id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
cb6e5454-4072-4ebb-9c1d-eb1a086cd839 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Two-year update on my personal AI timelines
I worked on my [draft report on biological anchors for forecasting AI timelines](https://www.lesswrong.com/posts/KrJfoZzpSDpnrv9va/draft-report-on-ai-timelines) mainly between ~May 2019 (three months after the release of GPT-2) and ~Jul 2020 (a month after the release of GPT... |
3a07c8a8-93e5-4cd2-8704-502f9c5a4157 | trentmkelly/LessWrong-43k | LessWrong | Philosophy of mind review
I recently read A Brief Introduction to the Philosophy of Mind, a short undergraduate text. I didn’t understand some bits, but I’m not sure if that’s because the book wasn’t that good or philosophy isn’t or I’m not. Here I list them, for you to enlighten me on:
1. It’s apparently standard to... |
9e4e0897-3d40-4a0e-a012-140d6784cc49 | trentmkelly/LessWrong-43k | LessWrong | The goal of physics
In grad school, I was a teaching assistant for a course called, Why the Sky is Blue. It was a qualitative introduction to physics for non-majors, covering a lot of the same topics as Physics I, such as forces, conservation of energy and momentum, electric charges and magnetic fields, in less detail... |
db75c254-da6b-4316-bd96-0cf06a0bd25c | trentmkelly/LessWrong-43k | LessWrong | Arthur Chu: Jeopardy! champion through exemplary rationality
http://mentalfloss.com/article/54853/our-interview-jeopardy-champion-arthur-chu
I'm not sure I've ever seen such a compelling "rationality success story". There's so much that's right here.
The part that really grabs me about this is that there's no indica... |
5b4b8c91-a7e6-4690-956a-fabb5db22a28 | trentmkelly/LessWrong-43k | LessWrong | Social Presuppositions
During discussion in my previous post, when we touched the subject of human statistical majorities, I had a side-thought. If taking the Less Wrong audience as an example, the statistics say that any given participant is strongly likely to be white, male, atheist, and well, just going by general ... |
0ba4687e-a47d-477f-b956-029448832eba | trentmkelly/LessWrong-43k | LessWrong | Circular Altruism vs. Personal Preference
Suppose there is a diagnostic procedure that allows to catch a relatively rare disease with absolute precision. If left untreated, the disease if fatal, but when diagnosed it's easily treatable (I suppose there are some real-world approximations). The diagnostics involves an u... |
f721e7b4-2887-4199-95e0-332d2d08327a | StampyAI/alignment-research-dataset/blogs | Blogs | A reply to Francois Chollet on intelligence explosion
This is a reply to Francois Chollet, the inventor of the Keras wrapper for the Tensorflow and Theano deep learning systems, on his essay “[The impossibility of intelligence explosion](https://medium.com/@francois.chollet/the-impossibility-of-intelligence-explosion-... |
732482dc-d6c4-478d-a398-5fd6149b96b7 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Expectations for Gemini: hopefully not a big deal
**Introduction**
----------------
My goal is to register and share my expectations and hear others' opinions on their expectation for the relative performances of Gemini VS GPT-4.
**My expectations**
-------------------
GPT-4 to Gemini will likely not be as big a ju... |
9dcb1c23-7d19-4a98-9cd2-716538ba7a5b | trentmkelly/LessWrong-43k | LessWrong | Rival formalizations of a decision problem
Decision theory is not one of my strengths, and I have a question about it.
Is there a consensus view on how to deal with the problem of "rival formalizations"? Peterson (2009) illustrates the problem like this:
> Imagine that you are a paparazzi photographer and that rumou... |
1de45bae-0cdb-4ce9-ac9b-1808dd33b4f0 | trentmkelly/LessWrong-43k | LessWrong | Should I do it?
> Shall we bite the apple?
Hello community, nice to meet you here.
For a long time I have been tormented by a question that I can't seem to answer alone.
Let's talk hypothetically. Let's assume that I have developed a method that can be mapped in a small program. This method, once started, will ... |
bfceeac2-83f5-4abc-9361-62d3d7c0bbd4 | trentmkelly/LessWrong-43k | LessWrong | The rational rationalist's guide to rationally using "rational" in rational post titles
1. Don't. |
52487326-dbee-486d-ba80-42e38f329724 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Values lock-in is already happening (without AGI)
**Summary**
-----------
Algorithms as significant, constant factors in our material lives are very new things. Today, algorithms guide the majority of our social and economic exchanges. Twenty-five years ago, algorithms guided almost no aspect of our daily social and ... |
66f504cc-37a3-4237-837c-3db5ae854cfd | StampyAI/alignment-research-dataset/lesswrong | LessWrong | FC final: Can Factored Cognition schemes scale?
*(Apologies for the long delay.)*
Scaling of Regular Thought
==========================
The punchline of the [previous post](https://www.lesswrong.com/posts/mxmeeGk3mTM7BrT93/intuition) was that there is only one mode of thinking: your brain can solve various tasks i... |
f9fbea6e-5ca3-44ff-bed0-0fcf761da52c | trentmkelly/LessWrong-43k | LessWrong | Notes on "The Limits to Growth" and surrounding material
In 1972, Donella Meadows, Dennis Meadows, Jørgen Randers, and William Behrens III published The Limits to Growth, a book about the consequences of unchecked population growth and economic growth. The book was very popular at the time, selling 12 million copies. ... |
2af7c16e-07e7-41f6-9357-37a937496473 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Sydney Rationality Dojo - October 2016
Discussion article for the meetup : Sydney Rationality Dojo - October 2016
WHEN: 02 October 2016 04:00:00PM (+1000)
WHERE: 10 Shepherd Street, Chippendale
From 4 - 6 we'll be holding our normal rationality dojo at Humanist house. Afterwards there'll be an informal din... |
b486b4db-3ec5-4054-ac13-57d8937da888 | trentmkelly/LessWrong-43k | LessWrong | Consider Trying Dictation
I started using dictation for entering text on my phone and computer when my wrists suddenly went really bad, but while my wrists are enough better that I can often type there are still a lot of cases where I dictate. Even people whose wrists are fine would benefit from trying it out:
* I... |
c9e412f8-06f7-42e3-bee2-10269c1d48ce | trentmkelly/LessWrong-43k | LessWrong | How should I help us achieve immortality?
I was immensely glad to find this community, because while I knew intellectually that I was not the only person who felt that rationality was important, death was bad, and technology was our savior, I had never met anyone else who did. I thus determined my career without much ... |
48be4398-93d4-4122-83bc-cac975725681 | trentmkelly/LessWrong-43k | LessWrong | In a multipolar scenario, how do people expect systems to be trained to interact with systems developed by other labs?
I haven't seen much discussion of this, but it seems like an important factor in how well AI systems deployed by actors with different goals manage to avoid conflict (cf. my discussion of equilibriu... |
1290fc7e-381f-4dc2-ba44-097b3774224b | trentmkelly/LessWrong-43k | LessWrong | What do you believe are the most critical open questions/hypotheses that could inform a more effective COVID response?
None |
ac7a4f6b-c4c9-4f89-a015-41c21fccd5f8 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations
1 Introduction
---------------
The recent success of reinforcement learning (RL) in many domains showcases the great potential of applying this family of learning methods to real-world applications.
A key prerequisite for RL is to desi... |
5506337d-b2b9-457d-8851-dbeb5b881663 | trentmkelly/LessWrong-43k | LessWrong | The Thingness of Things
[Metadata: crossposted from https://tsvibt.blogspot.com/2022/08/the-thingness-of-things.html. I'm fairly likely to not respond to comments promptly. If you're especially interested in chatting, my gmail address is: tsvibtcontact ]
What's a thing, in general? Minds deal with things, so this ... |
28b23427-caf5-4aa1-9443-a5dae8c1c850 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Austin Meetup
Discussion article for the meetup : Austin Meetup
WHEN: 07 November 2020 02:30:00PM (-0500)
WHERE: 4001 N Lamar Blvd, Austin, TX 78756
Actually meets every saturday. https://www.google.com/maps/place/Central+Market,+4001+N+Lamar+Blvd,+Austin,+TX+78756/
Discussion article for the meetup : Au... |
f659100f-c443-4d7b-8074-58dc82386268 | trentmkelly/LessWrong-43k | LessWrong | Scrying for outcomes where the problem of deepfakes has been solved
(Prompted by the post: On Media Synthesis: An Essay on The Next 15 Years of Creative Automation, where Yuli comments "Deepfakes exist as the tip of the warhead that will end our trust-based society")
There are answers to the problem of deepfakes. I t... |
16e848aa-a904-4ec0-b963-310eeb58a5de | trentmkelly/LessWrong-43k | LessWrong | Catastrophe Engines: A possible resolution to the Fermi Paradox
The Fermi Paradox leads us to conclude that either A) intelligent life is extremely improbable, B) intelligent life very rarely grows to a higher-level civilization, or C) that higher-level civilizations are common, but are not easy to spot. But each of ... |
b68dd5de-77b3-4045-bb0b-95d26f827d9b | trentmkelly/LessWrong-43k | LessWrong | Robot ethics returns
Cross posted from Overcoming Bias. Comments there.
***
People are often interested in robot ethics. I have argued before that this is strange. I offered two potential explanations:
1. Ethics seems deep and human, so it’s engagingly eerie to combine it with heartless AI
2. People vastly misjud... |
0c28c87c-3f0f-4a32-aa68-e2fc5c9edd33 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Acausal trade: different utilities, different trades
.mjx-chtml {display: inline-block; line-height: 0; text-indent: 0; text-align: left; text-transform: none; font-style: normal; font-weight: normal; font-size: 100%; font-size-adjust: none; letter-spacing: normal; word-wrap: normal; word-spacing: normal; white-space:... |
1d799f16-7732-49ac-a0b8-136a337a220b | trentmkelly/LessWrong-43k | LessWrong | Against Desirism
|
1b3d7e58-a6b4-4697-81c6-8374b4227122 | trentmkelly/LessWrong-43k | LessWrong | A short poem I found
"If there ever was an enemy
who stared us directly in the face,
it's certainly
the computer screen."
-- Unknown |
095631f1-c784-4f3d-9b7a-2f6a717b9381 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Ottawa LessWrong Weekly Meetup
Discussion article for the meetup : Ottawa LessWrong Weekly Meetup
WHEN: 23 June 2011 07:00:00PM (-0400)
WHERE: Fox and Feather Pub, 283 Elgin Street, Ottawa, Ontario
Fox and Feather Pub, upstairs, possibly in back room #1 if it's free. Look for the LW sign.
7pm EDT, obvious... |
7c52ccfd-9d75-4cc1-be1a-fb457e3e387d | trentmkelly/LessWrong-43k | LessWrong | 2 small problems with the site...
They're more like inconveniences, but still.
1. I've set my account setting to display "magical algorithm" comments, but when I read posts I still see them in the order of "oldest". I guess that's because of a discrepancy between those drop-down options: in 1 it's "top scored", in an... |
7a1e67a9-e77c-4734-83f1-4ea1f0c773ef | trentmkelly/LessWrong-43k | LessWrong | [Link] The Hyborian Age
Yay a new cool post is up on West Hunters blog! It is written by Gregory Cochran and Henry Harpending with whom most LWers are probably already familiar with (particularly this awesome entry). It raises some interesting points on biases in academia.
> I was contemplating Conan the Barbarian, a... |
2e5ed439-498e-4fb0-b2da-d0412f315bde | trentmkelly/LessWrong-43k | LessWrong | Stories of Summer Solstice
[Epistemic Status: talking in the language of metaphorical soul and mysticism.]
Previously:
* Visions of Summer Solstice
* Obligatory link to The Value and Danger of Ritual for people just tuning in.
June 23rd, the Bay community journeyed out to the edge of the world to celebrate the l... |
3201a6dc-4cd6-4622-a347-990d9a682f5a | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | The Value Definition Problem
How to understand non-technical proposals
=========================================
This post grew out of conversations at EA Hotel, Blackpool about how to think about the various proposals for ‘solving’ AI Alignment like CEV, iterated amplification and distillation or ambitious value lea... |
64fb9445-346e-474c-a15b-844d1e47f2bb | trentmkelly/LessWrong-43k | LessWrong | Probability is the oil of rationalisation
Or How to do whatever you feel like despite being a rationalist.
To rationally make a choice you weigh up all costs and benefits of all possibilities and choose the one with the greatest net benefit. To rationalise a choice you want to make, you choose costs and benefits that ... |
87d586f4-71af-4b01-906f-d08fbfa9f027 | trentmkelly/LessWrong-43k | LessWrong | In Defense of Epistemic Empathy
TLDR: Why think your ideological opponents are unreasonable? Common reasons: their views are (1) absurd, or (2) refutable, or (3) baseless, or (4) conformist, or (5) irrational. None are convincing.
----------------------------------------
Elizabeth is skeptical about the results of ... |
d39c65d5-bc70-4d68-b0d9-ea8c3205d4bf | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | Is AI Safety a Pascal's Mugging?
hi today we're going to talk about
Pascal's wager and Pascal's mugging this
is necessarily going to touch on
religious topics pretty heavily actually
and I'm just gonna say at the beginning
of the video that personally I don't
believe that any god or gods have ever
existed and I'm ... |
45431da3-f1a1-4c8e-adb0-b9180e6fe5e6 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Excerpts from "Doing EA Better" on x-risk methodology
The post "[Doing EA Better](https://forum.effectivealtruism.org/posts/54vAiSFkYszTWWWv4/doing-ea-better-1)" contains some critiques of the EA movement's approach to studying and ranking x-risks. These criticisms resonated with me and I wish we paid more attention t... |
eb812224-ff79-4f17-ac65-39ef68f1273a | trentmkelly/LessWrong-43k | LessWrong | AI #58: Stargate AGI
Another round? Of economists projecting absurdly small impacts, of Google publishing highly valuable research, a cycle of rhetoric, more jailbreaks, and so on. Another great podcast from Dwarkesh Patel, this time going more technical. Another proposed project with a name that reveals quite a lot. ... |
082cd236-8832-4e7c-851e-58ad994a32c2 | trentmkelly/LessWrong-43k | LessWrong | Bangalore Meetup: 28th May
Bangalore hopefully has enough LessWrongers to have its own meet up. I suggest having one in the afternoon on Saturday, 28th May at Cubbon Park Bandstand. (Behind the high court in Cubbon park).
I commit to be there from 4 pm-7 pm with a LW meetup sign and a book (can't commit to which book... |
3f04e230-cc6e-4d2b-a2c7-7d53555c90ff | trentmkelly/LessWrong-43k | LessWrong | Meetup : Bi-weekly Frankfurt Meetup
Discussion article for the meetup : Bi-weekly Frankfurt Meetup
WHEN: 27 July 2015 06:30:00PM (+0200)
WHERE: Frankfurt/Main
Contact: 0176 3066 164 (Janko)
You can also find the address in our google group (https://groups.google.com/forum/#!forum/less-wrong-frankfurt)
Location: The... |
0dd951e7-798a-447d-8116-c4b42cfddbc5 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Briefly how I've updated since ChatGPT
I'm laying out my thoughts in order to get people thinking about these points and perhaps correct me. I definitely don't endorse deferring to anything I say, and I would write this differently if I thought people were likely to do so.
1. **OpenAI's model** of "deploy as early as... |
57ce7fc8-d866-416a-89d3-40e4b4b25324 | StampyAI/alignment-research-dataset/arbital | Arbital | Log as the change in the cost of communicating
When interpreting logarithms as [a generalization of the notion of "length"](https://arbital.com/p/416) and as [digit exchange rates](https://arbital.com/p/427), in both cases, multiplying the input to the logarithm base 10 by a factor of 10 caused the output to go up by ... |
7d65ed5f-2207-471d-87d5-fb8d9885ecdf | StampyAI/alignment-research-dataset/blogs | Blogs | future paths
future paths
------------
we are at a node in a state graph (or [MDP](https://en.wikipedia.org/wiki/Markov_decision_process)), where every state points to a bunch of other states, notably by way of:
* irreversible superintelligent singleton implementation, whether it leads to [doom, utopia, or hell](t... |
0c577d6a-6508-478f-97cf-906b59231a9d | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Two questions about CEV that worry me
Taken from some [old comments of mine](/lw/sz/moral_error_and_moral_disagreement/2ytz) that never did get a satisfactory answer.
1) One of the justifications for CEV was that extrapolating from an American in the 21st century and from Archimedes of Syracuse should give similar r... |
5d3b6dc6-6a6b-4711-be59-0dfb1475a092 | trentmkelly/LessWrong-43k | LessWrong | New 'landing page' website: Friendly-AI.com
I've created a new "landing page" on Friendly AI at Friendly-AI.com. This is similar to IntelligenceExplosion.com, Existential-Risk.org, Anthropic-Principle.com, and simulation-argument.com.
The site is less ambitious than the original plan for it was, but it serves its pur... |
48b3b629-dff1-418c-a6e7-08c1d60999eb | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "I’ve been interested in drawing ever since I was a little kid. I like drawing people. I practiced a lot by looking at a cool picture of a character I like, and copying it as closely as I can.The better I got at copying, the better my work became. I got some great results this way. I even advanced to the level where I ... |
d92e4cb8-026d-4093-9bf2-659c50cd1dbf | trentmkelly/LessWrong-43k | LessWrong | "Inner Alignment Failures" Which Are Actually Outer Alignment Failures
If you don’t know what “inner” and “outer” optimization are, or why birth control or masturbation might be examples, then check out one of the posts here before reading this one. Thanks to Evan, Scott, and Richard for discussions around these ideas... |
2d9863d7-75eb-4301-92a1-c7d31472c52d | trentmkelly/LessWrong-43k | LessWrong | Closest stable alternative preferences
A putative new idea for AI control; index here.
There's a result that's almost a theorem, which is that an agent that is an expected utility maximiser, is an agent that is stable under self-modification (or the creation of successor sub-agents).
Of course, this needs to be for ... |
6fe6dd33-d0b8-4d3d-a4c4-274204fc45a3 | trentmkelly/LessWrong-43k | LessWrong | Sections 1 & 2: Introduction, Strategy and Governance
This post is part of the sequence version of the Effective Altruism Foundation's research agenda on Cooperation, Conflict, and Transformative Artificial Intelligence.
1 Introduction
Transformative artificial intelligence (TAI) may be a key factor in the long-run ... |
4fbd1259-c245-443c-9575-a86a2da11f70 | trentmkelly/LessWrong-43k | LessWrong | [Link] Will Superintelligent Machines Destroy Humanity?
A summary and review of Bostrom's Superintelligence is in the December issue of Reason magazine, and is now posted online at Reason.com. |
868f63c7-f4b4-48a9-b003-16f2019af6c0 | trentmkelly/LessWrong-43k | LessWrong | Anti-akrasia tool: like stickK.com for data nerds
In 2009 I first described here on LessWrong a tool that Bethany Soule and I made to force ourselves to do things that otherwise fell victim to akrasia ("How a pathological procrastinator can lose weight"). We got an outpouring of encouragement and enthusiasm from the L... |
e21754d6-3c79-4dc1-8446-bd9215a15662 | trentmkelly/LessWrong-43k | LessWrong | Forecasting Newsletter: June 2021
Highlights
* Some Superforecasters start a substack, as does Dominic Cummings
* Alex Lawsen and I published Alignment Problems With Current Forecasting Platforms on the arxiv.
* What if Military AI is a Washout? considers a future in which AI ends up affecting war not because of it... |
43678371-5524-4645-9ca3-cb2f1bae1ca0 | trentmkelly/LessWrong-43k | LessWrong | LessWrong email subscriptions?
Right now, LessWrong has a fair amount of email subscription options, but they're given in a giant list in your user profile that's kind of annoying to look at.[1]
I have a sense that some people – especially newer users, or users who just don't have a habit of coming to LessWrong all t... |
0a0ce953-458f-4ebf-a6f3-d3f5f992bde3 | trentmkelly/LessWrong-43k | LessWrong | Stupid Questions January 2015
This thread is for asking any questions that might seem obvious, tangential, silly or what-have-you. Don't be shy, everyone has holes in their knowledge, though the fewer and the smaller we can make them, the better.
Please be respectful of other people's admitting ignorance and don't mo... |
815a1513-d55f-42f9-851c-a1afc993bff9 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "This diagram summarizes the requirements for independent AI alignment research
and how they are connected.
In this post I'll outline my four-year-long attempt at becoming an AI alignment
researcher. It's an ‘I did X [including what I did wrong], and here's how it
went’ post (see also jefftk's More
writeups!).
I'm not ... |
08af2e99-6448-4d03-8fa7-367f5274efe0 | trentmkelly/LessWrong-43k | LessWrong | The PUSA System- Repost
Hello all!
Here is the repost of the PUSA system:
The PUSA System
The concept of any situation, component, or figment of our life or imagination being rational, increases based on a few factors:
* a: An increase of factual, unbiased, and logical evidence for the truth of the concept in co... |
d1f224c2-0b68-4439-be82-a6220a9b0d11 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Review: What We Owe The Future
For the inaugural edition of Asterisk, I wrote about What We Owe The Future. Some highlights:
> What is the longtermist worldview? First — that humanity’s potential future is vast beyond comprehension, that trillions of lives may lie ahead of us, and that we should try to secure and ... |
8ebec93f-c6a4-4124-8245-365b69eed461 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Optimality is the tiger, and agents are its teeth
You've done it. You've built the machine.
You've read the AI safety arguments and you aren't stupid, so you've made sure you've mitigated all the reasons people are worried your system could be dangerous, but it wasn't so hard to do. AI safety seems a tractable concer... |
31488f1c-95c1-4901-9b9e-486e66c145e4 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Learning Heuristics for Quantified Boolean Formulas through Deep Reinforcement Learning
|
1853fa1b-19c4-4670-88a2-68640f077081 | trentmkelly/LessWrong-43k | LessWrong | Learning incomplete models using dominant markets
% operators that are separated from the operand by a space
% operators that require brackets
% operators that require parentheses
% Paper specific
This post is formal treatment of the idea outlined here.
Given a countable set of incomplete mo... |
61f78c7a-5809-4032-bdb9-77d73a6ff16b | trentmkelly/LessWrong-43k | LessWrong | Interesting new Pew Research study on American opinions about radical life extension
This new study by Pew Research on American opinions about radical life extension turned up some interesting results:
> Asked whether they, personally, would choose to undergo medical treatments to slow the aging process and live to b... |
d86c494d-8e15-4da7-b071-e457b3386e8b | trentmkelly/LessWrong-43k | LessWrong | "How quickly can you get this done?" (estimating workload)
Epistemic status: based partly upon what I learnt as a certified ScrumMaster and mainly from practical experience running a software development team. Some of the later ideas come from Gower Handbook of Project Management, Judgement in Managerial Decision Maki... |
a257928d-58f2-48af-9cae-f628c144b8d5 | trentmkelly/LessWrong-43k | LessWrong | Processing people
Some of my friends think that a random process of deciding who should live or die is more important than the lives of those people, because lives should all be valued equally (and a process can ensure approximately random choice).
For example, this would mean it is better to make sure the life rafts... |
95fa003c-324c-49c5-a0d2-6e2300156592 | trentmkelly/LessWrong-43k | LessWrong | Hedonic asymmetries
Automatically crossposted
Creating really good outcomes for humanity seems hard. We get bored. If we don’t get bored, we still don’t like the idea of joy without variety. And joyful experiences only seems good if they are real and meaningful (in some sense we can’t easily pin down). And so on.
On... |
c58602e6-ebfa-4b5c-94f5-f181bceb37b1 | trentmkelly/LessWrong-43k | LessWrong | Book Review: Complications
Atul Gawande's Complications: A Surgeon's Notes on an Imperfect Science is a mixed bag for rationalists. Written as a series of essays organized into three sections entitled Fallibility, Mystery, and Uncertainty, the book as a whole is of questionable value, but the sections need to be cons... |
73e10a15-59b9-4a81-96c5-c09caee7e5e0 | trentmkelly/LessWrong-43k | LessWrong | Chains, Bottlenecks and Optimization
Consider an idea consisting of a group of strongly connected sub-ideas. If any sub-idea is an error (doesn’t work), then the whole idea is an error (doesn’t work). We can metaphorically model this as a metal chain made of links. How strong is a chain? How hard can you pull on it be... |
8a0a45f0-8270-4343-8096-d344ac17a136 | trentmkelly/LessWrong-43k | LessWrong | December 2010 Southern California Meetup
A meetup in Southern California will occur on Sunday December 19, 2010. The meetup will start around 3:30PM and run for at least 2 hours and possibly 4 or 5. Anna Salamon and Yvain are very likely to be in attendance, as well as people from the last few meetups who may have p... |
7f58ace8-09ba-4814-ab7e-834d425c3385 | trentmkelly/LessWrong-43k | LessWrong | MITx class(es): [LINK] and discussion
MIT is offering online classes under the name MITx, the first of which is MITx 6.002: Circuits and Electronics. I think the idea is similar in philosophy to that of the Stanford AI class, which I saw interested LessWrong-ers, though the subject matter (intro EE class) may appeal ... |
2fea50c5-f253-49f3-9717-9c89e9a64a5d | trentmkelly/LessWrong-43k | LessWrong | Training Regime Day 17: Deflinching and Lines of Retreat
Introduction
Declaring commitment to Crocker's rules means that other people can optimize their messages to you for information, disregarding our cultures normal rules against potentially causing offense. The reason why one might commit to said rules is to maxim... |
91f56e5f-1aa3-466a-8554-a3de2acb632b | trentmkelly/LessWrong-43k | LessWrong | My January alignment theory Nanowrimo
Update: list of posts so far. "(s)" denotes shortform.
post 1, post 2, post 3, post 4 (s), post 5 (s), post 6 (s), post 7, post 8, post 9 (s), post 10, post 11, post 12, post 13 (s), post 14, post 15, post 16 (with Lauren Greenspan), post 17, post 18, post 19 (s), post 20, post 2... |
76ceacfa-4ebc-452e-b7c2-801939981e15 | trentmkelly/LessWrong-43k | LessWrong | Towards an Intentional Research Agenda
This post is motivated by research intuitions that better formalisms in consciousness research contribute to agent foundations in more ways than just the value loading problem. Epistemic status: speculative.
David Marr's levels of analysis is the idea that any analysis of a syst... |
68b60de0-6128-4f58-844b-dbed7bafb2d9 | trentmkelly/LessWrong-43k | LessWrong | A Principled Cartoon Guide to NVC
TL;DR: Making claims or demands about/into other people's internal states, rather than about your state or observable external states, predictably ties people in knots—instead: only make claims about your own experience or observables. This lets the other control the copy of them that... |
974be91d-f6a7-424f-99ac-d2b5704cb4a4 | trentmkelly/LessWrong-43k | LessWrong | Are Cognitive Load and Willpower drawn from the same pool?
I was recently reading a blog here, that referenced a paper done in 1999 by Baba Shiv and Alex Fedorikhin (Heart and Mind in Conflict: The Interplay of Affect and Cognition in Consumer Decision Making). In it, volunteers are asked to memorise short or long num... |
da7338b1-8f65-4d7f-8036-9bad899646d4 | trentmkelly/LessWrong-43k | LessWrong | Harry Potter and the Methods of Rationality Podcast
Have you ever thought “I’d love to read Harry Potter and the Methods of Rationality, but I just don’t have the spare time. I wish it was available in audio format.” Fret no more! I present to you the HPMoR Podcast! First chapter out now, and another one added every W... |
e601729d-95cf-46a3-88ad-a46ce1fe6a8f | trentmkelly/LessWrong-43k | LessWrong | What have we learned from meetups?
We've been running regular, well-attended Less Wrong meetups in London for a few years now, (and irregular, badly-attended ones for even longer than that). In this time, I'd like to think we've learned a few things about having good conversations, but there are probably plenty of are... |
cd3d9923-f4c6-4073-b90b-7ebe18e0d1e9 | trentmkelly/LessWrong-43k | LessWrong | Have an idea for an interactive learning module? Consider applying for a ClearerThinking.org micro grant!
If you have an idea for an interactive learning module (on topics such as rationality, psychology, self-improvement, statistics, probability, effective altruism, philosophy economics, math, science, behavior chang... |
45b505a3-4e96-4fa4-89bd-e40c9a71a937 | trentmkelly/LessWrong-43k | LessWrong | SERI ML Alignment Theory Scholars Program 2022
The Stanford Existential Risks Initiative (SERI) recently opened applications for the second iteration of the ML Alignment Theory Scholars (MATS) Program, which aims to help aspiring alignment researchers enter the field by pairing them with established research mentors a... |
afa6c0d9-963a-4acb-aeb2-4cb69ba7fb93 | trentmkelly/LessWrong-43k | LessWrong | Communication Prior as Alignment Strategy
Alice has one of three objects:
* A red triangle
* A blue square
* A red circle
She wants Bob to learn which object she has. However, Alice may only send one of three messages:
* “My object is round”
* “My object is red”
* “This is not a pipe”
The rules of the game (... |
a2109817-207c-44d9-8c7c-7865e7b3086c | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Reshaping the AI Industry
The wider AI research community is an almost-optimal engine of apocalypse. The primary metric of a paper's success is how much it improves capabilities along concrete metrics, publish-or-perish dynamics supercharge that, the safety side of things is neglected to the tune of [1:49 rate of safe... |
e418efe4-ff9f-4bd9-a7f6-36c41cb4c8bc | trentmkelly/LessWrong-43k | LessWrong | A (small) critique of total utilitarianism
In total utilitarianism, it is a morally neutral act to kill someone (in a painless and unexpected manner) and creating/giving birth to another being of comparable happiness (or preference satisfaction or welfare). In fact if one can kill a billion people to create a billion ... |
9b89ceb7-8bcc-4d63-9842-bb3762382d41 | trentmkelly/LessWrong-43k | LessWrong | What's Not Our Problem
Cross-posted, as always, from Putanumonit.
Putanumonit started in 2015, and like every rationalist blogger at the time my main inspirations were Scott Alexander and Tim Urban. In the year prior, Scott wrote a remarkable series of posts transforming how I understand politics and political psycho... |
9fad58d5-35f5-4e11-b5e7-1da7005d105b | trentmkelly/LessWrong-43k | LessWrong | What explanatory power does Kahneman's System 2 possess?
In the 70s and 80s, Kahneman and Tversky did a bunch of pioneering research on heuristics and biases in human thought. Then, in Thinking Fast and Slow, Kahneman divided human cognition into System 1 and System 2 - basically, System 1 applies quick heuristics whi... |
b7334c02-2f8c-45c0-a423-ebdc20dc709f | trentmkelly/LessWrong-43k | LessWrong | Autism, Watson, the Turing test, and General Intelligence
Thinking aloud:
Humans are examples of general intelligence - the only example we're sure of. Some humans have various degrees of autism (low level versions are quite common in the circles I've moved in), impairing their social skills. Mild autists nevertheles... |
af51ec11-055d-42b0-a55f-d5555a14e25b | trentmkelly/LessWrong-43k | LessWrong | Meetup : London mini-meetup
Discussion article for the meetup : London mini-meetup
WHEN: 07 August 2011 02:00:00PM (+0100)
WHERE: Shakespeares Head, Africa House, 64-68 Kingsway, City of London WC2B 6AG, United Kingdom
Sorry for the late notice: the next London mini-meetup is on Sunday August 7 at 14:00 at the Shak... |
ceb391f3-35b6-47ef-8fa8-ba46fe9fd05a | trentmkelly/LessWrong-43k | LessWrong | Let's Talk About Intelligence
I'm writing this because, for a while, I have noticed that I am confused: particularly about what people mean when they say someone is intelligent. I'm more interested in a discussion here than actually making a formal case, so please excuse my lack of actual citations. I'm also trying to... |
6b77978f-cc3b-462b-9b74-e70779c78d14 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Modulation of viability signals for self-regulatory control
1 Introduction
---------------
The continual interaction that exists between an organism and the environment requires an active form of regulation of the mechanisms safeguarding its integrity. There are several aspects an agent must consider, ranging from ... |
090f5d2d-7575-4d89-94dc-22a19d2bc335 | trentmkelly/LessWrong-43k | LessWrong | Preparing for the Intelligence Explosion
This is a linkpost for a new paper called Preparing for the Intelligence Explosion, by Will MacAskill and Fin Moorhouse. It sets the high-level agenda for the sort of work that Forethought is likely to focus on.
Some of the areas in the paper that we expect to be of most inter... |
9e60e13d-848e-4d36-8532-9cbe7341f825 | trentmkelly/LessWrong-43k | LessWrong | Zut Allais!
Huh! I was not expecting that response. Looks like I ran into an inferential distance.
It probably helps in interpreting the Allais Paradox to have absorbed more of the gestalt of the field of heuristics and biases, such as:
* Experimental subjects tend to defend incoherent preferences even when they'... |
9ad9710b-3248-4be7-afc8-26aeb5011af8 | trentmkelly/LessWrong-43k | LessWrong | How I'm telling my friends about AI Safety
One of the comments on the new book post asked how to tell normie friends about AI safety. I don't have any special credentials here, but I thought it'd be worthwhile to share the facebook post I've drafted, both to get feedback and to give an example of one way a post could... |
33e8ae05-858e-4dfe-a61f-8c87ad40bdb6 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | By how much should Meta's BlenderBot being really bad cause me to update on how justifiable it is for OpenAI and DeepMind to be making significant progress on AI capabilities?
I'm pretty ignorant on AI risk and honestly tech stuff in general, but I'm trying to learn more. I think AI risk is like the #2 or #3 most imp... |
7e5ac475-cd69-4cec-a6f1-ce7b9a945528 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Conclusion and Bibliography for "Understanding the diffusion of large language models"
*This post is one part of the sequence* [*Understanding the diffusion of large language models*](https://forum.effectivealtruism.org/s/8rYkpiFhbb4HsbzFc)*. As context for this post, I strongly recommend reading at least the* [*5-mi... |
c80b3584-513a-4bf3-b37a-916f7ed661f0 | trentmkelly/LessWrong-43k | LessWrong | Where might I direct promising-to-me researchers to apply for alignment jobs/grants?
It sometimes happens that people who I've talked to or worked with ask me where they should go for financial support for their research. I haven't developed a standard list of answers to this question. It seems to me like there are a ... |
e9a5cb0a-cc5c-4134-b502-550fdf1c40f0 | trentmkelly/LessWrong-43k | LessWrong | Ambiguity causes conflict
Consider the following model of conflict:
Two parties, say A and B, have a dispute about some issue. The state of the world can be represented as a real number in the interval s∈[0,1]. A and B have utility functions uA(1−s) and uB(s) respectively, where uA,uB are increasing and concave. Intu... |
90e655d1-d707-47c5-9faa-c47542a51a15 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | The EU AI Act: A Simple Explanation - A Stanford Study Reveals the gaps of ChatGPT and 9 more
The EU AI Act is in the news due to a recent Stanford study revealing that 10 AI platforms, including ChatGPT, aren't entirely in line with its standards. News coverage has been quite complex, so I've consolidated the details... |
7b8533fa-7efd-42d3-b05c-95a92b910a53 | trentmkelly/LessWrong-43k | LessWrong | The US Executive vs Supreme Court Deportations Clash
Forecaster perspectives
Sentinel forecasters in aggregate assess as “83% true” (65% to 100%) the statement that the Trump administration has disobeyed the Supreme Court so far. On the one hand, the Trump administration has done nothing to “facilitate” bringing Abreg... |
4fc01ea7-b080-476d-a672-c6b8c3dc2442 | trentmkelly/LessWrong-43k | LessWrong | Book Review: Consciousness Explained (as the Great Catalyst)
[Thanks to wilkox for helpful discussion, as well as Charlie Steiner, Richard Kennaway, and Said Achmiz for feedback on a previous version. Extra special thanks to the Long-Term Future Fund for funding research related to this post.]
Consciousness Explained... |
5663d597-30c0-444d-a5f3-f6d3c02d0cfe | trentmkelly/LessWrong-43k | LessWrong | this is a test
it won't actually get posted |
ea1b0767-f085-4415-9e46-9b631a85113f | trentmkelly/LessWrong-43k | LessWrong | On Collusion - Vitalik Buterin
> ...if there is a situation with some fixed pool of resources and some currently established mechanism for distributing those resources, and it’s unavoidably possible for 51% of the participants can conspire to seize control of the resources, no matter what the current configuration is ... |
94dd023b-fa18-4d4a-bda8-9bd52a42a8e4 | trentmkelly/LessWrong-43k | LessWrong | Link: David Friedman's Positive Account of Property Rights
http://www.daviddfriedman.com/Academic/Property/Property.html
It's really good and not that long. Talks about how Schelling points bring humans out of the Hobbesian jungle. Also acts as introduction to Schelling points I suppose. |
757af016-516a-4ee1-b85a-0184153e8459 | trentmkelly/LessWrong-43k | LessWrong | Holiday Pitch: Reflecting on Covid and Connection
Somewhere on the edge of a Pareto frontier somewhere, I decided to make one of my shticks “founding holidays that fill important gaps in the 21st century." Founding a holiday is not normally the best solution to a problem, but it sometimes is, and I’ve spent ~10 years ... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.