id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
1e906030-62e3-4d3f-93b6-3372704ca07b | trentmkelly/LessWrong-43k | LessWrong | Who is Slimrock Investments Pte. Ltd. and how are they related to Lightcone Infrastructure?
Slimrock Investments Pte. Ltd. is listed on the Alameda County Recorder's records as associated with Lightcone's recent purchase of the Rose Garden Inn in Berkeley.
"Assignment of Rents" implies that they are the lender who p... |
c9e968a5-7fde-4c50-9041-38a162380ec4 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Pitfalls of the agent model
*This is independent research. To make further posts like this possible, please consider* [*supporting me*](https://www.alexflint.io/donate.html)*.*
---
Outline
-------
* I study the agent model as a frame for understanding the phenomenon of entities that exert influence over the fu... |
79dbaf80-395d-45e1-8f17-07175680c46d | trentmkelly/LessWrong-43k | LessWrong | [Intro to brain-like-AGI safety] 1. What's the problem & Why work on it now?
(Last revised: July 2024. See changelog at the bottom.)
1.1 Post summary / Table of contents
This is the first of a series of blog posts on the technical safety problem for hypothetical future brain-like Artificial General Intelligence (AGI... |
750da76b-f191-4871-99df-ef3418f0be37 | trentmkelly/LessWrong-43k | LessWrong | The effect of effectiveness information on charitable giving
A new working paper by economists Dean Karlan and Daniel Wood, The Effect of Effectiveness: Donor Response to Aid Effectiveness in a Direct Mail Fundraising Experiment.
The Abstract:
> We test how donors respond to new information about a charity’s effecti... |
73197f30-d266-49ed-b561-bf49e9df1e96 | trentmkelly/LessWrong-43k | LessWrong | A second example of conditional orthogonality in finite factored sets
Yesterday, I wrote a post that gave an example of conditional non-orthogonality in finite factored sets. I encourage you to read that post first. However, I'm kind of dissatisfied with it because it doesn't show any interesting cases of conditional ... |
bb135dda-d402-4c72-8e97-b8a14e309dfa | trentmkelly/LessWrong-43k | LessWrong | What is the biggest crypto news of the past year?
Please give reasons for why you consider it big.
Here are my top questions right now:
* What major policies are governments adopting, especially in the US?
* What the hell is Tesla up to?
* Does anyone really believe that Tesla sold its Bitcoin in order to help... |
c201a467-dfe8-4ba5-95b2-79ac36dcd68b | trentmkelly/LessWrong-43k | LessWrong | Yudkowsky on AGI risk on the Bankless podcast
Eliezer gave a very frank overview of his take on AI two weeks ago on the cryptocurrency show Bankless:
I've posted a transcript of the show and a follow-up Q&A below.
Andrea_Miotti, remember, and vonk previously posted transcripts to LessWrong (1,2 — see the comments ... |
13038b50-ff0d-492d-a698-878ae5b70754 | trentmkelly/LessWrong-43k | LessWrong | [Link] Small-game fallacies: a Problem for Prediction Markets
Nick Szabo writes about the dangers of taking assumptions that are valid in small, self-contained games and applying them to larger, real-world "games," a practice he calls a small-game fallacy.
> Interactions between small games and large games infect mos... |
93a4fc12-b409-424a-b64f-c7c765f7a429 | trentmkelly/LessWrong-43k | LessWrong | Metatickle Intelligence Metrics and Friendly Utility Functions
Related to: Intelligence Metrics and Decision Theories
Previously I presented a formalism for dealing with the Duality and Ontology problems associated with attempts to define a formal metric of general intelligence. It also solves the environment distrib... |
05f78c34-5bb0-4d4d-9e5d-be7944530fc8 | trentmkelly/LessWrong-43k | LessWrong | Rethinking AI Safety Approach in the Era of Open-Source AI
Open-Source AI Undermines Traditional AI Safety Approach
In the past years, the mainstream approach to AI safety has been "AI alignment + access control." In simple terms, this means allowing a small number of regulated organizations to develop the most advanc... |
cb0cd688-4aab-4621-82dd-491460800dd8 | StampyAI/alignment-research-dataset/blogs | Blogs | A research agenda for assessing the economic impacts of code generation models
A Research Agenda for Assessing the Economic
Impacts of Code Generation Models
Sam Manning1‡, Pamela Mishkin∗2‡, Gillian Hadfield3, Tyna
Eloundou2, and Emily Eisner4
1OpenResearch
2OpenAI
3University of Toronto
4University of California, Be... |
acf950ef-3ce4-49be-a40e-c9ee71fff643 | trentmkelly/LessWrong-43k | LessWrong | Why you must maximize expected utility
This post explains von Neumann-Morgenstern (VNM) axioms for decision theory, and what follows from them: that if you have a consistent direction in which you are trying to steer the future, you must be an expected utility maximizer. I'm writing this post in preparation for a sequ... |
21cfc713-eee6-44cf-9ed2-d78962223246 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Fort Collins, Colorado Meetup Wedneday 7pm
Discussion article for the meetup : Fort Collins, Colorado Meetup Wedneday 7pm
WHEN: 08 February 2012 07:00:00PM (-0700)
WHERE: 144 North College Avenue, Fort Collins, CO 80524
Sorry for the short notice. We will be having our usual meetups every Wednesday in Febr... |
a298e1c2-26f4-4edf-ada5-4c53648523ce | trentmkelly/LessWrong-43k | LessWrong | Last chance to donate for 2011
Many LW readers choose to direct their charitable donations to SingInst with a view toward reducing existential risk. Others do not, whether because they feel they lack an understanding of the relevant issues, because they value present day humans more than future humans or because they ... |
b97f76df-ffb6-49bf-b25e-7ce68d90ce74 | trentmkelly/LessWrong-43k | LessWrong | Open & Welcome Thread - December 2022
If it’s worth saying, but not worth its own post, here's a place to put it.
If you are new to LessWrong, here's the place to introduce yourself. Personal stories, anecdotes, or just general comments on how you found us and what you hope to get from the site and community are invi... |
8c05b2f8-8d72-4cf0-91b9-6af7762fad7a | trentmkelly/LessWrong-43k | LessWrong | Keep Your Identity Fluid [LINK]
Building on Graham's Small Identity, here I look at the hazards of identity, and give a suggestion for leveraging it to your advantage, as well as avoiding pitfalls.
As per my last article, feel free to let me know what you think here, privately, or anonymously.
Link. |
89c420d6-b66a-4b50-a955-af895aae1442 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Questions about Conjecure's CoEm proposal
Conjecture recently released an [AI safety proposal](https://www.lesswrong.com/posts/ngEvKav9w57XrGQnb/cognitive-emulation-a-naive-ai-safety-proposal). The three of us spent a few hours discussing the proposal and identifying questions that we have. (First, we each re-read the... |
75b16231-0ca9-4c35-ae6f-f00286b5c17f | trentmkelly/LessWrong-43k | LessWrong | Subway Slides
Here is the current layout of Davis Square station:
If you're coming in from the primary headhouse, on the right, your path is really indirect:
I think the solution is clear:
Put a fare gate at the top, or switch the entire MBTA to industry best practice proof-of-payment.
Comment via: faceb... |
dff654e0-7e65-41e7-bc03-5955e97103f3 | StampyAI/alignment-research-dataset/blogs | Blogs | Whole Bird Emulation requires Quantum Mechanics
*Jeffrey Heninger, 14 February 2023*
*Epistemic status: Written for engagement. More sober analysis coming soon.*
>
> Bird navigation is surprisingly cruxy for the future of AI.
>
>
> – Zach Stein-Perlman
>
> This seems pretty wrong.
>
>
> – Richard Korze... |
84d4ebd2-95ae-4e80-85c2-b567724aac4b | trentmkelly/LessWrong-43k | LessWrong | Solve Corrigibility Week
A low-hanging fruit for solving alignment is to dedicate a chunk of time actually trying to solve a sub-problem collectively.
To that end, I’ve broken up researching the sub-problem of corrigibility into two categories in this google doc (you have suggestion privileges):
1. Previous Work: l... |
5d8848bb-bcf3-4fe5-93e2-7aa0f06105ad | trentmkelly/LessWrong-43k | LessWrong | All The Latest Human tFUS Studies
from Peng, et al; stimulating the nucleus accumbens inhibits its activity
Transcranial focused ultrasound neuromodulation — altering the brain’s activity with low-intensity ultrasound — is really exciting .
It allows us to manipulate arbitrary regions of the brain without surgery, p... |
eb117c61-efc2-48b6-b39b-776fdf2d67d5 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Inner Alignment via Superpowers
*Produced As Part Of The SERI ML Alignment Theory Scholars Program 2022 Under* [*John Wentworth*](https://www.lesswrong.com/users/johnswentworth)
The Problem
===========
When we train RL agents, they have many opportunities to see what makes actions *useful*(they have to locate obstac... |
b75cc6f3-f17b-4336-870d-7e3cd36714bd | trentmkelly/LessWrong-43k | LessWrong | Unraveling the Failure's Try
I'm sure this idea exists somewhere else, but I haven't found it yet. (Probably my fault, I've only been on here for a few weeks and I'm still working through the core sequences.)
The failure's try is a seemingly earnest attempt to overcome a challenge, but the challenger lacks the fundam... |
ec56ad60-48a7-4c3d-834a-593e9388b5ff | trentmkelly/LessWrong-43k | LessWrong | The Sheepskin Effect
Previously: The Case Against Education, The Case Against Education: Foundations, The Case Against Education: Splitting the Education Premium Pie and Considering IQ
Epistemic Status: The spirit of Local Validity as a Key to Sanity and Civilization
The sheepskin effect is that completing the last ... |
be18669a-369b-4e56-8f9c-ab01efb6fd37 | trentmkelly/LessWrong-43k | LessWrong | Intelligence risk and distance to endgame
There are at least three objections to the risk of an unfriendly AI. One is that uFAI will be stupid - it is not possible to build a machine that is much smarter than humanity. Another is that AI would be powerful but uFAI is unlikely - the chances of someone building somethin... |
bf22fcf5-504e-49ea-88f9-da68d95917d8 | trentmkelly/LessWrong-43k | LessWrong | Radical Honesty
I recently ran across this interesting article about Radical Honesty, a movement founded by a psychotherapist named Brad Blanton who suggests that we should kick our addiction to lying and just tell the complete truth all the time. I also like this quote from the Wikipedia article on Radical Honesty: ... |
441e8a60-7157-4dba-bcf7-899a27188a64 | trentmkelly/LessWrong-43k | LessWrong | Weirdness Points
Vegans are often disliked. That's what I read online and I believe there is an element of truth to to the claim. However, I eat a largely[1] vegan diet and I have never received any dislike IRL for my dietary preferences whatsoever. To the contrary, people often happily bend over backwards to accommod... |
42fc0862-66b0-417e-8bc8-2f014edb9e56 | trentmkelly/LessWrong-43k | LessWrong | The National Dashboard and Human Progress
In this post, I would like to consider a hypothetical national dashboard comprising essential metrics that measure the economy, human well-being, and long-term progress. It is hypothetical because, although all these metrics are measured today, not all of them receive equal at... |
56cc233a-7cf9-44b0-8178-465320fbed36 | trentmkelly/LessWrong-43k | LessWrong | Reading the ethicists 2: Hunting for AI alignment papers
Introduction
I'm back, reading more papers in ethics (but now also in philosophy and wherever the citations lead me). Unlike last time when I surveyed one journal's approach to AI in general, this time I'm searching specifically for interesting papers that bear ... |
c8e1a421-5f41-40b6-a650-73d224d04e45 | trentmkelly/LessWrong-43k | LessWrong | Taking the parameters which seem to matter and rotating them until they don't
A big bottleneck in interpretability is neural networks are non-local. That is, given the layer setup
if we change a small bit of the original activations, then a large bit of the new activations are affected.
This is an impediment to find... |
f1c8f777-fec4-4ad9-88d2-6aaf42952242 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Medical Image Registration: The obscure field where Deep Mesaoptimizers are already at the top of the benchmarks. (post + colab notebook)
Background: Introduction to Image Registration
----------------------------------------------
Image registration, or finding the corresponding points in a pair of, eg, MRI scans, ... |
1da9b38f-9792-4f28-bc4d-164e11032438 | trentmkelly/LessWrong-43k | LessWrong | Where to Draw the Boundary?
The one comes to you and says:
> Long have I pondered the meaning of the word "Art", and at last I've found what seems to me a satisfactory definition: "Art is that which is designed for the purpose of creating a reaction in an audience."
Just because there's a word "art" doesn't mean tha... |
3411d156-3fdb-43f6-8f76-3f0bfc8c2edd | trentmkelly/LessWrong-43k | LessWrong | Луна Лавгуд и Комната Тайн, Часть 6
Disclaimer: This is Kongo Landwalker's translation of lsusr's fiction Luna Lovegood and the Chamber of Secrets - Part 6 into russian.
----------------------------------------
— Она в Зеркале Атлантиды, — сказал Гарри.
— Нам нужны жабросли, — сказала Луна. — Огромная туча жабросле... |
76f9a5a0-86bc-4769-8c28-9bdcb666ea65 | trentmkelly/LessWrong-43k | LessWrong | Speaking of the efficiency of utopia
I noted that it is probably reasonable for people to be wary of things introducing themselves as ‘efficiency’, since maximization of specific metrics has some tendency to go badly.
On the other hand, ‘efficiency’ doesn’t mean anything about building explicit or quantitative machin... |
b136c582-e994-49c6-ba0a-4d470d911d16 | trentmkelly/LessWrong-43k | LessWrong | Virulence Management
Cross posted from my blog
I have spent some time reviewing the literature on an approach to dealing with human pathogens known as “virulence management”. Here, I hope to provide a jumping-off point to the field for others. I have included a list of relevant papers at the end.
Acquired Immunity
... |
ca9f2ef1-6bdc-499d-9e53-e02384a42857 | trentmkelly/LessWrong-43k | LessWrong | Startup Roundup #1: Happy Demo Day
There were a bunch of discussions recently related to issues surrounding Y-Combinator, related as usual to their annual demo day. It seemed worth splitting them off into a post.
BIDDERS AT AUCTION MOSTLY THINK PRICES ARE TOO HIGH
YC is in session, so all the usual talk is back.
> ... |
e744a2f6-385d-4b68-b9cc-1818da23855e | trentmkelly/LessWrong-43k | LessWrong | MIT FutureTech are hiring a Product and Data Visualization Designer
Why apply or share?
* Our work to understand progress in computing and artificial intelligence, and its implications, is highly relevant to understanding and mitigating the risks of AI. This write-up provides a good overview of some of our interests... |
804dca17-d8ea-44f1-be16-6664cab3eaa2 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | How does iterated amplification exceed human abilities?
.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-spa... |
55571a14-4e96-458d-8c2e-7e3e20d20435 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "In Disguised Queries, I talked about a classification task of "bleggs" and "rubes". The typical blegg is blue, egg-shaped, furred, flexible, opaque, glows in the dark, and contains vanadium. The typical rube is red, cube-shaped, smooth, hard, translucent, unglowing, and contains palladium. For the sake of simplicity, ... |
ef08865b-b61a-424a-9079-0d2177afdd2c | trentmkelly/LessWrong-43k | LessWrong | Circular belief updating
This article is going to be in the form of a story, since I want to lay out all the premises in a clear way. There's a related question about religious belief.
Let's suppose that there's a country called Faerie. I have a book about this country which describes all people living there as ra... |
bbec7b0f-6f4a-40a1-be53-8506f66bb471 | trentmkelly/LessWrong-43k | LessWrong | Meetup : West LA: The Substitution Principle
Discussion article for the meetup : West LA: The Substitution Principle
WHEN: 04 March 2015 07:00:00PM (-0800)
WHERE: 11066 Santa Monica Blvd, Los Angeles, CA 90025
How to Find Us: Go into this Del Taco. We will be in the back room if possible.
Parking is free in the lo... |
ec580e88-887e-4ffd-8ab4-774704e780aa | trentmkelly/LessWrong-43k | LessWrong | Wrong however unnamed
Related to: 37 ways that words can be wrong.
Consider the following sentence (from Internet; but I have heard it before): 'Lichens consist of fungi and algae, but they are more than the sum of their constituents.'
It is supposed to say something like 'the fungus and the alga don't just live ver... |
84d4065b-a47c-4fd6-9f86-724bf470c0fd | trentmkelly/LessWrong-43k | LessWrong | AI Safety Bounties
Earlier this year, Vaniver recommended Bug Bounties for Advanced ML Systems.
I spent a while at Rethink Priorities considering and expanding on this idea, suggesting potential program models, and assessing the benefits and risks of programs like this, which I've called 'AI Safety Bounties':
Short... |
f9ed2e54-6bfd-4791-acb5-450cefe41655 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Helpless Individuals
Today's post, Helpless Individuals was originally published on 30 March 2009. A summary (taken from the LW wiki):
> When you consider that our grouping instincts are optimized for 50-person hunter-gatherer bands where everyone knows everyone else, it begins to seem miraculous that ... |
7efddbd1-913e-49c7-be45-cb78fc3b9b99 | trentmkelly/LessWrong-43k | LessWrong | Systems of Survival
In this 1992 dialogue, Jane Jacobs lays out two basic descriptive clusters (syndromes) of morality, each tied to a means of production, and describes them as ‘systems of survival’. That is, life requires inputs; those inputs can come from either taking, which is the foundation of what she calls the... |
3f7397e6-8615-48c7-a3fe-4e176d3604c3 | trentmkelly/LessWrong-43k | LessWrong | Conservation of Expected Ethics isn't enough
An idea relevant for AI control; index here.
Thanks to Jessica Taylor.
I've been playing with systems to ensure or incentivise conservation of expected ethics - the idea that if an agent estimates that utilities v and w are (for instance) equally likely, then its future e... |
e63d9a42-6d3c-432e-836d-6c25ef6deb7c | trentmkelly/LessWrong-43k | LessWrong | Philosophical self-ratification
"Ratification" is defined as "the act or process of ratifying something (such as a treaty or amendment) : formal confirmation or sanction". Self-ratification, then, is assigning validity to one's self. (My use of the term "self-ratification" follows philosophical usage in analysis of ca... |
6b2ff1ed-e5d4-4c65-927c-023aef867c49 | trentmkelly/LessWrong-43k | LessWrong | Parasitic Language Games: maintaining ambiguity to hide conflict while burning the commons
> “They are playing a game. They are playing at not playing a game. If I show them I see they are, I shall break the rules and they will punish me. I must play their game, of not seeing I see the game”
> - R. D. Laing
"It's not... |
93b4a924-47ca-43d1-bec4-abb021a06c02 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Meetup #7 - Becoming Less Wrong
Discussion article for the meetup : Meetup #7 - Becoming Less Wrong
WHEN: 27 November 2016 03:13:37PM (-0500)
WHERE: Meester Treublaan 18, 1097 DP Amsterdam, Netherlands
We actually didn't get around to our LessWrong discussion last time, so lets try again on Sunday the 27th... |
ef9cfcac-5d3f-4126-8f5c-12b3bf9ae252 | trentmkelly/LessWrong-43k | LessWrong | UML XII: Dimensionality Reduction
(This is the twelfth post in a sequence on Machine Learning based on this book. Click here for part I.)
This post will be more on the mathy side (all of it linear algebra). It contains orthonormal matrices, eigenvalues and eigenvectors, and singular value decomposition.
I
Almost ev... |
bce83e4d-eb9f-4304-aa66-ad1b2032eee6 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Realism about rationality
*Epistemic status: trying to vaguely gesture at vague intuitions. A similar idea was [explored here](https://intelligence.org/files/HowIntelligible.pdf) under the heading "the intelligibility of intelligence", although I hadn't seen it before writing this post. As of 2020, I consider [this fo... |
5b4c03d5-0ef8-4c21-bf6b-e54c44872732 | trentmkelly/LessWrong-43k | LessWrong | Why giving workers stocks isn’t enough — and what co-ops get right
In my last post, I argued that worker co-ops can help restore declining social trust. But a common objection I keep hearing goes something like this:
> Worker co-ops seem basically equivalent to a firm that gives its employees stock—but then permanent... |
26d7b7b0-de13-48d2-ab3a-ddb1827b476f | trentmkelly/LessWrong-43k | LessWrong | Survey on intermediate goals in AI governance
It seems that a key bottleneck for the field of longtermism-aligned AI governance is limited strategic clarity (see Muehlhauser, 2020, 2021). As one effort to increase strategic clarity, in October-November 2022, we sent a survey to 229 people we had reason to believe are ... |
25ec3b1b-d2a0-4060-a8ea-17c62c650740 | trentmkelly/LessWrong-43k | LessWrong | Acausal romance
I just realized I haven't previously pointed the metaphysicians on Less Wrong to "Possible Girls," a hilarious paper about acausal romance:
> The ability to causally interact with your partner is important to many aspects of happy romantic relationships, but not to all of them. It’s quite pleasant sim... |
aacd55ba-bd99-411a-a9bb-bf71c0a7ce3f | trentmkelly/LessWrong-43k | LessWrong | We don't want to post again "This might be the last AI Safety Camp"
We still need more funding to be able to run another edition. Our fundraiser raised $6k as of now, and will end if it doesn't reach the $15k minimum, on February 1st. We need proactive donors.
If we don't get funded for this time, there is a good cha... |
22ce77be-0006-46e9-aaf5-d562d62651da | trentmkelly/LessWrong-43k | LessWrong | Meetup : Phoenix/ASU Less Wrong
Discussion article for the meetup : Phoenix/ASU Less Wrong
WHEN: 12 April 2014 10:00:00AM (-0700)
WHERE: 300 E Orange Mall, Tempe, AZ 85281
We will be meeting up at Hayden Library. We're going to try a Saturday morning meetup to mix up the states of mind and see if we can bring some ... |
500c04f1-54d2-4b0e-800f-24fa49b1f960 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | [MLSN #8]: Mechanistic interpretability, using law to inform AI alignment, scaling laws for proxy gaming
As part of a larger community building effort, [CAIS](https://safe.ai/) is writing a safety newsletter that is designed to cover empirical safety research and be palatable to the broader machine learning research c... |
3774fc84-806a-43ae-b194-8360f8b23899 | trentmkelly/LessWrong-43k | LessWrong | Mentioning cryonics to a dying person
My paternal grandmother is dying of cancer (not brain cancer). She is still relatively healthy, and is taking chemo, but there is little hope of remission (and even if that does happen, she'll probably die of heart failure fairly soon). Her current plan is to be cremated and have ... |
879a06c8-54d6-4256-9d4a-f30aacd7617d | trentmkelly/LessWrong-43k | LessWrong | What charities can I donate to for preventing another pandemic?
Simple question but surprisingly I didn't find an answer with a quick google. Most charities (including WHO) are focused on resolving the current problem. |
fd662bc3-f5f0-44f5-a0ba-4ba77d2b9f51 | trentmkelly/LessWrong-43k | LessWrong | Will Manifold Markets/Metaculus have built-in support for reflective latent variables by 2025?
Prediction markets and similar systems are currently nice for soliciting predictions for outcomes where there is a clear, unambiguous objective resolution criterion. However, many phenomena in the real world are hard to dire... |
5a9fe1eb-c15f-4dcb-aa0f-a7f873df5c6a | trentmkelly/LessWrong-43k | LessWrong | Nov 16-18: Rationality for Entrepreneurs
CFAR is taking LW-style rationality into the world, this month, with a new kind of rationality camp: Rationality for Entrepreneurs. It is aimed at ambitious, relatively successful folk (regardless of whether they are familiar with LW), who like analytic thinking and care about... |
0c2acfe4-30f9-44bc-afda-27fdf6d45d63 | trentmkelly/LessWrong-43k | LessWrong | Retrospective on the 2022 Conjecture AI Discussions
At the end of 2022, following the success of the 2021 MIRI Conversations, Conjecture started a project to host discussions about AGI and alignment with key people in the field. The goal was simple: surface positions and disagreements, identify cruxes, and make these ... |
eb0af184-a911-47d3-9ce0-cafb578fc726 | trentmkelly/LessWrong-43k | LessWrong | Dancing With Covid
The Society of Stranders puts on a Shag (a regional Swing dance) festival every fall in North Myrtle Beach SC. This year, with the pandemic, the organization made the hard but necessary decision to cancel ( pdf, fb). Unfortunately, one of the venues decided to go ahead with their part of the festiva... |
6713d230-135d-49ff-88d8-d1d8ed084426 | trentmkelly/LessWrong-43k | LessWrong | Linkpost: Look at the Water
This is a linkpost for https://jbostock.substack.com/p/prologue-train-crash
Epistemic status: fiction, satire even!
I am writing a short story. This is the prologue. Most of it will just go on Substack, but I'll occasionally post sections on LessWrong, when they're particularly good.
---... |
4b1ab63b-dc7a-4f16-9e58-19bf9c1fc46b | trentmkelly/LessWrong-43k | LessWrong | Alignment Newsletter #43
Find all Alignment Newsletter resources here. In particular, you can sign up, or look through this spreadsheet of all summaries that have ever been in the newsletter.
Highlights
AlphaStar: Mastering the Real-Time Strategy Game StarCraft II (The AlphaStar team): The AlphaStar system from Deep... |
ca02c11c-4e8e-4e5b-a822-1e6f8786dea1 | trentmkelly/LessWrong-43k | LessWrong | [Proposed Paper] Predicting Machine Super Intelligence
Note from Malo
The Singularity Institute is always on the lookout for interested and passionate individuals to contribute to our research. As Luke frequently reminds everyone, we've got 2–3 years of papers waiting to be written (see “Forthcoming and Desired Articl... |
1f2bbc5d-4b3d-4bd1-8eb5-6a98083b7dfb | trentmkelly/LessWrong-43k | LessWrong | Chess - "Elo" of random play?
I'm interested in a measure of chess-playing ability that doesn't depend on human players, and while perfect play would be the ideal reference, as long as chess remains unsolved, the other end of the spectrum, the engine whose algorithm is "list all legal moves and uniformly at random pi... |
3aedad37-fe34-45a9-a6b6-894c90740edf | trentmkelly/LessWrong-43k | LessWrong | Willpower: not a limited resource?
Stanford Report has a university public press release about a recent paper [subscription required] in Psychological Science. The paper is available for free from a website of one of the authors.
The gist is that they find evidence against the (currently fashionable) hypothesis that... |
cf4c2831-5923-4c97-8426-046e2bf67a5c | StampyAI/alignment-research-dataset/lesswrong | LessWrong | A Study of AI Science Models
*Generated during AI Safety Camp 2023 by the AI Science Team: Eleni Angelou, Cecilia Tilli, Louis Jaburi, Brian Estany. Many thanks to our external collaborators Joshua Flanigan and Rachel Mason for helpful feedback.*
1. Introduction: Why science models?
===============================... |
e8458e37-ba60-4ac1-9e74-005a2feb9787 | trentmkelly/LessWrong-43k | LessWrong | Nick Bostrom says Google is winning the AI arms race
|
f181e9e6-255d-4270-8aea-73522e4745ee | trentmkelly/LessWrong-43k | LessWrong | Many methods of causal inference try to identify a "safe" subset of variation
(crossposted from my substack)
I have been thinking a lot about causality lately, and as a result I’ve come up with a common way to think of many different methods of causal inference that often seem to be used in science. This is probably ... |
d271842c-1ca6-4b83-b111-ae0db48e8a59 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Blog post: A tale of two research communities
This is a copy of a [blog post](https://www.york.ac.uk/assuring-autonomy/news/blog/ai-safety-research-communities/) from Francis Rhys Ward, an incoming doctoral student in Safe and Trusted AI at Imperial College London. I just discovered this on the website of the [Assurin... |
416e7d37-6fb4-4b47-8742-779e94cd05d9 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Takeoff speeds, the chimps analogy, and the Cultural Intelligence Hypothesis
In debates about AI takeoff speeds, the most common empirical example/analogy is that of the transition between chimpanzees and humans. For example, in [this conversation](https://www.google.com/search?q=yudkowsky+takeoff+speeds+chimps&rlz=1... |
6f7d07cd-177b-45aa-af2c-91a61e702626 | trentmkelly/LessWrong-43k | LessWrong | Bridging Expected Utility Maximization and Optimization
Background
This is the second of our (Ramana, Abram, Josiah, Daniel) posts on our PIBBSS research. Our previous post outlined five potential projects that we were considering pursuing this summer. Our task since then has been to make initial attempts at each proj... |
87fd98c6-d3b8-498c-bf69-cedf9c63be44 | trentmkelly/LessWrong-43k | LessWrong | [Paper Blogpost] When Your AIs Deceive You: Challenges with Partial Observability in RLHF
TL;DR
There has been a lot of discussion on Lesswrong on concerns about deceptive AI, much of which has been philosophical. We have now written a paper that proves that deception is one of two failure modes when using RLHF improp... |
89785af1-840e-4800-8d5c-17c28c9dd4a5 | trentmkelly/LessWrong-43k | LessWrong | A collection of approaches to confronting doom, and my thoughts on them
I just published A Slow Guide to Confronting Doom, containing my own approach to living in a world that I think has a high likelihood of ending soon. Fortunately I'm not the only person to have written on topic.
Below are my thoughts on what oth... |
4448e6c4-f7ff-41f8-8c78-4ea7dcb9c86d | trentmkelly/LessWrong-43k | LessWrong | Meetup : Washington, D.C.: Pi Day
Discussion article for the meetup : Washington, D.C.: Pi Day
WHEN: 12 March 2017 02:30:00PM (-0500)
WHERE: Donald W. Reynolds Center for American Art and Portraiture
Note: Daylight Saving Time begins on March 12. 3:30 p.m. EDT corresponds to 2:30 p.m. EST.
We will be meeting in th... |
c905d080-7b86-47a3-af63-535a2a84d0c0 | trentmkelly/LessWrong-43k | LessWrong | Any Good Criticism of Karl Popper's Epistemology?
I believe there are no correct, unaddressed criticisms of Karl Popper’s epistemology (Critical Rationalism – CR). If I'm mistaken, I'd like to be told. If others are mistaken, I'd like them to find out and take an interest in CR.
CR is important for the general reason... |
ed74dcf9-c59d-4ce3-a043-16bbcf8aba7b | trentmkelly/LessWrong-43k | LessWrong | Picking your battles
I think that raising the sanity waterline is a worthwhile goal, but picking your battles is absolutely necessary. It doesn't matter how formidable your argument is if you're arguing in the comments of a youtube video, you've lost by default. So where is the line in the sand? Where would you feel ... |
ce69bc31-e1ba-4d96-a6ba-cac97919d437 | trentmkelly/LessWrong-43k | LessWrong | Angry Atoms
Fundamental physics—quarks 'n stuff—is far removed from the levels we can see, like hands and fingers. At best, you can know how to replicate the experiments which show that your hand (like everything else) is composed of quarks, and you may know how to derive a few equations for things like atoms and ele... |
4d858ae1-525f-4619-9611-bad9f455a0fa | trentmkelly/LessWrong-43k | LessWrong | Epistemic Artefacts of (conceptual) AI alignment research
The fact that this post is seeing the light of day now rather than in some undefined number of weeks is, not in small part, due to participating in the second Refine blog post day. Thank you, fake-but-useful containers, and thank you, Adam.
Tl;dr
In this pos... |
11172b44-eb98-46c8-a1a7-d7180d607c0a | trentmkelly/LessWrong-43k | LessWrong | December 2020 gwern.net links
None |
a70d6023-1d7c-4a3f-ba24-104502b95b0a | trentmkelly/LessWrong-43k | LessWrong | [AN #159]: Building agents that know how to experiment, by training on procedurally generated games
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 summa... |
97d64560-ca1f-48c4-a91e-d09fa7fd84f5 | trentmkelly/LessWrong-43k | LessWrong | Weekly LW Meetups
This summary was posted to LW Main on May 31st. The following week's summary is here.
Irregularly scheduled Less Wrong meetups are taking place in:
* Atlanta LessWrong June Meetup: Effective Altruism: 15 June 2013 07:00PM
* Berlin Social Meetup: 15 June 2013 05:00PM
* [Boston] The Science Of Hap... |
23905e38-1126-4e8c-9475-40c55ff762f0 | trentmkelly/LessWrong-43k | LessWrong | The 'Bitter Lesson' is Wrong
There are serious problems with the idea of the 'Bitter Lesson' in AI. In most cases, things other than scale prove to be extremely useful for a time, and then are promptly abandoned as soon as scaling reaches their level, when they could just as easily combine the two, and still get bett... |
f5255d36-20cb-425c-8f0f-26b40b7f3a51 | trentmkelly/LessWrong-43k | LessWrong | Meetup Feedback: Topic selection and precommittments
This post is part of the Cambridge LW meetup group's attempt to publish what works for us, and try to make good meetups easier.
Breaking the ice and topic selection
A consistent problem has been starting discussion, and more generally breaking the ice. Last week, ... |
aa3e2d2e-ce90-4f0e-9983-fd9cded42cc0 | trentmkelly/LessWrong-43k | LessWrong | Conceptual Typography Example
* Memento mori, Latin for "remember you must die," has been a significant theme in art and philosophy, aiming to remind us of our mortality, the fleeting nature of earthly pleasures, and the imperative to live a meaningful life.
* Conceptual Typography is a design technique where typogr... |
8f7d4498-0396-4ab5-ad8c-d6e7d25f4bb6 | trentmkelly/LessWrong-43k | LessWrong | Future Filters [draft]
See Katja Grace's article: http://hplusmagazine.com/2011/05/13/anthropic-principles-and-existential-risks/
There are two comments I want to make about the above article.
First: the resolution to God's Coin Toss seems fairly straightforward. I argue that the following scenario is formally equi... |
ebd111bc-3c11-452f-bde4-963345f83c9e | trentmkelly/LessWrong-43k | LessWrong | Coursera classes relevant to LW
I assume You're familiar with Coursera. They have several on going classes that are relevant to LW such as:
1. Intro to Logic.
2. Probabilistic Graphical Models
3. Introduction to Mathematical thinking
Would anybody be interested in taking these classes with me? |
06194a15-35f0-429b-a05e-7cd9cefff7cb | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] The Level Above Mine
Today's post, The Level Above Mine was originally published on 26 September 2008. A summary (taken from the LW wiki):
> There are people who have acquired more mastery over various fields than Eliezer has over his.
Discuss the post here (rather than in the comments to the origina... |
9d71fe0d-6d1b-4b68-a6a3-ee46540a8287 | trentmkelly/LessWrong-43k | LessWrong | Don't teach people how to reach the top of a hill
When is it faster to rediscover something on your own than to learn it from someone who already knows it?
Sometimes it's faster to re-derive a proof or algorithm than to look it up. Keith Lynch re-invented the fast Fourier transform because he was too lazy to walk all... |
18c81be7-e386-476a-96be-dcb2ae74983e | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | An interactive introduction to grokking and mechanistic interpretability
Our write up largely agrees with [@Quintin Pope](https://www.alignmentforum.org/users/quintin-pope?mention=user)'s [summary](https://www.alignmentforum.org/posts/GpSzShaaf8po4rcmA/qapr-5-grokking-is-maybe-not-that-big-a-deal), with the addition o... |
0888d4da-c9b5-45c6-97e7-475344ff2520 | trentmkelly/LessWrong-43k | LessWrong | Brief question about Conway's Game of LIfe and AI
Conway’s Game of Life is Turing-complete. Therefore, it is possible to create an AI in it. If you created a 3^^3 by 3^^3 Life board, setting the initial state at random, presumably somewhere an AI would be created. Would this AI somehow take over the whole game board, ... |
632b1202-08aa-4c5d-b561-5aebc02a758a | trentmkelly/LessWrong-43k | LessWrong | Functional Analysis Reading Group
We've been running a Functional Analysis reading group on the EleutherAI Discord (partially motivated by a desire to grok Infrabayes). According to hard earned advice it's useful to pair up when learning difficult things.
We're as of this posting on section 2.3 of "A Friendly Approac... |
1ef4226f-18e1-4cd3-9647-33e79b16cc3a | StampyAI/alignment-research-dataset/blogs | Blogs | What mechanisms drive agent behaviour?
[](/?source=post_page-----e7b8d9aee88--------------------------------)Listen
Share
*By the Safety Analysis Team: Grégoire Déletang, Jordi Grau-Moya, Miljan Martic, Tim Genewein... |
d753f095-1f90-4c0d-89ad-493bfa3599b0 | trentmkelly/LessWrong-43k | LessWrong | Replacing the Water Heater's Anode
We installed a new water heater 8 years ago, and since then I've ignored it. It's an indirect model, heated by the same gas boiler that heats our house, and it has done its job well. When I was thinking about heat pumps, however, I reread the manuals for our existing system and notic... |
eb8eacbe-926e-47b6-9b66-2fe67cd0a568 | trentmkelly/LessWrong-43k | LessWrong | What are examples of perennial discoveries?
Quotes are from a private mailing list I'm part of. I asked the author if they wanted acknowledgement; I'll update if so.
Definition of "perennial discoveries": "These are science or engineering 'breakthroughs' that get announced in the press over and over and over, yet alm... |
f006df8e-119f-4ea5-842b-275632fe9551 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | [AN #161]: Creating generalizable reward functions for multiple tasks by learning a model of functional similarity
Alignment Newsletter is a weekly publication with recent content relevant to AI alignment around the world. Find all Alignment Newsletter **[resources here](http://rohinshah.com/alignment-newsletter/)**. ... |
4c7543e6-fdf3-4b41-b0d1-2af1a153b4c7 | trentmkelly/LessWrong-43k | LessWrong | GPT4 is capable of writing decent long-form science fiction (with the right prompts)
I like to experiment with AI-assisted fiction writing. Today, for the first time, I've noticed that GPT4 is actually getting good at the task.
Perhaps it's a result of some updates by OpenAI, or maybe I got the prompts right, but GP... |
c60c43dd-0766-41bb-a230-d5a92a0c12c3 | trentmkelly/LessWrong-43k | LessWrong | Applied Picoeconomics
Related to: Akrasia, Hyperbolic Discounting, and Picoeconomics, Fix It And Tell Us What You Did
A while back, ciphergoth posted an article on "picoeconomics", the theory that akrasia could be partially modeled as bargaining between present and future selves. I think the model is incomplete, bec... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.