id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
66f8a59f-a967-45f6-845f-43ccb6409a66 | trentmkelly/LessWrong-43k | LessWrong | Meetup : West LA Meetup - Nomic
Discussion article for the meetup : West LA Meetup - Nomic
WHEN: 09 May 2012 07:00:00PM (-0700)
WHERE: 10850 West Pico Blvd, Los Angeles, CA 90064
When: 7:00pm - 9:00pm Wednesday, May 9th.
Where: The Westside Tavern in the upstairs Wine Bar (all ages welcome), located inside the Wes... |
3070a778-9310-46b7-8c6f-ea6b17a2c2e6 | trentmkelly/LessWrong-43k | LessWrong | [Linkpost] Building Altruistic and Moral AI Agent with
Brain-inspired Affective Empathy Mechanisms
Abstract
> As AI closely interacts with human society, it is crucial to ensure that its decision-making is safe, altruistic, and aligned with human ethical and moral values. However, existing research on embedding ethic... |
9006b312-244b-4a14-a388-8f4c2be541c5 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Winners-take-how-much?
The treatments I have seen to date of the "winner-takes-all'' dynamic in AI development focus on the risk-taking engendered by this dynamic: the more AI researchers have to gain from being early movers, the stronger the incentive to cut corners in safety measures. Concern about a result in which... |
b1c0ace6-92c5-49a4-a1df-9b65543f9a96 | trentmkelly/LessWrong-43k | LessWrong | Funding Good Research
Series: How to Purchase AI Risk Reduction
I recently explained that one major project undergoing cost-benefit analysis at the Singularity Institute is that of a scholarly AI risk wiki. The proposal is exciting to many, but as Kaj Sotala points out:
> This idea sounds promising, but I find it ha... |
ad0e8b5b-54c7-4f4e-875e-04a5ac899527 | trentmkelly/LessWrong-43k | LessWrong | 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 efficiencies wi... |
895915d3-bf8c-4ecf-8bc3-5fd21879017a | StampyAI/alignment-research-dataset/blogs | Blogs | AGI Ruin: A List of Lethalities
### Preamble:
(If you’re already familiar with all basics and don’t want any preamble, skip ahead to [Section B](https://intelligence.org/feed/?paged=2#Section_B_) for technical difficulties of alignment proper.)
I have several times failed to write up a well-organized list of reaso... |
768f1b8e-94d2-4705-bc96-bd871f46ac3a | trentmkelly/LessWrong-43k | LessWrong | Biases: An Introduction
Imagine reaching into an urn that contains seventy white balls and thirty red ones, and plucking out ten mystery balls.
Perhaps three of the ten balls will be red, and you’ll correctly guess how many red balls total were in the urn. Or perhaps you’ll happen to grab four red balls, or some othe... |
c8b09c88-3a58-4f6c-8130-4866199ec4c8 | trentmkelly/LessWrong-43k | LessWrong | Open Thread for February 11 - 17
If it's worth saying, but not worth its own post (even in Discussion), then it goes here. |
d7766d8a-d31d-4676-8f23-779c45e04ffc | trentmkelly/LessWrong-43k | LessWrong | Stopping dangerous AI: Ideal US behavior
Disclaimer: this post doesn't have the answers. Moreover, it's an unfinished draft. Hopefully a future version will be valuable, but that will only occur if I revise/rewrite it. For now you're better off reading sources linked from AI policy ideas: Reading list and Slowing AI: ... |
38052a90-d4f9-4590-82da-ca2b7d7e5d21 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Yudkowsky on AGI ethics
A Cornell computer scientist recently wrote on social media:
> [...] I think the general sense in AI is that we don't know what will play out, but some of these possibilities are bad, and we need to start thinking about it. We are plagued by highly visible people ranging from Musk to Ng paint... |
30df1ac6-4674-456a-9f10-684370d5c33d | trentmkelly/LessWrong-43k | LessWrong | Meetup : Philadelphia-- Debugging in Meatspace
The discussion prompt William Burroughs's "The discipline of DE (do easy)"
http://melancholia.typepad.com/melancholia/2009/07/do-easy.html
WHEN: 23 February 2014 01:00:00PM (-0500)
WHERE: Nam Phuong, 11th & Broad St., Philadelphia, PA
Meets every two weeks. Forum/mail... |
f6bd2c64-32ae-4727-bb6f-1661bd7afd32 | trentmkelly/LessWrong-43k | LessWrong | mental number lines
This paper says:
> it was shown that second-grade children unevenly placed numbers on a 0–1000 number line as their placement pattern was best fit by a logarithmic rather than by a linear function. The same age group placed numbers more linearly (i.e., resulting in a constant distance between cons... |
cfaeb8da-8cc2-4df0-81f7-fe4b8258e051 | trentmkelly/LessWrong-43k | LessWrong | Debate update: Obfuscated arguments problem
This is an update on the work on AI Safety via Debate that we previously wrote about here.
Authors and Acknowledgements
The researchers on this project were Elizabeth Barnes and Paul Christiano, with substantial help from William Saunders (who built the current web interfa... |
e5c745ff-b55f-45b4-84e5-76b9a4426eab | StampyAI/alignment-research-dataset/arbital | Arbital | Needs work
Meta tag for pages which need content improvement. |
1a5e7633-99df-4043-a9fa-04d7cdae8b7f | trentmkelly/LessWrong-43k | LessWrong | [Link] A superintelligent solution to the Fermi paradox
Here.
Long story short, it's an attempt to justify the planetarium hypothesis as a solution to the Fermi paradox. The first half is a discussion of how it and things like it are relevant to the intended purview of the blog, and the second half is the meat of the... |
3548049b-e392-4faf-804a-891801fb7dbf | StampyAI/alignment-research-dataset/arxiv | Arxiv | Formal Definition of AI
1Formal Definition of AI
Dimiter Dobrev
dobrev@2-box.net
18 October, 2005
Abstract
A definition of Artificial Intelligence was propose d in [1] but this definition was not
absolutely formal at least because the word "Human" was used. In this paper we will
formalize the definition from [... |
45f6d720-2174-44d0-bd71-8eac1be6438a | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Chat GPT's views on Metaphysics and Ethics
Was playing around with chat gpt and and some fun learning about its thoughts on metaphysics. It looks like the ego is an illusion and hedonistic utilitarianism is too narrow minded to capture all of welfare. Instead, it opts for principles of beneficence, non-maleficence, au... |
be44bd19-12c6-4751-ab66-876b5bec82b4 | trentmkelly/LessWrong-43k | LessWrong | A Positive Double Standard—Self-Help Principles Work For Individuals Not Populations
This story is reposted from nonzerosum.games where it appears in it’s intended form, full colour with functioning interactive elements, jump over to the site for the authentic experience.
I have a confession: As a teenager I was de... |
21d4e381-f681-4f21-a607-3d334cd56787 | trentmkelly/LessWrong-43k | LessWrong | Conditioning, Counterfactuals, Exploration, and Gears
,,,,,,,,,,
The view of counterfactuals as just conditioning on low-probability events has a lot going for it. To begin with, in a bayesian setting, updates are done by conditioning. A probability distribution, conditioned on some event x (an imaginary update), and ... |
6cf82e30-deec-42a4-b9ab-5b5185d58208 | trentmkelly/LessWrong-43k | LessWrong | Dealing with the left overs: COVID-19
A recent news story highlighted how China's next bit COVID-19 challenge is how to deal with all the contaminated trash that comes as a result of dealing with the epidemic.
Clearly China has a lot more to deal with but this is not something other countries wont have to face as wel... |
c0d084fd-4826-42b5-a076-23e4090ace65 | trentmkelly/LessWrong-43k | LessWrong | Ontologies are Operating Systems
Ontologies are Operating Systems: Post-CFAR 1
[I recently came back from volunteering at a CFAR workshop. I found the whole experience to be 100% enjoyable, and I’ll be doing an actual workshop review soon. I also learned some new things and updated my mind. This is the first in a four... |
d669cba6-2c49-4de9-8580-e1799d97a10b | trentmkelly/LessWrong-43k | LessWrong | AI Safety Strategies Landscape
The full draft textbook is available here. This document constitutes the Chapter 3.
Introduction
tldr: Even if we still don't know how to make AI development generally safe, many useful classes of strategies already exist, which are presented in this chapter. You can look at the table ... |
5b0f9202-20d6-440c-a25a-9603db009598 | trentmkelly/LessWrong-43k | LessWrong | The Great Filter isn't magic either
A post suggested by James Miller's presentation at the Existential Risk to Humanity conference in Gothenburg.
Seeing the emptiness of the night sky, we can dwell upon the Fermi paradox: where are all the alien civilizations that simple probability estimates imply we should be seein... |
e00bd717-4b34-499f-b55a-f8d7cefbadeb | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Newcomb Variant
There are two boxes. If you open a box, you get to keep the contents.
Omega is an omniscient oracle. Omega predicts what will happen if you open the first box and observe that it contains $100.
* If Omega predicts that you will open the second box, then Omega puts $0 in both boxes.
* If Omega predi... |
32bf5776-a13d-417a-bf59-422db2964c1f | trentmkelly/LessWrong-43k | LessWrong | Calling all Nigerian rationalists and effective altruists
I'm in Lagos, Nigeria till the end of May and I'd like to hold a LessWrong/EA meetup while I'm here. If you'll ever be in the country in the future (or in the subcontinent), please get in touch so we can coordinate a meetup. I'd also appreciate being put in con... |
11b8d9df-2a35-4640-8263-27f5baccca51 | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | What is AI Safety via Debate?
**Debate** is a proposed technique for allowing human evaluators to get correct and helpful answers from experts, even if the evaluator is not themselves an expert or able to fully verify the answers.[^7clr966emb9] The technique was suggested as part of an approach to build advanced AI sy... |
e074b681-e62c-454e-b9ee-9f64a88554ca | trentmkelly/LessWrong-43k | LessWrong | Has LessWrong been a good early alarm bell for the pandemic?
The S&P 500 began to crash on Feb. 20th.
On or prior to that date, there were 6 posts on LessWrong related to COVID-19 (thanks to habryka, who found 3 that I'd missed).
Jan 20 - Rationalist prepper thread
Jan 26 - Concerning the Recent 2019-Novel Coronavi... |
e716cb26-1db2-48ad-bce5-47555641b14d | trentmkelly/LessWrong-43k | LessWrong | Friendly AI - Being good vs. having great sex
> [...] I think an LW post is important and interesting in proportion to how much it helps construct a Friendly AI, how much it gets people to participate in the human project [...]
-- Eliezer Yudkowsky
> I’m not going to wait for philosophers to cover this issue correct... |
4740f25a-dea7-4f6c-be97-843754e42d24 | trentmkelly/LessWrong-43k | LessWrong | Inexistence of Rational Disagreement when Information can be Freely Exchanged
Suppose rationality is a set of principles that people agreed on to process information then arrive at conclusions. Then, on the basis of cost-free information exchange, should rational disagreements still exist? In that case, both parties w... |
79d3a55c-c408-4761-880c-14a069d55d06 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Beware safety-washing
Tl;dr: don’t be fooled into thinking that some groups working on AI are taking “safety” concerns seriously (enough).[[1]](#fn6zkt67gme6q)
**Outline**
* [Two non-AI examples](https://forum.effectivealtruism.org/posts/f2qojPr8NaMPo2KJC/beware-safety-washing#Two_non_AI_examples)
+ [Greenwashing](... |
63be28e3-27c6-4445-8f8d-93fe6abd5dba | trentmkelly/LessWrong-43k | LessWrong | Police violence: The veil of darkness
Measuring police bias using simple ratios doesn't work. You can never cleanly separate the impact of race from other factors associated with race.
Instead, I want augmented-reality goggles that make race invisible. Then we could run the following experiment:
* Have half of poli... |
bbd65d6a-ba4a-4f4a-bec0-dc1dda1844c6 | trentmkelly/LessWrong-43k | LessWrong | Outline of an approach to AGI Estimation
We are worried about what will happens when we make a system that can do the important things that human can do, like programming and science. Will it explode off into infinity as it finds better ways to improve itself or will it be a slower more manageable process? There are a... |
fac56cc3-7cff-4ec1-afd9-49715f1cb040 | trentmkelly/LessWrong-43k | LessWrong | How can I argue without people online and not come out feeling bad?
I wont be the only one here who "wastes time" arguing about things they care about online (note: I am referring to web forums and things like subreddits, I am not including Less Wrong whose dynamic is completely different). It seems like something tha... |
381ef11b-3e8b-4165-b0ef-da1d4b04e11a | trentmkelly/LessWrong-43k | LessWrong | Neural network polytopes (Colab notebook)
The polytope theory of neural networks (also known as the "spline theory of deep learning") seeks to explain (ReLU) neural networks based on their piecewise linear regions. This gives a helpful intuition for how neural networks approximate functions, as well as a potential ave... |
28ae9704-d523-4676-be23-a865eae83d3a | trentmkelly/LessWrong-43k | LessWrong | Meetup : Dallas - Fort Worth Less Wrong Meetup 4/29/12
Discussion article for the meetup : Dallas - Fort Worth Less Wrong Meetup 4/29/12
WHEN: 29 April 2012 01:00:00PM (-0500)
WHERE: America's Best Coffee, Arlington
I apologize for the short notice. The Dallas / Fort Worth metroplex area desperately needs a Less Wr... |
62525f5a-8397-4bf1-b716-6a0266b615a9 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Autonomy as taking responsibility for reference maintenance
I think semantics – specifically, maintaining reference relationships – is a core component of intelligent behaviour. Consequently, I think a better understanding of semantics would enable a better understanding of what machine intelligence that is “trying to... |
da185df1-5901-442d-bcb8-b39fb66416e9 | trentmkelly/LessWrong-43k | LessWrong | Clarifying AI X-risk
TL;DR: We give a threat model literature review, propose a categorization and describe a consensus threat model from some of DeepMind's AGI safety team. See our post for the detailed literature review.
The DeepMind AGI Safety team has been working to understand the space of threat models for exis... |
1e126eda-db52-4647-9c38-6eee51a78e0e | StampyAI/alignment-research-dataset/arxiv | Arxiv | Relational recurrent neural networks
1 Introduction
---------------
Humans use sophisticated memory systems to access and reason about important information regardless of when it was initially perceived ([schacter1994memory,](#bib.bib1) ; [knowlton2012neurocomputational,](#bib.bib2) ). In neural network research ma... |
9c99d55e-82f8-477e-8ac2-d412c256744a | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] The Apocalypse Bet
Today's post, The Apocalypse Bet, was originally published on 09 August 2007. A summary (taken from the LW wiki):
> If you think that the apocalypse will be in 2020, while I think that it will be in 2030, how could we bet on this? One way would be for me to pay you X dollars every year ... |
08545fe3-9efb-4fe6-8973-ae778d23cd8b | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | Value Alignment | Stuart Russell
so the first question is what is a good
decision anyway an economist will tell
you that it means maximizing your
expected over the whole future utility
and this applies to everything from
lottery tickets to Davos meetings to
building radio telescopes on maximizing
AI has made a great d... |
0eb69a3e-0502-4127-8ce3-437a332836fb | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Did AI pioneers not worry much about AI risks?
It's seems noteworthy just how little the AI pioneers from the 40s-80s seemed to care about AI risk. There is no obvious reason why a book like "Superintelligence" wasn't written in the 1950s, but for some reason that didn't happen... any thoughts on why this was the case... |
6ea6ec3c-7df7-494e-9685-8c8d587cd042 | trentmkelly/LessWrong-43k | LessWrong | London meetup, Sunday 2011-08-21 14:00, near Holborn
We're meeting up in London tomorrow. Sunday 21st August, at 2pm, in the Shakespeares Head (official page) on Kingsway near Holborn Tube station. See you there! |
59361f13-42f4-4368-b1d8-4a5fb25def0f | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | 243. A General Language Assistant as a Laboratory for Alignment
hello and welcome to session
243 in the ai safety.com reading group
tonight we'll be discussing the article
a general language assistant as a
laboratory for alignment by jared kaplan
and many others
this is the first work done by anthropic
new alignment r... |
0cf16a07-731c-434e-b93b-aa89b3f011a8 | trentmkelly/LessWrong-43k | LessWrong | Are Your Enemies Innately Evil?
We see far too direct a correspondence between others’ actions and their inherent dispositions. We see unusual dispositions that exactly match the unusual behavior, rather than asking after real situations or imagined situations that could explain the behavior. We hypothesize mutants.
... |
007b4ae2-e187-445b-a8a8-21601b1b1bb7 | trentmkelly/LessWrong-43k | LessWrong | “Pivotal Act” Intentions: Negative Consequences and Fallacious Arguments
tl;dr: I know a bunch of EA/rationality-adjacent people who argue — sometimes jokingly and sometimes seriously — that the only way or best way to reduce existential risk is to enable an “aligned” AGI development team to forcibly (even if nonviole... |
4de80b98-36c5-47d9-8a96-406952286455 | trentmkelly/LessWrong-43k | LessWrong | Examine self modification as an intuition provider for the concept of consciousness
(epistemic status: this direction of thought is pretty strongly endorsed by me, but not very thoroughly expressed/developed, I'm working on it)
This post is kind of a mess, and made out of pieces of discussions I had in many places, ... |
f9a1c360-da53-48ec-aef1-3f027ffe7e03 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | How much EA analysis of AI safety as a cause area exists?
AI safety has become a big deal in EA, and so I'm curious about how much "due diligence" on it has been done by the EA community as a whole. Obviously there have been many in-person discussions, but it's very difficult to evaluate whether these contain new or h... |
23c71ed7-ac75-494e-9410-c6b2a40844f7 | trentmkelly/LessWrong-43k | LessWrong | The strongest status signals
The community’s awareness and strong understanding of status-motivated behavior in humans is clearly evident. However, I still believe the community focuses too much on a small subset of observable status transactions; namely, status transactions that occur between people of approximately ... |
150d930b-b30a-4f9d-ada9-99f0030087e6 | trentmkelly/LessWrong-43k | LessWrong | Do IQ tests measure intelligence? - A prediction market on my future beliefs about the topic
I created a market on the meaning of IQ tests. Would be curious to hear arguments.
The text of the market also contains my initial position on the question. |
0145ec1c-0a72-48de-a96e-d8d455cae125 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Washington, D.C.: Sharing Book Excerpts
Discussion article for the meetup : Washington, D.C.: Sharing Book Excerpts
WHEN: 13 December 2015 03:00:00PM (-0500)
WHERE: Reynolds Center
x-posted from list. Gathering in courtyard from 3:00pm, hard start 3:30pm - until closing (7:00 pm).
We'll be meeting to read... |
8d7223a7-00b0-4364-8a86-525bc1848757 | trentmkelly/LessWrong-43k | LessWrong | I'm still mystified by the Born rule
(This post was originally intended as a comment on Adele's question, but ballooned to the point where it seems worthy of a top-level post. Note that I'm not trying to answer Adele's (specific fairly-technical) question here. I consider it to be an interesting one, and I have some g... |
95bf9489-d3ff-4955-818f-844e65582c55 | StampyAI/alignment-research-dataset/blogs | Blogs | Parsing by counterfactual
---
Table of Contents* [Detecting semantic conditions](#detecting-semantic-conditions)
* [Example](#example)
* [Single-token counterfactuals](#single-token-counterfactuals)
* [Applications](#applications)
* [Code](#code)
+ [tokenizing](#tokenizing)
+ [conditional probability of a target](#... |
3c20156a-9b29-4676-ac10-8941c6abe619 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Research agenda - Building a multi-modal chess-language model
This is one of the posts that detail [my research agenda](/posts/DWWy7oqopwsuN3mpz/my-agenda-for-research-into-transformer-capabilities), which tries to marry Deep Learning and chess to gain insight into current AI technologies.
How "the world", "what the... |
5ed41676-cc04-4f20-8cc4-63831f07f312 | trentmkelly/LessWrong-43k | LessWrong | A hypothesis concerning discounting.
Humans have a value function which is inconsistent over time, discounting roughly with proportion to distance in the future, so that we discount more steeply as an event approaches. This is why we stay up late, ignore the alarm, put off work until close to a deadline, et cetera et ... |
be3c9c00-e237-4d76-9cef-9c7d6c3c61cf | trentmkelly/LessWrong-43k | LessWrong | The principle of genomic liberty
PDF version. berkeleygenomics.org. Twitter thread. (Bluesky copy.)
Summary
The world will soon use human germline genomic engineering technology. The benefits will be enormous: Our children will be long-lived, will have strong and diverse capacities, and will be halfway to the end of... |
ecd5166f-01f4-4162-96db-3916896296b5 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Catastrophic Risks from AI #3: AI Race
*This is the third post in a sequence of posts giving an* [*overview of catastrophic AI risks*](https://arxiv.org/abs/2306.12001)*.*
3 AI Race
=========
The immense potential of AIs has created competitive pressures among global players contending for power and influence. This ... |
4a60d9f3-0f66-4de2-b475-1a59788c0282 | trentmkelly/LessWrong-43k | LessWrong | Second Insight: Repairing My "Repairs" or Aspiring to Rationality instead of "Rationality"
|
76df042d-4974-4bdf-855e-1851a7cd3bff | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Misha Yagudin and Ozzie Gooen Discuss LLMs and Effective Altruism
Misha and I recently recorded a short discussion about large language models and their uses for effective altruists.
This was mostly a regular Zoom meeting, but we added some editing and text transcription. After we wrote up the transcript, both Mi... |
fa399c93-eca4-426e-a0fa-e52908081b53 | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | How is the Alignment Research Center (ARC) trying to solve Eliciting Latent Knowledge (ELK)?
[ARC](https://www.alignment.org/) is trying to solve the problem of [Eliciting Latent Knowledge (ELK)](https://docs.google.com/document/d/1WwsnJQstPq91_Yh-Ch2XRL8H_EpsnjrC1dwZXR37PC8/edit). Suppose that you are training a *pre... |
338e4410-8f63-4fa6-9339-2ace3d482e7e | trentmkelly/LessWrong-43k | LessWrong | Framing AI Childhoods
Generated as part of SERI MATS, under John Wentworth. Thanks to Alex Turner and Garrett Baker for related discussion, and to Justis Mills for draft feedback.
All bold claims and ignorant mistakes herein are my own.
Do you remember when Evan Hubinger became really enamored with 'training stories... |
e924a9b6-981e-4d61-a620-7779a89858fc | trentmkelly/LessWrong-43k | LessWrong | Lessons from Isaac: Poor Little Robbie
Every so often, when explaining issues related to AI safety, I call on good old Asimov. That's easy: almost everyone that is at least interested in science knows his name, and the Three Laws of Robotics are a very good example of misspecified goal. Or are they?
The truth is: I d... |
512f8257-e59c-4f75-8630-7b5b2ceeb773 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Decision theory and dynamic inconsistency
Here is my current take on decision theory:
* When making a decision after observing X, we should condition (or causally intervene) on statements like “My decision algorithm outputs Y after observing X.”
* Updating seems like a *description* of something you do when making g... |
e8adb50b-3c71-4762-a58a-720f3747307f | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Abstraction = Information at a Distance
Why is abstraction useful? Why use a high-level model rather than a low-level model?
An example: when I type “4+3” in a python shell, I think of that as adding two numbers, not as a bunch of continuous voltages driving electric fields and current flows in little patches of meta... |
a70ff9ea-96d4-4a12-b5f1-eba9c0d87492 | trentmkelly/LessWrong-43k | LessWrong | Applied cognitive science: learning from a faux pas
Cross-posted from my LiveJournal:
> Yesterday evening, I pasted to two IRC channels an excerpt of what someone had written. In the context of the original text, that excerpt had seemed to me like harmless if somewhat raunchy humor. What I didn't realize at the time ... |
b77f3785-6f09-4028-ac0e-41589a614e47 | trentmkelly/LessWrong-43k | LessWrong | Visible Thoughts Project and Bounty Announcement
(Update Jan. 12: We released an FAQ last month, with more details. Last updated Jan. 7.)
(Update Jan. 19: We now have an example of a successful partial run, which you can use to inform how you do your runs. Details.)
We at MIRI are soliciting help with an AI-align... |
fdb28187-45c8-4849-ada5-536753144a19 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences
1 Introduction
---------------
Complex machine learning (ML) models such as Deep Neural Networks (DNNs) and Support Vector Machines (SVMs) perform very well on a wide range of tasks [[Lundberg and
Lee2016](#bib.bibx7)], but their ... |
b4898285-60da-45e7-b99e-8d6c0587a945 | trentmkelly/LessWrong-43k | LessWrong | Rebuttal piece by Stuart Russell and FHI Research Associate Allan Dafoe: "Yes, the experts are worried about the existential risk of artificial intelligence."
|
e06a5667-a9a5-40f3-ae9b-8f20c242ed94 | trentmkelly/LessWrong-43k | LessWrong | Aligned AI Needs Slack
(Half-baked)
Much has been said about slack on this site, starting with Zvi's seminal post. The point I couldn't find easily (probably missed) is that an aligned AI would need a fair bit of it. Having a utility function means zero slack: there is one thing you optimize, to the exclusion of ever... |
beceba19-a822-4219-b6b7-575c02c35eaf | trentmkelly/LessWrong-43k | LessWrong | Solomonoff Induction and Sleeping Beauty
Various people have said that Solomonoff Induction (SI) accords with the Self-Sampling Assumption (SSA) more than the Self-Indicating Assumption (SIA). See these posts and the comments on them:
https://www.lesswrong.com/posts/omqnrTRnHs3pSYef2/down-with-solomonoff-induction-up... |
7c5c1eab-cebd-4eb1-a311-f7239ae48cc2 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Rationality Meetup Vienna
Discussion article for the meetup : Rationality Meetup Vienna
WHEN: 14 March 2015 03:00:00PM (+0100)
WHERE: Kaisermühlenstraße 24, 1120 Wien
directions: http://web.student.tuwien.ac.at/~e0326238/rationality_meetup/directions.html
FB-Event for more details and discussions: https:/... |
b4bc997b-6e9c-4b53-a4c9-a3aa51d0a017 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Slide deck: Introduction to AI Safety
This is from a presentation that I've been giving over the past few months to various groups within the Johns Hopkins University Applied Physics Laboratory (APL), where I work. I'd be interested to hear people's comments, critiques, suggestions, etc.
Note that this is a somewhat ... |
5665d64f-3183-4d1a-9fee-165c29264f21 | trentmkelly/LessWrong-43k | LessWrong | LessWrong moderation messaging container
This is a shell post for various comments which I'm using as the source-of-truth for some moderation messaging (currently, what a new user sees when they go to make their first post or comment).
It seemed good to make it public so people could comment on it if they wanted. I'm... |
3d14d84a-348b-4dcc-b120-37eedf74d8dc | trentmkelly/LessWrong-43k | LessWrong | Bing Chat is blatantly, aggressively misaligned
I haven't seen this discussed here yet, but the examples are quite striking, definitely worse than the ChatGPT jailbreaks I saw.
My main takeaway has been that I'm honestly surprised at how bad the fine-tuning done by Microsoft/OpenAI appears to be, especially given tha... |
4164e72f-a9c4-4168-9db2-fe2f49585fdd | trentmkelly/LessWrong-43k | LessWrong | An alignment safety case sketch based on debate
This post presents a mildly edited form of a new paper by UK AISI's alignment team (the abstract, introduction and related work section are replaced with an executive summary). Read the full paper here.
Executive summary
AI safety via debate is a promising method for ... |
f2a4a4f4-03f0-4c08-9710-01326bc2fbbd | trentmkelly/LessWrong-43k | LessWrong | AI alignment landscape
Here (link) is a talk I gave at EA Global 2019, where I describe how intent alignment fits into the broader landscape of “making AI go well,” and how my work fits into intent alignment. This is particularly helpful if you want to understand what I’m doing, but may also be useful more broadly. I ... |
01f82335-7d8c-4ae1-8c55-8d4ab7b52f3c | trentmkelly/LessWrong-43k | LessWrong | An Illustrated Summary of "Robust Agents Learn Causal World Model"
This post was written during Alex Altair's agent foundations fellowship program, funded by LTFF. Thank you Alex Altair, Alfred Harwood, Daniel C for feedback and comments.
Introduction
The selection theorems agenda aims to prove statements of the fol... |
f9c52d57-6242-4692-9c39-64c02199f000 | trentmkelly/LessWrong-43k | LessWrong | AI #65: I Spy With My AI
In terms of things that go in AI updates, this has been the busiest two week period so far. Every day ends with more open tabs than it started, even within AI.
As a result, some important topics are getting pushed to whenever I can give them proper attention. Triage is the watchword.
In part... |
4b9cd03f-8746-4829-afbb-dc033559d316 | trentmkelly/LessWrong-43k | LessWrong | Sentience
Consciousness is primarily sentience. There may be parts of it that aren't, but I haven't managed to pin any down - consciousness all seems to be about feelings, some of them being pleasant or unpleasant, but others like colour qualia are neutral, as is the feeling of being conscious. There is a major proble... |
3188dd02-1055-440e-82ea-ba252cfdf319 | trentmkelly/LessWrong-43k | LessWrong | A New Center? [Politics] [Wishful Thinking]
Political polarization in the USA has been increasing for decades, and has become quite severe. This may have a variety of causes, but it seems highly probable that the internet has played a large role, by facilitating the toxoplasma of rage to an unprecedented degree.
Rece... |
66815859-c3db-4e3a-a527-78f30b94687d | trentmkelly/LessWrong-43k | LessWrong | Abstract Plans Lead to Failure
Epistemic Status: Probably not generalisable to everyone, applies especially strong to me
It's very easy to decide to do something in the abstract on the basis that it should give you some particular skills. Here are some personal examples where I didn't get what I wanted out of my time... |
38d1aa53-2ada-47d9-a495-37acb3ce7b4b | trentmkelly/LessWrong-43k | LessWrong | Dissolution of free will as a call to action
Accepting determinism and the insuing dissolution of free will is often feared as something that would lead to loss of will and fatalism. Gary Drescher and Eliezer spend considerable effort explaining this as a fallacy.
The one thing I don't remember mentioned is the oppo... |
c2ce8153-6655-4d42-ab17-6fca61e3a683 | trentmkelly/LessWrong-43k | LessWrong | My problems with Formal Friendly Artificial Intelligence work
I'm writing this to get information about the lesswrong community and whether it worth engaging. I'm a bit out of the loop in terms of what the LW community is like and whether it can maintain multiple view points (and how known the criticisms are).
The TL... |
1c77e7ce-884d-49a5-b479-a4355c1a61e3 | trentmkelly/LessWrong-43k | LessWrong | Call For Distillers
Many technical alignment researchers are bad-to-mediocre at writing up their ideas and results in a form intelligible to other people. And even for those who are reasonably good at it, writing up a good intuitive explanation still takes a lot of work, and that work lengthens the turn-time on publis... |
29b0806a-c65d-40e9-ade5-5e092422f799 | trentmkelly/LessWrong-43k | LessWrong | Global Workspace Theory
Much research has been done upon visual perception. Humans have the illusion that they are directly aware of everything in their 'field of view', but it turns out that they actually navigate not through reality, but through a model of reality that their brain stitches together mainly from the... |
ac511464-4bb5-4611-962f-f573e3f65b91 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Spreading messages to help with the most important century
In the [most important century](https://forum.effectivealtruism.org/s/isENJuPdB3fhjWYHd) series, I argued that the 21st century could be the most important century ever for humanity, via the development of advanced AI systems that could dramatically speed up s... |
e985f2f8-ac3f-47d7-a8b1-afea74f113c6 | trentmkelly/LessWrong-43k | LessWrong | Safe Predictive Agents with Joint Scoring Rules
Thanks to Evan Hubinger for funding this project and for introducing me to predictive models, Johannes Treutlein for many fruitful discussions on related topics, and Dan Valentine for providing valuable feedback on my code implementation.
In September 2023, I received ... |
147b4b5e-47cd-4e4c-b5e7-70637dcc7560 | trentmkelly/LessWrong-43k | LessWrong | Communicating forecast uncertainty
Note: This post is part of my series of posts on forecasting, but this particular post may be of fairly limited interest to many LessWrong readers. I'm posting it here mainly for completeness. As always, I appreciate feedback.
In the course of my work looking at forecasting for MIRI... |
b3c7e966-244f-49b5-bc30-4ad59114a71d | trentmkelly/LessWrong-43k | LessWrong | Continuing the discussion thread from the MTG post
I moved and copies this discussion out of the latest MTG color-wheel post, since I would prefer the discussion on the post to stay on the object-level.
Commentary by Conor Moreton:
> [Meta/cultural note: as of this writing, the parent comment I made in reply to Cool... |
1760f6dc-980c-4ff1-8086-b534a092799b | StampyAI/alignment-research-dataset/blogs | Blogs | Transformer Circuit Exercises
d-article h2 {border-bottom: none !important;}
d-article h3 {font-size: 26px !important;}
d-article h4 {font-size: 16px !important; margin-top: 30px !important;}
d-article hr {margin-top: 60px; margin-bottom: 80px;}
d-article ul {padding-left: 0px;}
d-article ol {padding-left: 36pt;} ... |
85a78e7d-2e10-459b-801c-facde0431902 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Responsible Deployment in 20XX
The purpose of this post is to briefly talk about two categories of alignment and how I think AI safety evaluations should use them. I only consider responsible deployment in 20XX because I often find discussions about 2XXX to be distracting and unproductive. Also, for the remainder of t... |
75fb5e84-dc67-4dd3-95cd-a12bbc92fa0a | trentmkelly/LessWrong-43k | LessWrong | Meetup : MIT/Boston Secular Solstice
Discussion article for the meetup : MIT/Boston Secular Solstice
WHEN: 11 December 2015 08:00:00PM (-0500)
WHERE: MIT Chapel 50 Massachusetts Ave, Cambridge, Massachusetts 02139
It has become tradition, in the community of those who seek to become more rational, to gather for one... |
4f97ff39-ed93-42f0-9dc8-bc779e777800 | trentmkelly/LessWrong-43k | LessWrong | Follow along with Columbia EA's Advanced AI Safety Fellowship!
Columbia EA is starting an Advanced AI Safety Fellowship this summer, which will involve one 3-hour meeting per week with a group of people seriously considering careers in AI safety who have some background in both ML (at least working knowledge of linear... |
ea98c712-d07c-4c7b-8a98-7afade684156 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Beyond Near- and Long-Term: Towards a Clearer Account of Research Priorities in AI Ethics and Society
1. Introduction
----------------
There is a growing community of researchers focused on ensuring that advances in AI are safe and beneficial for humanity (which we call the AI ethics and society community, or AI E&... |
e6a92372-a161-4d2c-8969-82b35b3d596f | trentmkelly/LessWrong-43k | LessWrong | Paper review: A Cryptographic Solution to a Game Theoretic Problem
Crossposted from: Equilibria Club
It's time for a puzzle involving two fields: game theory and cryptography! Both fields model self-interested agents in a competitive setting. In game theory, we list actions and payoffs, after which we can determine w... |
911ffe82-4d48-4cdc-ab6b-2c257c1a5306 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "If you ever find yourself saying, "Even if Hypothesis H is true, it doesn't have any decision-relevant implications," you are rationalizing! The fact that H is interesting enough for you to be considering the question at all (it's not some arbitrary trivium like the 1923th binary digit of π, or the low temperature in ... |
18a63728-6073-4f46-8b46-66473c06cdd2 | trentmkelly/LessWrong-43k | LessWrong | Voiceofra is banned
I've gotten sufficient evidence from support that voiceofra has been doing retributive downvoting. I've banned them without prior notice because I'm not giving them more chances to downvote.
I'm thinking of something like not letting anyone give more than 5 downvotes/week for content which is more... |
b1c47ffd-2df9-42b4-8c36-6966335d93f8 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Stockholm Slate Star Codex Meetup
Discussion article for the meetup : Stockholm Slate Star Codex Meetup
WHEN: 06 May 2017 01:30:00PM (+0200)
WHERE: café Dox, Stora Nygatan 31, 111 27 Stockholm, Sweden
This is a meetup where we will discuss topics related to the blogg Slate Star Codex, for example rationali... |
664dd716-2968-45e9-ac54-0ce1487124c3 | trentmkelly/LessWrong-43k | LessWrong | Absent Transhumanism and Transformative Technologies, Which Utopia is Left?
Assume for the time being that it will forever remain beyond the scope of science to change Human Nature. AGI is also impossible, as is Nanotech, BioImmortality, and those things.
Douglas Adams mice finished their human experiment, giving to ... |
19f9d17e-a12d-46e6-9d63-398b017d42ae | trentmkelly/LessWrong-43k | LessWrong | Why there are no online CFAR workshops?
As there are many people here here who attended CFAR workshops, I wanted to ask, if you understand why there are no online workshops, even when the in-person workshops were not possible due to the pandemic. In my experience, everything that does not require physical contact (lik... |
92dee6ab-e3a0-4283-98ed-9073f2686276 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Written with much help from Nick Tarleton and Kaj Sotala, in response to various themes here, here, and throughout Less Wrong; but a casual mention here1 inspired me to finally write this post. (Note: The first, second, and third footnotes of this post are abnormally important.)
It seems to have become a trend on Less... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.