id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
640de7e9-e059-4af2-9f85-e131b04d1df7 | trentmkelly/LessWrong-43k | LessWrong | Harry Potter and the Methods of Rationality discussion thread, part 19, chapter 88-89
This is a new thread to discuss Eliezer Yudkowsky’s Harry Potter and the Methods of Rationality and anything related to it. This thread is intended for discussing chapter 88-89. The previous thread has passed 500 comments.
There i... |
572eaa45-fc30-489f-893f-04bee0cf4703 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | 345M version GPT-2 released
OpenAI has released a larger GPT-2 model for public testing. They've also released the two larger models to select groups for experimenting. |
826ade49-2db8-49d7-b818-ac763e5d40f6 | StampyAI/alignment-research-dataset/blogs | Blogs | Analogpunk
Analogpunk
----------
(this video can also be found [on youtube](https://www.youtube.com/watch?v=0QJAd0NucuE)) |
f179e4a4-a216-48ed-a211-7d1a05447335 | trentmkelly/LessWrong-43k | LessWrong | Try o3-pro in ChatGPT for $1 (is AI a bubble?)
Will AI progress slow down? Current frontier AI models cost $100M+ to train, but in the old scaling law pre-training paradigm this was a one-off cost that scaled well i.e. it had a low marginal cost per query. Now this paradigm has now hit diminishing returns: New frontie... |
c1210b10-82be-49c9-8026-f98e41456fc0 | trentmkelly/LessWrong-43k | LessWrong | Why I'm not doing PauseAI
I'm a daily user of ChatGPT, sometimes supplementing it with Claude, and the occasional local model for some experiments. I try to make squeeze LLMs into agent-shaped bodies, but it doesn't really work. I also have a PhD, which typically would make me an expert in the field of AI, but the fie... |
34ec7676-3f4b-4ff0-8e5b-44960c9d77a3 | trentmkelly/LessWrong-43k | LessWrong | fake alignment solutions????
Suppose the long-term risk center's researchers, or a random group of teenage nerd hackers, or whatever, come up with what they call an "alignment solution". A really complicated and esoteric, yet somehow elegant, way of describing what we really, really value, and cramming it into a big m... |
73613511-ec0e-457a-9fd7-046473e26c4e | trentmkelly/LessWrong-43k | LessWrong | Paths Forward: Scaling the Sharing of Information and Solutions
Follow-up to: An Unexpected Victory: Container Stacking in the Port of Long Beach
My chronicle of how Ryan managed to change the container stacking rule in the Port of Long Beach quickly became the most viewed post I’ve ever had. A lot of people were exc... |
dc5bba38-508b-417f-b10b-65a876fcc60b | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Vanessa Kosoy's PreDCA, distilled
*This is an expanded version of my answer to* [*application problem 3*](https://docs.google.com/document/d/1NVVtdsfz7HiseVFSk3jYly4sPG4dG03wFFDrD8rBXU0/edit) *for Nate Soares and Vivek Hebbar's* [*SERI MATS*](https://www.lesswrong.com/posts/iR4kGzrWEJpXJ39ZB/seri-mats-program-winter-2... |
c9b5f611-aa4b-46c8-a859-4117936ca6c9 | trentmkelly/LessWrong-43k | LessWrong | [Altruist Support] How to determine your utility function
Follows on from HELP! I want to do good.
What have I learned since last time? I've learned that people want to see an SIAI donation; I'll do it as soon as PayPal will let me. I've learned that people want more "how" and maybe more "doing"; I'll write a doing p... |
99a4d521-4be9-4e5d-a880-5263e33f0d51 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Alignment via manually implementing the utility function
I would like to propose an idea for aligning AI.
First, I will provide some motivation for it. Suppose you are a programmer who's having a really hard time implementing a function in a computer program you're developing. Most of the code is fine, but there's t... |
7d9c7bea-31e9-40b4-9654-4cf8f69f653c | trentmkelly/LessWrong-43k | LessWrong | Low hanging fruit: analyzing your nutrition
Recently I decided to try an intermittent fasting diet. To do so, I had to figure out how much I could eat on my off/down days. I realized I didn't have a very good idea about how much calories my meals have, and as I was thinking about it, I started to get curious about my ... |
120b1658-9d2c-4000-99bc-9c2735fd9bae | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Skill up in ML for AI safety with the Intro to ML Safety course (Spring 2023)
**The Intro to ML Safety course covers foundational techniques and concepts in ML safety for those interested in pursuing research careers in AI safety, with a focus on empirical research.** We think it's a good fit for people with ML backgr... |
3eb11cd1-d5d2-4407-ad8d-70a01805d291 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Counterfactual Induction (Algorithm Sketch, Fixpoint proof)
So, to begin with, here's how the algorithm works.
The upstream algorithm iterates through all proofs, and records the lengths of all proofs of the form "a finite collection of sentences implies .mjx-chtml {display: inline-block; line-height: 0; text-indent:... |
12241f50-ac45-439f-8868-b04fc38d6bb6 | trentmkelly/LessWrong-43k | LessWrong | Expected utility without the independence axiom
John von Neumann and Oskar Morgenstern developed a system of four axioms that they claimed any rational decision maker must follow. The major consequence of these axioms is that when faced with a decision, you should always act solely to increase your expected utility. A... |
eafa58c8-6342-478f-bce6-c56a148409ff | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "SUMMARY: Let's collect people who want to work on for-profit companies that have significant positive impacts on many people's lives.
Google provides a huge service to the world - efficient search of a vast amount of data. I would really like to see more for-profit businesses like Google, especially in underserved are... |
0bca585b-7ae1-4779-bb8f-22abe6193027 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Chicago Applied Rationality Training
Discussion article for the meetup : Chicago Applied Rationality Training
WHEN: 30 April 2017 01:00:00PM (-0500)
WHERE: Harper Memorial Library Room 148, 1116 E 59th St, Chicago, IL 60637
The Chicago rationality group meets every Sunday from 1-3 PM in Room 148 of Harper... |
be1b222f-bbda-415b-aea8-abf9066ccac7 | trentmkelly/LessWrong-43k | LessWrong | Dan Luu on Futurist Predictions
Epistemic status: perspective derived from following Dan Luu's output for the last 5 years or so. Trying to vaguely gesture at a few things at once. Please ask questions if you find something confusing.
Dan Luu has written a interesting post analysing the track record of futurists' p... |
187f7cd7-eeeb-472d-9389-b7698e96ac43 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Results from the AI testing hackathon
We ([Apart Research](https://apartresearch.com)) ran a [hackathon for AI testing research projects](https://itch.io/jam/aitest) with 11 projects submitted by 34 participants between the 16th and 18th December. Here we share the winning projects. See them all [here](https://alignme... |
1d5c2f76-0863-4040-acfc-1c5ab84e1845 | trentmkelly/LessWrong-43k | LessWrong | Can't Pursue the Art for its Own Sake? Really?
Can anyone tell me why it is that if I use my rationality exclusively to improve my conception of rationality I fall into an infinite recursion? EY say's this in The Twelve Virtues and in Something to Protect, but I don't know what his argument is. He goes as far as to sa... |
927593ed-df61-4561-a9f2-eee2e7e32fe4 | trentmkelly/LessWrong-43k | LessWrong | Another Way to Be Okay
Cross-posted on lesswrong.com and integrationbyparts.substack.com.
Compare and contrast with Duncan Sabien’s essay A Way to Be Okay, written in parallel and with collaboration.
See also: Mental Health and the Alignment Problem
Photo by Simon Berger
If you look around, there are plenty of reas... |
77aa49c6-e09d-40ff-94cd-da21be20ba6e | trentmkelly/LessWrong-43k | LessWrong | Legal Brief: Plurality Voting is Unconstitutional
Epistemic status: certain of nothing. I'm not a legal scholar, but my training in philosophy has prepared me for legalese: I believe there might be a case here? Something worth exploring? Feedback from those with legal expertise would be greatly appreciated. UPDATE: I'... |
99318871-6c79-449c-b96c-587b763a7e77 | trentmkelly/LessWrong-43k | LessWrong | Reading More Each Day: A Simple $35 Tool
Life is full of clever little hacks. Sometimes the most impactful ones are also the simplest. I recently stumbled upon a basic tool that has remarkably boosted my daily reading time. I'm excited to share this game-changing discovery.
Last Thanksgiving, during a visit to my cou... |
c3d22858-c553-4cd2-8ae0-759edbdd66a0 | trentmkelly/LessWrong-43k | LessWrong | Which things were you surprised to learn are metaphors?
I love this question, but I've enjoyed noticing answers to its opposite more. What are some things you thought weren't metaphors but were surprised to learn actually are metaphors.
A classic example is that, at least in English, time is often described using dis... |
f38f047f-f632-4fe2-8d62-0965180f0def | trentmkelly/LessWrong-43k | LessWrong | On possible cross-fertilization between AI and neuroscience [Creativity]
Cross-posted from New Savanna.
MIT Center for Minds, Brains, and Machines (CBMM), a panel discussion: CBMM10 - A Symposium on Intelligence: Brains, Minds, and Machines.
On which critical problems should Neuroscience, Cognitive Science, and Co... |
de9da911-68ed-4b53-8d16-d5cdba6cd9e3 | trentmkelly/LessWrong-43k | LessWrong | AI-assisted alignment proposals require specific decomposition of capabilities
Some alignment strategies involve using weaker AI systems to help with alignment. I'm interesting in figuring out what dependencies each plan has, which need to be true for the plan to succeed. These are likely to vary across plans. (Sep... |
55c2fc63-f6b6-48d9-8919-7f052c4b9766 | trentmkelly/LessWrong-43k | LessWrong | A deep critique of AI 2027’s bad timeline models
Thank you to Arepo and Eli Lifland for looking over this article for errors.
I am sorry that this article is so long. Every time I thought I was done with it I ran into more issues with the model, and I wanted to be as thorough as I could. I’m not going to blame anyon... |
34e3cb2d-0fc8-4bbd-b54a-93ce7171b4af | trentmkelly/LessWrong-43k | LessWrong | Open & Welcome Thread – April 2021
Can anyone start these? Let's find out!
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 ge... |
c0cd17e4-0d66-43e1-8067-6ae116a1ea81 | trentmkelly/LessWrong-43k | LessWrong | Bounded Solomonoff induction using optimal predictor schemes
Most of the content of this post was covered by the talk I gave in Los Angeles MIRIx in October, minus the proofs and a minor amendment of Theorem 1 (the role of Δ2sqp,ϕ).
We define variants of the concept of generatable distributional estimation problem an... |
7e03996b-555a-4d42-b750-cb725170a4ec | trentmkelly/LessWrong-43k | LessWrong | Why is the nitrogen cycle so under-emphasized compared to climate change
While listing various environmental issues of how planetary boundaries are exceeded the Stockholm Resilience Centre lists climate change in the "increasing risk category" while listing "Nitrogen and phosphorus flows to the biosphere and oceans" i... |
4330f9a7-4d72-4d80-b23d-c8c416e4c238 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Encultured AI, Part 1: Enabling New Benchmarks
*Also available on* [*LessWrong*](https://www.lesswrong.com/posts/AR6mfydDJiGksj6Co/encultured-ai-part-1-enabling-new-benchmarks)*.*
*Followed by: Encultured AI, Part 2 of 3 (forthcoming)*
Hi! In case you’re new to Encultured AI, we’re a for-profit start-up with a pub... |
23627f99-e738-4977-a8bd-475b3360c53d | trentmkelly/LessWrong-43k | LessWrong | Dark Arts: Schopenhauer wrote The Book on How To Troll
AKA "The Art Of Controversy" AKA "The Art Of Always Being Right" AKA "Dialectic Eristic". Here's a pretty fun, illustrated version of the text, in actual Troll terms]. Here's an audiobook.
EDIT: In this article I adopt a bit of a Devil's Advocate attitude. I'm no... |
c6ad3637-d255-4062-a611-c81d110e03d0 | trentmkelly/LessWrong-43k | LessWrong | When did you orient?
John David Pressman says that the orienting is the tricky and valuable and underdocumented part of OODA. It occurs to me that I can hardly name any times anyone I know "oriented". When did you orient and what happened? |
6691a010-039e-4a48-84a9-0f12e428eb88 | trentmkelly/LessWrong-43k | LessWrong | Interpretability isn’t Free
Epistemic status: This post uses a simple and intuitive model[1], which seems obvious in retrospect, but it hasn’t been formalized and I’m not confident in its conclusions.
Current consensus is that large language models will be a core component of transformative AI systems. If that’s the ... |
72cdcc2c-b991-4bbe-ac18-244a1e381d35 | trentmkelly/LessWrong-43k | LessWrong | Looking for Opinions on "Antifragile" by N. Taleb
I'm reading Antifragile, and I don't have much relevant background, so it's hard for me to evaluate what he's saying. If anyone has relevant background/expertise, I'd like to hear it.
I can certainly see how the author's tone could annoy a lot of readers, but so ... |
d676f20d-c13a-42c5-8fda-002756951af8 | trentmkelly/LessWrong-43k | LessWrong | In memoryless Cartesian environments, every UDT policy is a CDT+SIA policy
Summary: I define memoryless Cartesian environments (which can model many familiar decision problems), note the similarity to memoryless POMDPs, and define a local optimality condition for policies, which can be roughly stated as "the policy is... |
fbb2c142-4962-4afe-9db2-3c4a3258974c | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | DeepMind x UCL RL Lecture Series - MDPs and Dynamic Programming [3/13]
hi everyone
uh welcome to
uh our third lecture in the
reinforcement learning course i'm diana
i'm one of the other lecturers of this
course alongside with harlow and mateo
a bit about myself before we begin i'm a
research scientist at deepmind and ... |
700f1338-067d-4984-a564-fca8914e6db1 | trentmkelly/LessWrong-43k | LessWrong | Vaccination and House Rules
One of the effects of living with others during a pandemic is that risks you take don't just affect yourself. While this is also true even if you live alone, you can't really negotiate with society at large over acceptable levels of risk. When our house decided to lock down a year ago, open... |
dd7c0d64-6022-4862-91bc-1740f5ad5652 | trentmkelly/LessWrong-43k | LessWrong | Epistemic spot checking one claim in The Precipice
On page 221 of The Precipice, Toby Ord says "scientists expect the brightening of the sun to also slow Earth's plate tectonics, dampening volcanic activity". This seemed very weird to me; how could sunlight possibly have any effect on mantle movement?
The book didn't... |
438c60af-c9e8-48e4-ae1c-7bc63089b3fc | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Slaying the Hydra: toward a new game board for AI
AI Timelines as a Hydra
-----------------------
Think of current timelines as a giant hydra. You can’t exactly see where the head is, and you don’t know exactly if you’re on the neck of the beast or the body. But you do have some sense of what a hydra is, and the diff... |
d2f939eb-567f-42d9-b7ba-4e4e7b2f4067 | trentmkelly/LessWrong-43k | LessWrong | Notes on Sincerity and such
This post examines a cluster of virtues that includes straightforwardness, frankness, sincerity, earnestness, candor, and parrhêsia. I hope it helps people who want to know more about these virtues and how to nurture them.
I am a technical writer by trade and have some strong opinions abou... |
6b7ff78f-d516-4373-9bb9-e467ec8db870 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Auditing and Debugging Deep Learning Models via Decision Boundaries: Individual-level and Group-level Analysis
1. Introduction
----------------
Our focus in this paper is auditing and debugging deep learning models in social applications of machine learning.
In these applications, deep learning models are usually t... |
f5869080-2c9f-4e41-aec6-c33740bc8ff2 | trentmkelly/LessWrong-43k | LessWrong | SlateStarCodex 2020 Predictions: Buy, Sell, Hold
Previously: Evaluating Predictions in Hindsight
Epistemic Status: Having fun
Evaluating predictions is hard, especially about the future. Let’s do it.
The most frustrating part of predictions is defining them carefully. A lot of Scott’s 2020 predictions seem like the... |
ea4102b9-0ea4-4a49-bf44-18288ee66842 | trentmkelly/LessWrong-43k | LessWrong | Persuasion Tools: AI takeover without AGI or agency?
[epistemic status: speculation]
> I'm envisioning that in the future there will also be systems where you can input any conclusion that you want to argue (including moral conclusions) and the target audience, and the system will give you the most convincing argumen... |
840189e6-e934-4b21-96fe-8a6357409639 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Software Engineering for Responsible AI: An Empirical Study and Operationalised Patterns
1 Introduction
---------------
Artificial intelligence (AI) continues demonstrating its positive impact on society and successful adoptions in data rich domains. The global AI market was valued at approx. USD 62 billion in 2020... |
25d8f6d9-f4fd-473f-b545-9f3f28bff959 | trentmkelly/LessWrong-43k | LessWrong | Kalman Filter for Bayesians
,
Summary: the Kalman Filter is Bayesian updating applied to systems that are changing over time, assuming all our distributions are Gaussians and all our transformations are linear.
Preamble - the general Bayesian approach to estimation: the Kalman filter is an approach to estimating movi... |
f6bf44b9-182c-47a2-b98b-f89c0c5f7a90 | trentmkelly/LessWrong-43k | LessWrong | Open Thread April 11 - April 17, 2016
If it's worth saying, but not worth its own post (even in Discussion), then it goes here.
Notes for future OT posters:
1. Please add the 'open_thread' tag.
2. Check if there is an active Open Thread before posting a new one. (Immediately before; refresh the list-of-threads p... |
1e5036e6-7c9e-4264-93c9-8d5d7151f293 | trentmkelly/LessWrong-43k | LessWrong | What are some podcasts that just read aloud worthwhile content?
Things like the SlateStarCodex Podcast, SecondEnumerations, the HPMOR podcast, Rationality: From AI to Zombies - The Podcast. |
9fab8ef1-1cf2-43c5-919b-e6e11b7be454 | trentmkelly/LessWrong-43k | LessWrong | Weekly LW Meetups: Washington DC, Baltimore, Houston, Seattle, Edinburgh
There are upcoming irregularly scheduled Less Wrong meetups in:
* University of Maryland: 16 September 2011 06:00PM
* BALTIMORE: Anyone wanna meet up?: 17 September 2011 03:00PM
* Houston: 17 September 2011 03:00PM
* Seattle Biweekly Meetup:... |
f2542ae4-8f50-4758-81dd-3b0e77b1c9c5 | trentmkelly/LessWrong-43k | LessWrong | Pair Debug to Understand, not Fix
I'm an adjunct instructor at CFAR, but this is my opinion, not CFAR's.
At CFAR, one of the exercises is 'pair debugging'; one person is the protagonist exploring one of their problems, and the other person is the helper, helping them understand and solve the problem. (Like many thing... |
9f412d60-1bfb-4a42-8f55-d492a3312296 | trentmkelly/LessWrong-43k | LessWrong | If calorie restriction works in humans, should we have observed it already?
Although there are no long-term scientific studies of calorie restriction in humans, there are religious groups, cults, and ascetics who voluntarily practice calorie restriction or intermittent fasting. Presumably there have been tens or hundr... |
5f4bb138-ace3-455b-8316-a8f014ee675f | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Designing agent incentives to avoid side effects
This is a [new post](https://medium.com/@deepmindsafetyresearch/designing-agent-incentives-to-avoid-side-effects-e1ac80ea6107) on the DeepMind Safety Research blog that summarizes the latest work on impact measures presented by the [relative reachability paper (version ... |
566bb023-4d56-47ad-b1f5-4f705a4bd31d | trentmkelly/LessWrong-43k | LessWrong | In a world… of venture capital
On Twitter, Robin Hanson asked a question yesterday I have given a lot of thought to, which is why the bigger venture capital firms dominate the market and make oversize profits while the other firms taken together make almost no profits. Most industries do not work that way, so this req... |
4897c7c7-d339-4d6d-8eaf-55e91e22b6e7 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | AI That Doesn't Try Too Hard - Maximizers and Satisficers
hi so way back when I started this
online air safety videos thing on
computer file I was talking about how
you have a problem when you maximize
just about any simple utility function
the example I used was an AI system
meant to collect a lot of stamps which
wor... |
6b11f1c1-16fc-450b-9b21-b716f0436357 | trentmkelly/LessWrong-43k | LessWrong | Zuckerberg’s Dystopian AI Vision
You think it’s bad now? Oh, you have no idea. In his talks with Ben Thompson and Dwarkesh Patel, Zuckerberg lays out his vision for our AI future. I thank him for his candor. I’m still kind of boggled that he said all of it out loud. We will start with the situation now. How are things... |
c623923c-c7a9-4879-a654-a689a7d97851 | trentmkelly/LessWrong-43k | LessWrong | Compositional language for hypotheses about computations
TLDR: I sketch a language for describing (either Bayesian or infra-Bayesian) hypotheses about computations (i.e. computable[1] logical/analytic facts). This is achieved via a novel (AFAIK) branch of automata theory, which generalizes both ordinary and tree autom... |
1f6dcf35-c135-46e1-81c8-3a650ab055b8 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Alignment Newsletter #29
Highlights
**[Deep Imitative Models for Flexible Inference, Planning, and Control](http://arxiv.org/abs/1810.06544)** *(Nicholas Rhinehart et al)*: It's hard to apply deep RL techniques to autonomous driving, because we can't simply collect a large amount of experience with collisions in orde... |
5469935e-55eb-4bb5-91d0-ea9fa7148e2e | trentmkelly/LessWrong-43k | LessWrong | Typology of blog posts that don’t always add anything clear and insightful
I used to think a good blog post should basically be a description of a novel insight.
To break it down more, on this view:
1. A blog post should have a propositional claim (e.g. ‘the biggest externalities are from noise pollution’, or ‘nois... |
7b3ee26f-3ff2-4aad-8cdc-9f494ab44794 | StampyAI/alignment-research-dataset/blogs | Blogs | One Cold Link: “The Past and Future of Economic Growth: A Semi-Endogenous Perspective”
[The Past and Future of Economic Growth: A Semi-Endogenous Perspective](https://www.nber.org/papers/w29126) is a growth economics paper by Charles I. Jones, asking big questions about what has powered economic growth[1](#fn1) over t... |
b54d52a3-a1a8-4449-b88c-44e45cc54705 | trentmkelly/LessWrong-43k | LessWrong | Chesterton’s Fence vs The Onion in the Varnish
Chesterton's Fence cautions us against making changes rashly, before we understand the reason why something is the way it is.
> In the matter of reforming things, as distinct from deforming them, there is one plain and simple principle; a principle which will probably be... |
8b658c79-c6ec-4c7d-a2ce-30d1ad36b4d5 | trentmkelly/LessWrong-43k | LessWrong | Why mechanistic interpretability does not and cannot contribute to long-term AGI safety (from messages with a friend)
tl;dr: Reasons why the scope of application of mechanistic interpretability is too limited to prevent long-term lethal AGI misalignment. Hooks into reasoning, not covered below, why any physically poss... |
83814d93-9da0-48a5-a29f-9f0aee580859 | trentmkelly/LessWrong-43k | LessWrong | z is not the cause of x
Introduction
In this note, I argue that the interpretation of representations (mental or machine learning) as causes of observed effects, is wrong by any sensible definition of causality. This interpretation seems to be somewhat common, although not pervasive. I propose a new interpretation bas... |
75f955b0-927c-4f8b-9a19-ef1ce035b45f | trentmkelly/LessWrong-43k | LessWrong | Sparsely-connected Cross-layer Transcoders
TLDR: I develop a method to sparsify the internal computations of a language model. My approach is to train cross-layer transcoders that are sparsely-connected: each latent depends on only a few upstream latents. Preliminary results are moderately encouraging: reconstruction ... |
ee5bf213-9898-4d22-914c-d41456c62bcc | StampyAI/alignment-research-dataset/arxiv | Arxiv | Reinforcement Learning with a Corrupted Reward Channel
1 Introduction
---------------
In many application domains, artificial agents need to learn their objectives,
rather than have them explicitly specified.
For example, we may want a house cleaning robot to keep the house clean,
but it is hard to measure and quan... |
916bc802-bf75-4dca-b361-204108a9f551 | trentmkelly/LessWrong-43k | LessWrong | Progress links and tweets, 2022-11-01
Announcements
* The Reef Starter Innovation Challenge, to identify startups that could benefit from operations in Low Earth Orbit
* AI startup Generally Intelligent has launched and open-sourced their research environment (via @kanjun)
* Deep Science Ventures is launching a doc... |
86ea4e5a-5c65-4076-9cda-b7d30c0b0542 | trentmkelly/LessWrong-43k | LessWrong | The Fourth Arena 2: New beings in time
Yesterday I suggested that we are at the edge of a new era in cosmic history, at least our local version of it, for we have little idea what’s been happening with life on other planets in other solar systems in other galaxies or even if such life exists or has existed. The arena ... |
e9825aca-d35b-4563-96c1-c8bf2a8a8704 | trentmkelly/LessWrong-43k | LessWrong | Connor Leahy on Dying with Dignity, EleutherAI and Conjecture
I talked to Connor Leahy about Yudkowsky's antimemes in Death with Dignity, common misconceptions about EleutherAI and his new AI Alignment company Conjecture.
Below are some highlighted quotes from our conversation (available on Youtube, Spotify, Google P... |
8802d405-4db3-4995-b999-238f8cdc1868 | trentmkelly/LessWrong-43k | LessWrong | [Link] Better results by changing Bayes’ theorem
> If it ever turns out that Bayes fails - receives systematically lower rewards on some problem, relative to a superior alternative, in virtue of its mere decisions - then Bayes has to go out the window.
-- Eliezer Yudkowsky, Newcomb's Problem and Regret of Rationality... |
5a9f32ca-b850-4d98-9e37-66bcb096cedd | trentmkelly/LessWrong-43k | LessWrong | Less Wrong Lacks Representatives and Paths Forward
In my understanding, there’s no one who speaks for LW, as its representative, and is *responsible* for addressing questions and criticisms. LW, as a school of thought, has no agents, no representatives – or at least none who are open to discussion.
The people I’ve... |
2296fa8f-23ac-49c8-8c39-9160b8711db9 | trentmkelly/LessWrong-43k | LessWrong | D&D.Sci 4th Edition: League of Defenders of the Storm Evaluation & Ruleset
This is a follow-up to last week's D&D.Sci scenario: if you intend to play that, and haven't done so yet, you should do so now before spoiling yourself.
RULESET
Code is available here for those who are interested.
CHARACTER STATS
A characte... |
5ba1f41a-0a93-48b4-b207-0bc6a4042afa | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Goal-directedness is behavioral, not structural
Goal-directedness is the term used by the AI Safety community to point to a specific property: following a goal. It comes from Rohin Shah's [post](https://www.alignmentforum.org/s/4dHMdK5TLN6xcqtyc/p/DfcywmqRSkBaCB6Ma) in his [sequence](https://www.alignmentforum.org/s/4... |
d901be9a-3a43-4cfa-8a94-c7405011fbdb | StampyAI/alignment-research-dataset/arxiv | Arxiv | Provably Bounded-Optimal Agents
|
fe2c9ee7-69f8-417e-a375-737b07015517 | trentmkelly/LessWrong-43k | LessWrong | Outline Summary: The Procrastination Equation
Lukeprog has written an excellent summary of The Procrastination Equation by Piers Steel. However, since everybody has a different style that they enjoy, I thought I'd post my own summary in the style that I like best: the bullet-point outline. In fact I'm hoping this post... |
02ca918b-92b3-42e2-b09f-405ca43b6f22 | trentmkelly/LessWrong-43k | LessWrong | Hashing out long-standing disagreements seems low-value to me
(Status: a short write-up of some things that I find myself regularly saying in person. In this case, I'm writing up my response to the question of why I don't spend a bunch more time trying to resolve disagreements with people in the community who disagree... |
fc123471-7029-4555-8674-b4a27a86ec62 | trentmkelly/LessWrong-43k | LessWrong | “And that’s okay": accepting and owning reality
The Context
I was having a conversation with Ruby a while back–the gist of it was that I was upset because of a nightmare I’d had the night before, and mad at myself for being upset about something that hadn’t even really happened, and trying to figure out how to stop f... |
b70db27c-1091-49eb-83a0-fca855364c34 | trentmkelly/LessWrong-43k | LessWrong | [Link] Beyond the hill: thoughts on ontologies for thinking, essay-completeness and forecasting
This is a link-post for: https://www.foretold.io/c/1bea107b-6a7f-4f39-a599-0a2d285ae101/n/5ceba5ae-60fc-4bd3-93aa-eeb333a15464
---
Epistemic status: gesturing at something that feels very important. Based on a true story... |
6e29768f-8abd-4b70-9e2a-f0afbdf874f2 | trentmkelly/LessWrong-43k | LessWrong | Friendship is transactional, unconditional friendship is insurance
It feels a little icky to say, but we befriend people because we get something out of it. We enjoy the company, the conversation, the emotional support, the activities, the connection, etc. It's not a coincidence people don't befriend brick walls.
(Th... |
3d991b44-1677-4fa0-9e4f-ef162571bec9 | trentmkelly/LessWrong-43k | LessWrong | Current State of Probabilistic Logic
So I've been thinking about how to assign probabilities to true/false assignments over claims in the context of a probabilistic argument mapping program.[1] Inevitably I've been confronted with the liar's paradox and a million related headaches. I have some tentative ideas on how I... |
3d0a34b6-7bc2-4c34-a27f-4d6b06255cc0 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Large scale distributed neural network training through online distillation
1 Introduction
---------------
For large-scale, commercially valuable neural net training problems, practitioners would be willing to devote many more machines to training if it sped up training time dramatically or improved the quality of ... |
11ee176a-c1f0-4bd3-9da3-77815cd3ac32 | trentmkelly/LessWrong-43k | LessWrong | How many researchers does a new paper reach?
How much of a field of research papers you must read to be "read" in your specialty in your concurrency? What contributing factors beside novelty does a paper have to have to get read? Are there some research areas where an idea needs to be "repapered" like a retweet multip... |
e5708245-da1b-4176-abff-84aac2eb6be4 | trentmkelly/LessWrong-43k | LessWrong | LessWrong experience on Alcohol
following on from this thread:
http://lesswrong.com/lw/m14/id_like_advice_from_lw_regarding_migraines/c9kr?context=3
User Algon asked:
I don't drink alcohol, but is it really all that? I just assumed that most people have alcoholic beverages for the 'buzz'/intoxication.
I related... |
d00f0b3b-7c1b-46db-9d07-baebf36bbcc5 | trentmkelly/LessWrong-43k | LessWrong | All AGI Safety questions welcome (especially basic ones) [July 2023]
tl;dr: Ask questions about AGI Safety as comments on this post, including ones you might otherwise worry seem dumb!
Asking beginner-level questions can be intimidating, but everyone starts out not knowing anything. If we want more people in the worl... |
2a07ab7a-c395-415f-b30d-b3b4bf9c1e0e | trentmkelly/LessWrong-43k | LessWrong | The Problem of "Win-More"
In Magic: the Gathering and other popular card games, advanced players have developed the notion of a "win-more" card. A "win-more" card is one that works very well, but only if you're already winning. In other words, it never helps turn a loss into a win, but it is very good at turning a win... |
08434e75-63ec-43d6-9ed7-f354fb5b3176 | trentmkelly/LessWrong-43k | LessWrong | A presentation about Cox's Theorem made for my English class
At my English class everybody was supposed to make a short presentation about subject of one's choice. I decided to tell people about Cox's Theorem (heavily based on the introduction in "Probability theory: The Logic Of Science" by E T Jaynes and "Constructi... |
fdce09c5-93dc-429c-944a-a40c82403368 | trentmkelly/LessWrong-43k | LessWrong | What is an alignment tax?
This is an article in the featured articles series from AISafety.info. AISafety.info writes AI safety intro content. We'd appreciate any feedback.
The most up-to-date version of this article is on our website, along with 300+ other articles on AI existential safety.
The alignment tax is th... |
b562b67e-3d5b-4985-89f1-918fb568516b | trentmkelly/LessWrong-43k | LessWrong | AGI by 2050 probability less than 1%
There are three serious gaps in our current scientific understanding of AI:
* We know nothing about working memory
* Our knowledge save for feed forward networks with gradient descent is invalid
* We know nothing about AGI, except for an uncomputable definition
Due to these ba... |
7fedf629-b6c1-4ea0-87bd-d1a2144b0544 | trentmkelly/LessWrong-43k | LessWrong | Double-thick transistors and other subjective phenomena
If I'm running on a silicon computer, do I have twice as much subjective experience if my computer is twice as thick?
Why is this even a good question?
Consider a computer that was printed on a flat sheet. If we stick two of these computers (one a mirror image)... |
25d7d653-acd8-4ce6-b98b-c63e901168b4 | trentmkelly/LessWrong-43k | LessWrong | Racing Towards Fusion and AI
Racing Towards a New Technology Is a Collective Choice, Not an Inevitable Consequence of Incentives
Before I started thinking about AI policy, I was working in the trying-to-get-fusion industry.
There are some significant similarities between AI and fusion.
* Both are emerging techn... |
c3101430-8b87-4f56-a4b4-6c1091bc784e | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Superintelligence FAQ
*Editor's note: this post is several years out of date and doesn't include information on modern systems like GPT-4, but is still a solid layman's introduction to why superintelligence might be important, dangerous and confusing.*
**1: What is superintelligence?**
A superintelligence is a mind ... |
5fb84e1e-cc49-4a21-8f4a-0d16723e571a | trentmkelly/LessWrong-43k | LessWrong | Socratic Persuasion: Giving Opinionated Yet Truth-Seeking Advice
The full post is long, but you can 80/20 the value with the 700 word summary! Over half the post is eight optional case studies. Thanks to Jemima Jones, Claude 4 Opus and Gemini 2.5 Pro for help copy-editing and drafting
TL;DR: I recommend giving advice... |
f3a2de71-8968-417c-9fdf-f3230d02681b | trentmkelly/LessWrong-43k | LessWrong | Is population collapse due to low birth rates a problem?
Elon Musk published a few hours this tweet:
"Population collapse due to low birth rates is a much bigger risk to civilization than global warming"
Robin Hanson, who is something for whom I feel a lot of intellectual respect, liked the tweet.
In my model of th... |
cea01d4a-2251-49fc-ac63-24ac2d1cd294 | trentmkelly/LessWrong-43k | LessWrong | SI/MIRI's emerging tech summaries [link]
I just noticed they have "summaries of emerging technologies".
http://singularity.org/techsummaries/
|
cfea33b3-88b6-43eb-8e2b-2021d0bc3e2a | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | A Proof of Löb's Theorem using Computability Theory
Löb’s Theorem states that, if PA⊢□PA(P)→P.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: no... |
309d0b12-bcf2-4451-992f-615db00e9f33 | trentmkelly/LessWrong-43k | LessWrong | Combat vs Nurture: Cultural Genesis
In my post Conversational Cultures: Combat vs Nurture, I described two different sets of norms and assumptions norms used in discussion. In this follow-up post, I add some important clarifications, state the defining differences, and begin to explore the conditions which might give ... |
8a514d51-ad34-4477-9d4f-5cdce4895343 | trentmkelly/LessWrong-43k | LessWrong | Distribution of knowledge and standardization in science
Modern technology facilitates the distribution of knowledge immensely. Through Google and Wikipedia, billons have access to an enormous amount of knowledge that previously was hard to get hold of. Still, there is lots of knowledge that is not getting properly di... |
37b4207b-a262-4a7e-9a72-47c6ba7c49b8 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Implementational Considerations for Digital Consciousness
This post is a summary of my conclusions after a philosophical [project](https://philpapers.org/rec/SHIICF) investigating some aspects of computing architecture that might be relevant to assessing digital consciousness. I tried to approach the issues in a way t... |
bb2edffe-3ed2-4cc4-8737-e066ac6655fe | StampyAI/alignment-research-dataset/arxiv | Arxiv | HYCEDIS: HYbrid Confidence Engine for Deep Document Intelligence System
1 Introduction
---------------
Recent advances in machine learning enables creations of automatic information extractors that can read the input document in image format, locate and understand relevant text lines before organizing the informati... |
46441985-54ed-4db6-a39b-aeb42f751d02 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Release Strategies and the Social Impacts of Language Models
OpenAI ReportNovember,2019Release Strategies and theSocialImpacts of Language ModelsIreneSolaiman∗OpenAIB`2M2!QT2M BX+QKMilesBrundageOpenAIKBH2b!QT2M BX+QKJackClarkOpenAID +F!QT2M BX+QKAmandaAskellOpenAI K M/ !QT2M BX+QKArielHerbert-VossHarvardUniversity `B2... |
37d69da9-86ad-471a-b3e2-55ef0fe45e15 | trentmkelly/LessWrong-43k | LessWrong | New Cause Area Proposal
Epistemic status - statistically verified.
I'm writing this post to draw peoples' attention to a new cause area proposal - haircuts for alignment researchers.
Aside from the obvious benefits implied by the graph (i.e. haircuts having the potential to directly improve organizational stabili... |
13ce56df-fa25-451e-96e3-b0a24123552b | trentmkelly/LessWrong-43k | LessWrong | For reducing caffeine dependence, does daily maximum matter more, or does total daily intake matter more?
I'm trying to reduce my dependence on caffeine from needing ~160mg in the morning to needing 80mg. My strategy is to slowly reduce my intake, dropping maybe 20mg every 3 days. So far so good.
But sometimes I fee... |
9969b107-109e-46e4-a9b8-2156f53ed852 | trentmkelly/LessWrong-43k | LessWrong | Potential factors in Bell Labs' intellectual progress, Pt. 1
Epistemic status: these are notes from a popular account filtered through my own existing beliefs. Here, I am largely trusting the book to report true things and not misrepresent them, though, in fact, I suspect the book is trying to create a certain narrat... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.