a model “which interacts in a conversational way”. And it even had limited sa... |
61f4dbde-ec38-49bc-8b69-cfaf4196702f | StampyAI/alignment-research-dataset/arbital | Arbital | Real number
A **real number** is any number that can be used to represent a physical quantity.
Intuitively, real numbers are any number that can be found between two [integers](https://arbital.com/p/48l), such as $0,$ $1,$ $-1,$ $\frac{3}{2},$ $\frac{-7}{2},$ [$\pi,$](https://arbital.com/p/49r) [$e$](https://arbital.... |
dbb6f4ec-bc2e-4d1e-addb-08607e46a189 | trentmkelly/LessWrong-43k | LessWrong | Trends – Artificial Intelligence
May 30, 2025
Mary Meeker / Jay Simons / Daegwon Chae / Alexander Krey
BOND |
c156c842-8ec8-49fe-9cce-d9dc021dc988 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Deep reinforcement learning from human preferences
1 Introduction
---------------
Recent success in scaling reinforcement learning (RL) to large problems
has been driven in domains that have a well-specified reward function (Mnih et al., [2015](#bib.bib29), [2016](#bib.bib30); Silver et al., [2016](#bib.bib37)).
Un... |
990f9ea9-cd55-4117-a5bf-8b330300a0f5 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Conditions for Superrationality-motivated Cooperation in a one-shot Prisoner's Dilemma
Summary
=======
It has been argued that, if two very similar agents follow decision theories allowing for [superrationality](https://www.lesswrong.com/tag/superrationality) (e.g., [EDT](https://www.lesswrong.com/tag/evidential-deci... |
ee8b858b-9115-4553-abd9-86d3a8cd19b5 | StampyAI/alignment-research-dataset/arbital | Arbital | Proof of Bayes' rule
Bayes' rule (in the [odds form](https://arbital.com/p/1x5)) says that, for every pair of hypotheses $H_i$ and $H_j$ and piece of evidence $e,$
$$\dfrac{\mathbb P(H_i)}{\mathbb P(H_j)} \times \dfrac{\mathbb P(e \mid H_i)}{\mathbb P(e \mid H_j)} = \dfrac{\mathbb P(H_i \mid e)}{\mathbb P(H_j \mid e)... |
1c483d0a-a9d1-4d3f-a346-93b2389360a9 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | 6:How to Build a Safe Advanced AGI?: Evan Hubinger 2023
okay so uh yeah so this is the the last
lecture so today we are going to be
talking about uh how to build a safe
Advanced AI
um
so we're not quite going to be doing
that uh because I don't know how to do
that but we are going to be talking
about some ways that pe... |
6be20d65-e104-4df7-9049-6f6e45138575 | trentmkelly/LessWrong-43k | LessWrong | Newsletter for Alignment Research: The ML Safety Updates
Introducing the ML Safety Updates
TLDR; We present a new AI safety update series in podcast, YouTube and newsletter format released weekly to stay updated in alignment and ML safety research and get exposed to Ai safety opportunities. Read the latest newsletter ... |
4cd60c00-30ee-4b93-b4cb-0532f7f012db | trentmkelly/LessWrong-43k | LessWrong | I'm trying out "asteroid mindset"
This is a personal note, and not an advocation that anyone do the same. I'm honestly not really sure why I'm writing it. I think I just want to talk about it in a place where other people might feel similarly or have useful things to say.
Like many others, the past few months of AI a... |
7a0352e2-5b14-46be-bfad-b72deb1829be | trentmkelly/LessWrong-43k | LessWrong | Soviet-era Jokes, Common Knowledge, Irony
None |
26ee1d67-ae2b-4778-aeae-cd87f8df3ad4 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | How much should governments pay to prevent catastrophes? Longtermism’s limited role
Preamble
--------
* We use standard cost-benefit analysis (CBA) to argue that governments should do more to reduce global catastrophic risk.
* We argue that getting governments to adopt a CBA-driven catastrophe policy should be the go... |
68951a25-9530-409b-9df0-bf4438cfa56e | trentmkelly/LessWrong-43k | LessWrong | AXRP Episode 2 - Learning Human Biases with Rohin Shah
YouTube link
This podcast is called AXRP, pronounced axe-urp and short for the AI X-risk Research Podcast. Here, I (Daniel Filan) have conversations with researchers about their papers. We discuss the paper and hopefully get a sense of why it's been written and h... |
23fddb3a-692e-40f8-97f8-d2e5e178b146 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Doom doubts - is inner alignment a likely problem?
After reading Eliezer's list of lethalities, I have doubts (hopes?) that some of the challenges he mentions will occur.
Let's start with inner alignment. Let's think step by step. 😁
1. Inner alignment is a new name for a long-known challenge of many systems. Whethe... |
ad205d4a-8dad-4ae7-8e7a-cc9ac2bb0f02 | trentmkelly/LessWrong-43k | LessWrong | The RPG Thread
I thought maybe playing RPG's might help us get to know each other outside meet-ups. Specifically, I found this particular game of interest to this community: it is in many ways the antithesis of everything we stand for... which is why I think we rationalists, of all people, would appreciate it the most... |
fd07b321-c2c7-4525-8162-668a3c0ad70f | StampyAI/alignment-research-dataset/arbital | Arbital | Transcendental number
summary: A *transcendental* number $z$ is one such that there is no (nonzero) [https://arbital.com/p/-polynomial](https://arbital.com/p/-polynomial) function which outputs $0$ when given $z$ as input. $\frac{1}{2}$, $\sqrt{6}$, $i$ and $e^{i \pi/2}$ are not transcendental; $\pi$ and $e$ are both ... |
6f058b41-1429-4b4a-a8c1-90aa05bfe578 | trentmkelly/LessWrong-43k | LessWrong | Training Regime Day 0: Introduction
Introduction
The sad truth of life is that there is a difference between knowing how to do something and actually being able to do it. Knowledge about how various instrumental rationality techniques work is not a substitute for actually being able to use them in practice. As the sto... |
ffaa6c3d-6704-4703-a823-2745c3ea13ac | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | What counts as defection?
*Thanks to Michael Dennis for proposing the formal definition; to Andrew Critch for pointing me in this direction; to Abram Demski for proposing non-negative weighting; and to Alex Appel, Scott Emmons, Evan Hubinger, philh, Rohin Shah, and Carroll Wainwright for their feedback and ideas.*
*T... |
decb498f-1b16-499c-be22-c18baa8ceb93 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | The Opt-In Revolution — My vision of a positive future with ASI (An experiment with LLM storytelling)
I writing and publishing a story to better clarify my vision for a positive future with transformative AI (or AGI/ASI). The story is written in chapters, and is still being put together piece by piece. Each chapter is... |
3eb30f12-5684-4f12-8e89-88a83726ac6d | StampyAI/alignment-research-dataset/arxiv | Arxiv | Certified Adversarial Robustness via Randomized Smoothing
1 Introduction
---------------
x
pA–––
¯¯¯¯¯¯pB
Figure 1: Illustration of randomized smoothing. Left: the decision regions of the base classifier f are drawn in different ... |
37de4283-b577-4e57-87f8-cc8b06399dfc | trentmkelly/LessWrong-43k | LessWrong | Open Thread, Feb. 2 - Feb 8, 2015
If it's worth saying, but not worth its own post (even in Discussion), then it goes here.
Previous Open Thread
----------------------------------------
Notes for future OT posters:
1. Please add the 'open_thread' tag.
2. Check if there is an active Open Thread before posting a ne... |
0fd41a58-b32c-4cde-869e-1c82b6b12cfe | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Terry Tao is hosting an "AI to Assist Mathematical Reasoning" workshop
The workshop is on 12-14 June, following a [previous workshop](https://terrytao.wordpress.com/2022/10/21/upcoming-workshop-on-machine-assisted-proofs-at-ipam/) on "Machine-assisted proofs" held last Feb.
Maybe an opportunity to nerd snipe him and... |
bd44ca70-1951-44d7-b57f-701a7eab2231 | trentmkelly/LessWrong-43k | LessWrong | Three ways interpretability could be impactful
Epistemic status: somewhat confident that overall these arguments show interpretability could be impactful, but not confident on any individual point.
Background: I wrote a draft of this post here after reading Charbel’s work. Thanks to Charbel and several others’ feedba... |
057c8611-2485-4c10-9a8b-be7e05b3b242 | trentmkelly/LessWrong-43k | LessWrong | What would the FLI moratorium actually do?
I read a lot of agreement with the six months memorandum and very little discussion of the details and what the proposed memorandum would actually do.
The memorandum says 'we call on all AI labs to immediately pause for at least 6 months the training of AI systems more power... |
3c1e7fa0-e54a-42f0-9d10-2e0264041e5f | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Into AI Safety Episodes 1 & 2
I have now released Episode 1 and Episode 2 of the Into AI Safety Podcast! Currently it is available on the [Into AI Safety](https://into-ai-safety.github.io/) website, and Spotify ([show link](https://open.spotify.com/show/5AGzrA4jo6mgZuibVabTLM?si=394c56d8792b4b9a)).
I would consider E... |
f620a4b6-e517-483e-86c2-fab8aa0d841f | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Implications of Quantum Computing for Artificial Intelligence alignment research (ABRIDGED)
I recently co-authored a paper with Pablo Moreno, *Implications of Quantum Computing for Artificial Intelligence alignment research*, which can be accessed through [arXiv](https://arxiv.org/abs/1908.07613).
Our paper focuses ... |
c7a99a65-10ed-4238-b251-eb6d2ddb3662 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Bielefeld Meetup, January 23rd
Discussion article for the meetup : Bielefeld Meetup, January 23rd
WHEN: 23 January 2013 07:00:00PM (+0100)
WHERE: Grill/Bar Verve, Klosterplatz 13, Bielefeld
We are meeting once again in Bielefeld.
The topics of this evening will be the current series "Highly Advanced Epis... |
5ea576e8-a3a9-4737-b4f1-c11553bc2ada | StampyAI/alignment-research-dataset/arbital | Arbital | Shift towards the hypothesis of least surprise
The [log-odds form of Bayes' rule](https://arbital.com/p/1zh) says that strength of belief and strength of evidence can both be measured in [bits](https://arbital.com/p/3y2). These evidence-bits can also be used to measure a quantity called "Bayesian surprise", which yiel... |
ab30a1e2-6d2a-4fa2-b7fe-98274d350b97 | trentmkelly/LessWrong-43k | LessWrong | Melbourne meetup discussion: Contrarian positions
NOTE: This post is a stub for the comments below. Please don't participate in the voting unless you think it likely that you will attend the next Melbourne, Australia meetup (Friday Aug 5, 7pm).
The next Melbourne meetup may feature a moderated, rationality-policed no... |
5dabfc22-9f2e-4bcc-b48b-a1fd23f75e51 | StampyAI/alignment-research-dataset/blogs | Blogs | October 2015 Newsletter
| |
| --- |
|
**Research updates**
* New paper: [Asymptotic Logical Uncertainty and The Benford Test](https://intelligence.org/2015/09/30/new-paper-asymptotic-logical-uncertainty-and-the-benford-test)
* New at IAFF: [Proof Length and Logical Counterfactuals Revisited](https://agentfoundation... |
2341d506-ff8b-4b99-9bd1-d4fa2eef1f76 | trentmkelly/LessWrong-43k | LessWrong | Truth is holistic
You already know by now that truth is undefinable: by a famous result of Tarski, no formal system powerful enough (from now on, just system) can consistently talk about the truth of its own sentences.
You may however not know that Hamkins proved that truth is holistic.
Let me explain: while no syste... |
d15b759e-41c0-472d-b0cb-59c4f2b82605 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Paper: Identifying the Risks of LM Agents with an LM-Emulated Sandbox - University of Toronto 2023 - Benchmark consisting of 36 high-stakes tools and 144 test cases!
Paper: <https://arxiv.org/abs/2309.15817>
Github: <https://github.com/ryoungj/toolemu>
Website: <https://toolemu.com/>
Abstract:
> Recent advances i... |
a68c93d6-2bc7-4d48-9151-f14f0c131fb5 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Garden grove meetup
Discussion article for the meetup : Garden grove meetup
WHEN: 22 May 2012 07:18:15PM (-0700)
WHERE: Brookhurst and Garden Grove 10130 Garden Grove Blvd, Garden Grove, CA 92844
At Genki Living. For Snacks and Drinks with light discussion on how to properly have a meetup and what to meetu... |
e0af0f97-85a2-464a-816e-b070efb08089 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Urbana-Champaign: TRVTH
Discussion article for the meetup : Urbana-Champaign: TRVTH
WHEN: 16 November 2014 02:00:00PM (-0600)
WHERE: 206 S. Cedar St. Urbana IL
How good would knowing the truth be, if we were perfect enough to use it?
How irrational do we have to be before lying to ourselves is a good idea... |
e55e4766-9e43-476b-9597-704624d1c497 | trentmkelly/LessWrong-43k | LessWrong | [Link] TEDx talk of Anders Sandberg on the Fermi "paradox"
Anders Sandberg, Where are they?, TEDxUHasselt.
> On the long term, how much change in the universe can a civilization possibly cause? In this talk, Anders Sandberg brings an enthusiastic introduction to the different scenarios of the Fermi paradox and what t... |
823178b8-baf5-4f8f-ade6-b69ac9e2be19 | trentmkelly/LessWrong-43k | LessWrong | singinst reading recommendations
Whatever happened to all of these pages and pages of reading recommendations? I had to go wayback to 2007 |
8dea4bd3-a8ae-45a7-910f-5e80cfbe7dbf | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Trying out Prompt Engineering on TruthfulQA
*I try out "let's gather the relevant facts" as a zero-shot question answering aid on TruthfulQA. It doesn't help more than other helpful prompts. Possibly it might work better on more typical factual questions.*
*This post could potentially be useful to people interested i... |
bf631e41-a698-43f5-885d-93fc23fd8c0b | trentmkelly/LessWrong-43k | LessWrong | Optimal predictors and conditional probability
|
1280e8a9-c2c4-4a1b-b81a-ad23971eb9a0 | trentmkelly/LessWrong-43k | LessWrong | Fake Causality
Phlogiston was the eighteenth century’s answer to the Elemental Fire of the Greek alchemists. Ignite wood, and let it burn. What is the orangey-bright “fire” stuff? Why does the wood transform into ash? To both questions, the eighteenth-century chemists answered, “phlogiston.”
. . . and that was it, yo... |
bccddef8-be44-4250-8608-fbadad83077b | StampyAI/alignment-research-dataset/lesswrong | LessWrong | AI Risk in Terms of Unstable Nuclear Software
*(This is an entry for* [*the AI Safety Public Materials contest*](https://www.lesswrong.com/posts/gWM8cgZgZ9GQAYTqF/usd20k-in-bounties-for-ai-safety-public-materials) *testing out a novel-ish* [*frame on the AI Risk*](https://www.lesswrong.com/posts/m3fyWQgCcFwro5KQh/refr... |
f6b9c333-98ec-44fb-9eb1-121eb49f7fee | StampyAI/alignment-research-dataset/arxiv | Arxiv | Safe AI -- How is this Possible?
Safe AI
Seite 1 von 44 Safe AI – How is this possible?1 Harald Rueß fortiss Research Institute of the Free State of Bavaria for Software-Intensive Systems ruess@fortiss.org Simon Burton Fraunhofer Institute for Cognitive Systems simon.burton@iks.fraunhofer.de Munich, ... |
12c63b72-8b58-4006-a7a9-c403698af2f4 | trentmkelly/LessWrong-43k | LessWrong | [AN #147]: An overview of the interpretability landscape
Alignment Newsletter is a weekly publication with recent content relevant to AI alignment around the world. Find all Alignment Newsletter resources here. In particular, you can look through this spreadsheet of all summaries that have ever been in the newsletter.... |
280117f5-b38d-44f5-bfc3-dd85b3c779ff | trentmkelly/LessWrong-43k | LessWrong | Notes on the importance and implementation of safety-first cognitive architectures for AI
Background
I've been working on a knowledge management/representation system for ~1.5 years with the initial goal of increasing personal and collective intelligence. I discovered that this work could be highly applicable to AI sa... |
98581e5f-df28-408b-a0eb-55e76d274e0e | trentmkelly/LessWrong-43k | LessWrong | Modelling Social Exchange: A Systematised Method to Judge Friendship Quality
Introduction
Evolution has designed humans to be empathetic to help others, and grateful to give back in a mutually beneficial transaction. Unfortunately, not all series of exchanges are fair long-term.
Whether these relationships are worth ... |
7b9a771f-a7b8-4bb5-9f54-b35dea1637cf | trentmkelly/LessWrong-43k | LessWrong | Ideologies are slow and necessary, for now
Thinking through an ideology makes one dumber than they would otherwise be. Nevertheless, they remain an important tool for scaling coordination on beliefs.
How can we do better?
Just an essay detailing this dynamic. |
5c29974f-cbc4-42e5-8691-f5c17be4d536 | trentmkelly/LessWrong-43k | LessWrong | The problem of other minds
Originally posted at Bearlamp.com.au: http://bearlamp.com.au/the-problem-of-other-minds/ (also Greaterwrong)
I'm trapped in here and you are trapped in there.
It's an odd problem. How do we communicate when we are each locked in our own Chinese room.
In computing terms - a handshake allow... |
264c5ab7-e487-4660-9475-62edb0429c16 | trentmkelly/LessWrong-43k | LessWrong | Harry Potter and the Methods of Rationality discussion thread, part 13, chapter 81
This is a new thread to discuss Eliezer Yudkowsky’s Harry Potter and the Methods of Rationality and anything related to it. This thread is intended for discussing chapter 81, which should be published later today. The previous thread pa... |
ae330f4d-ea6f-4c09-97cd-8ee43b47549c | trentmkelly/LessWrong-43k | LessWrong | On excluding dangerous information from training
Introduction
In this short post, I would like to argue that it might be a good idea to exclude certain information – such as cybersecurity and biorisk-enabling knowledge – from frontier model training. I argue that this
1. is feasible, both technically and socially;
... |
a658dfda-2913-493c-b1f8-dd2e7c5bd609 | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post1964
So a few posts ago I looked at the problem of not being able to anticipate all consequences of an action as being related to deceptive mesaoptimization, but also outer alignment too. This post digs more into some of the things I only touched on briefly in that post. Editor’s note: I’m experimenting with h... |
56aaab1c-e3c3-4341-b8aa-acfc1690ccc8 | trentmkelly/LessWrong-43k | LessWrong | Who looked into extreme nuclear meltdowns?
Here’s a scenario:
1. Electricity grids fail across one or more continents for a year. This could happen because right now the Earth magnetic field is weakening, and could eventually let through a corona burst that damages hard-to-replace voltage transformers. See intervi... |
591d155b-2243-43cb-9a27-33bf0f7b3e40 | trentmkelly/LessWrong-43k | LessWrong | The things we know that we know ain't so
We're all familiar with false popular memes that spread faster than they can be stomped out: You only use 10% of your brain. Al Gore said he invented the internet. Perhaps it doesn't surprise you that some memes in popular culture can't be killed. But does the same thing ha... |
6ca0c1bf-82c0-44aa-8309-f3c37a01e1d8 | trentmkelly/LessWrong-43k | LessWrong | Rhythm Stage Setup Components
I typically play what I'm calling my "rhythm stage setup", though it needs a better name. It's a keyboard, foot drums, breath controller, and whistle-controlled synthesizer, connected with code I write, that lets me give a full and varied sound while keeping the control and flexibility to... |
9831bec3-01b0-4e1b-8eb9-577eebe03255 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Offline Reinforcement Learning as One Big Sequence Modeling Problem
1 Introduction
---------------
The standard treatment of reinforcement learning relies on decomposing a long-horizon problem into smaller, more local subproblems.
In model-free algorithms, this takes the form of the principle of optimality (bellman... |
4d89fe28-f81a-43b7-b63c-0838770d987f | trentmkelly/LessWrong-43k | LessWrong | The Genetics of Space Amazons
If you wanted to colonize other planets with meat suite humans, then females are the superior choice as they have lower nutritional needs. Here I imagine a fictional Amazon gene that could lead to a skewed sex ratio favoring females.
Background
* Human Females need less food than male... |
dd00e313-92b8-4a6d-ab41-263a045fc5b8 | trentmkelly/LessWrong-43k | LessWrong | Rationality Quotes 9
"A world ought to have a few genuine good guys, and not just a spectrum of people running from bad to worse."
-- Glen Cook, A Shadow of All Night Falling
"You couldn't get a clue during the clue mating season in a field full of horny clues if you smeared your body with clue musk and did t... |
0942c798-85b6-432a-aa5f-60411931dedb | trentmkelly/LessWrong-43k | LessWrong | A kind or reverse "tragedy of the commons" - any solution ideas?
I have recently come across a very practical example of a kind of "tragedy of the commons" - the unwillingness to invest in assets that benefit stakeholders indiscriminately. Specifically, on large strata-title apartment projects there is a reluctance to... |
b1907cb3-80ae-40ad-9993-3755a0cd0455 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Strategic implications of AIs' ability to coordinate at low cost, for example by merging
It seems likely to me that AIs will be able to coordinate with each other much more easily (i.e., at lower cost and greater scale) than humans currently can, for example by merging into coherent unified agents by combining their u... |
4c8e0b8b-ca52-45ad-9b53-c07276fc2928 | trentmkelly/LessWrong-43k | LessWrong | [DISC] Are Values Robust?
Epistemic Status
Discussion question.
Related Posts
See also:
* Complexity of Value
* Value is Fragile
* The Hidden Complexity of Wishes
* But exactly how complex and fragile?
----------------------------------------
Robust Values Hypothesis
Consider the following hypothesis:
1... |
1fd3be48-d559-400d-af1a-62607f3c3601 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Optimization and Adequacy in Five Bullets
*Context: Quite recently,* [*a*](https://www.lesswrong.com/s/oLGCcbnvabyibnG9d)[*lot*](https://www.neelnanda.io/blog/mini-blog-post-22-the-8020-rule)[*of*](https://www.lesswrong.com/posts/6s3xABaXKPdFwA3FS/what-is-evidence)[*ideas*](https://www.lesswrong.com/tag/complexity-of-... |
fec5e610-0b51-4866-8604-2242a86edb2c | trentmkelly/LessWrong-43k | LessWrong | A compilation of misuses of statistics
Statistics are hard. The more statistics I learn the harder the discipline seems. To truly extract insight form data using statistical methods one has to take many factors and nuances into account, and I discover new ones very week. This is the reason much of the studies publishe... |
edd89d2e-541c-4255-9e73-eb9abcbac926 | trentmkelly/LessWrong-43k | LessWrong | Convoy Crackdown
The convoy has been dispersed. Yet Tyler Cowen was clearly correct that this will be a very important event. The story has barely begun.
[Writer’s Note: This post violates some of the usual lines that I set for myself regarding politics, because I do not know how to communicate the situation without ... |
e587fafe-92da-46f4-986b-3e017bf6eb6d | trentmkelly/LessWrong-43k | LessWrong | Meetup : Meetup 15 (for real this time) - Trigger Action Planning
Discussion article for the meetup : Meetup 15 (for real this time) - Trigger Action Planning
WHEN: 16 April 2017 03:10:01PM (+0200)
WHERE: Meester Treublaan 18, 1097 DP Amsterdam, Netherlands
I'll do it at some point.
I'll answer this message later.... |
c20b7283-89d1-44ac-9f34-c8f2103b1e48 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Phlogiston was the eighteenth century’s answer to the Elemental Fire of the Greek alchemists. Ignite wood, and let it burn. What is the orangey-bright “fire” stuff? Why does the wood transform into ash? To both questions, the eighteenth-century chemists answered, “phlogiston.”. . . and that was it, you see, that was t... |
99792bb2-4910-423f-acfe-52d038d497a4 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | 123 - Robin Hanson on AI Skepticism
initiate conversation and if I could ask
people to mute the microphones please
I'm here I was just waiting until the
sign down dead Sunday died down sorry
anyway so I'm not sure how you'll manage
like who initiates a question and how
somebody raises their hand but I presume
you've w... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.