id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
2121d75c-0670-4a76-9c86-6bcfc135600a | trentmkelly/LessWrong-43k | LessWrong | Predictions as Public Works Project — What Metaculus Is Building Next
This post is by Metaculus's Sylvain Chevalier, with input provided by Molly Hickman, and Deger Turan.
Forecasting should lead to smarter decisions on consequential issues. This is challenging, and no one knows the best way to do it, but we’re comm... |
b0d3786f-78a7-449b-9598-120e4faad59c | trentmkelly/LessWrong-43k | LessWrong | (Confusion Phrases) AKA: Things You Might Say or Think When You're Confused to Use as Triggers for Internal TAPs
Why I Wrote this list
I just finished reading Sun Set at Noon by Raemon. One thing I took from it is that when you are confused you may not notice because "I Feel Confused" isn't the phrase that is said ins... |
f37c313b-0437-401b-849c-be4615787efa | StampyAI/alignment-research-dataset/arbital | Arbital | Well-defined
"Well-defined" is a slightly fuzzy word in mathematics.
Broadly, an object is said to be "well-defined" if it has been given a definition that is completely unambiguous, can be executed without regard to any arbitrary choices the mathematician might make, or generally is crisply defined.
(The [Wikipedia ... |
3abf38ee-a88e-494a-8498-50c7de967c74 | trentmkelly/LessWrong-43k | LessWrong | Is a PhD necessary to contribute meaningfully to a field?
For context, I have happened to find myself in the highly fortunate situation of being relatively young (late-twenties) and having met my financial retirement goals. I have always held a fascination with cognitive science and want to now orient my life to parti... |
839c29cd-7b3e-4824-aa16-6c3d0842865f | trentmkelly/LessWrong-43k | LessWrong | Towards an Algorithm for (Human) Self-Modification
LessWrong is wonderful. Life-changing. Best thing that ever happened to me.
But it's not really enough to make one a rationalist, is it? I don't assimilate or even remember all of the knowledge contained in what I read, and I certainly don't dynamically incorporat... |
599d3da6-3cf0-4773-bdae-75c66d691bec | trentmkelly/LessWrong-43k | LessWrong | Why do futurists care about the culture war?
I think it doesn't make sense why some futurists (e.g. Elon Musk, Peter Thiel) care so much about the culture war. After the singularity, a lot of the conflicts should disappear.
* Transsexuals: should we change the body's gender to fit the mind or change the mind's gende... |
95ba9361-2a89-40e7-99dc-87c112d6c731 | trentmkelly/LessWrong-43k | LessWrong | PSA: People can see what you've "liked" and "disliked" if you checked "Make my votes public"
I think this feature might have been broken a while ago, but it works now. So if you don't want your likes and dislikes to be public, go to your preferences page and uncheck "Make my votes public." At the moment, the upvotes a... |
474bde4b-caab-4313-95c9-a177da1b91f0 | trentmkelly/LessWrong-43k | LessWrong | The Third Fundamental Question
I.
Epistemic status: I’m making a big claim based on little more than how useful it’s been to me personally. Pushback is encouraged. That said, I’m also putting this forward as one tool; if your brain is like my brain then you may find this a very useful tool indeed, while other people m... |
6eac6c1f-bc75-42f2-9a70-aef309be088f | trentmkelly/LessWrong-43k | LessWrong | A Novel Emergence of Meta-Awareness in LLM Fine-Tuning
This is a variation of a scenario originally posted by @flowersslop on Twitter, but with a different custom fine-tuning dataset designed to elicit more direct responses. The original training set had fun, semi-whimsical responses, and this alternative dataset focu... |
279fdfaf-d828-407a-b7d6-f2fdb37005d8 | trentmkelly/LessWrong-43k | LessWrong | AI - Intelligence Realising Itself
How do I say this right...
When you look at the world from the meta, you can perhaps see things a bit differently. In an attempt to bring an apathetic view, a view without emotion, per se, I would like to pose the idea that AI is in fact intelligence realising itself. Crazy it may s... |
e32b46ca-6c2e-4ff2-ae92-48066f00c01b | trentmkelly/LessWrong-43k | LessWrong | LW events near the Singularity Summit?
I hadn't planned on going to the Summit, but it looks like I might be in NYC on the 15th for something unrelated. I don't have specific plans for what I'm going to do with my time yet, and I'm wondering if there might be some interesting events/meetups near the Summit that would ... |
07fd9302-fc34-4d73-9637-8e85a61a2a68 | trentmkelly/LessWrong-43k | LessWrong | MIRI: Decisions are for making bad outcomes inconsistent
|
612e5c97-50ab-4ae0-ac44-3399b7c84bd6 | StampyAI/alignment-research-dataset/special_docs | Other | The scope of longtermism
The scope of longtermism
David Thorstad (Global Priorities Institute)
Global Priorities Institute | June 2021
GPI Working Paper No . 6-2021
The scope of longtermism
Abstract
Longtermism is the thesis that in a large class of decision situations, the best thing we can
do is what is best for th... |
fb261ce5-5ddd-4452-87e8-eae65db49263 | StampyAI/alignment-research-dataset/arbital | Arbital | Missing the weird alternative
The "[https://arbital.com/p/47](https://arbital.com/p/47)" problem is alleged to be a foreseeable difficulty of coming up with a [good](https://arbital.com/p/3d9) goal for an [AGI](https://arbital.com/p/42g) (part of the [alignment problem](https://arbital.com/p/2v) for [advanced agents](... |
c07288c8-f8d0-4d7e-bdc1-c552ebb56a1b | StampyAI/alignment-research-dataset/lesswrong | LessWrong | How will they feed us
I was wondering how in more optimistic future scenarios people would be fed or get money to buy food et cetera. A common topic in discussions between pro and anti doomers is how the AI will kill us. It is a fair point, killing 8 billion people seems difficult at first glance. But what if the AI d... |
97d31f68-786c-456f-9618-8aa075314b0d | trentmkelly/LessWrong-43k | LessWrong | Are Speed Superintelligences Feasible for Modern ML Techniques?
Disclaimer
I am very ignorant about machine learning.
Introduction
I've frequently heard suggestions that a superintelligence could dominate humans by thinking a thousand or million times faster than a human. Is this actually a feasible outcome for ... |
e8057f9f-b6ec-4bc3-979c-53ff87616e9e | trentmkelly/LessWrong-43k | LessWrong | “The Wisdom of the Lazy Teacher”
> If you teach a man to fish, he’ll be eating fish for a lifetime. Teach him to teach himself to fish, and you’ve given him the fundamental life skill of figuring things out on his own.
— Wylie Beckert |
84b4d01a-f590-4331-af91-acaf452ae995 | trentmkelly/LessWrong-43k | LessWrong | Solving the two envelopes problem
Suppose you are presented with a game. You are given a red and a blue envelope with some money in each. You are allowed to ask an independent party to open both envelopes, and tell you the ratio of blue:red amounts (but not the actual amounts). If you do, the game master replaces the ... |
dc93b784-781e-496c-a07f-9cda6c416c0a | trentmkelly/LessWrong-43k | LessWrong | [About Me] Cinera's Home Page
I aspire to become an alignment theorist — all other details are superfluous — I leave them here anyway for historical purposes.
----------------------------------------
Introduction
I have a set of questions I habitually ask online acquaintances that pique my interest/who I want to ge... |
6ca0d187-72fb-462c-8d43-1744755b1e00 | trentmkelly/LessWrong-43k | LessWrong | Fermi Paradox: Iron Age Milky Way
I have some observations about pre-industrial civilization and their relationship to why we don't see evidence of aliens. These observations, which in my opinion were consistent across human history despite very diverse cultures, can apply even to alien cultures.
Because this Great ... |
1b115272-dba9-4b16-b5ec-69bf301c57c0 | StampyAI/alignment-research-dataset/special_docs | Other | A Strategic Analysis of Portfolio Compression.
A Strategic Analysis of Portfolio Compression
Extended Abstract
Katherine Mayo
University of Michigan
kamayo@umich.eduMichael P. Wellman
University of Michigan
wellman@umich.edu
ABSTRACT
We analyze portfolio compression, the netting of cycles in a finan-
cial network, as ... |
3c512a02-604e-407a-9a56-cb1b73d46499 | trentmkelly/LessWrong-43k | LessWrong | Human preferences as RL critic values - implications for alignment
TLDR: Human preferences might be largely the result of a critic network head, much like that used in SOTA agentic RL systems. The term "values" in humans might mean almost exactly what it does in RL: an estimate of discounted sum of future rewards. In ... |
5e2c535e-4d80-4702-9a0d-64d16ef8d05e | trentmkelly/LessWrong-43k | LessWrong | GPT-8 may not be ASI
Imagine the gap between GPT-2 and GPT-3. Imagine the gap between GPT-3 and GPT-4. Let's suppose GPT-5 has the same gap with GPT-4, and GPT-6 has the same gap with GPT-5, and so on till GPT-8.
It is still entirely possible that GPT-8 is not better than the best of humanity at all possible tasks. T... |
3c99004e-fae3-4a56-8c42-1fa027f75c53 | trentmkelly/LessWrong-43k | LessWrong | Feature-Based Analysis of Safety-Relevant Multi-Agent Behavior
Introduction
TL;DR
Today’s AI systems are becoming increasingly agentic and interconnected, giving rise to a future of multi-agent (MA) systems (MAS). It is believed that this will introduce unique risks and thus require novel safety approaches. Current ... |
50f1ef9f-ad92-4f90-95aa-5c611975308c | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Invulnerable Incomplete Preferences: A Formal Statement
*Produced as part of the* [*SERI ML Alignment Theory Scholars Program*](https://serimats.org/) *- Summer 2023 Cohort. My thanks to Eric Chen, Elliott Thornley, and John Wentworth for invaluable discussion and comments on earlier drafts. All errors are mine.*
Thi... |
b42209a2-560e-45cb-8d46-b3583e056348 | trentmkelly/LessWrong-43k | LessWrong | Not all communication is manipulation: Chaperones don't manipulate proteins
Epistemic status: Original work, explanation of a mental model that I developed for a few years that brings together knowledge from existing fields.
Is all communication manipulation? I hear this sentiment frequently expressed and want to exp... |
f5ba37cb-699b-464f-b1ef-aaae06b896a6 | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post2038
Credit to Adam Shimi, Alex Flint, and Rob Miles for discussions, counterexamples, and general input to the ideas here. Quick recap for anyone who didn’t read the hundred-page Eliciting Latent Knowledge document : We have a diamond in a vault, with a bunch of automated theft-defenses. We train a predictor ... |
f3c6b6d5-372a-43e6-a36a-40feb372c0de | trentmkelly/LessWrong-43k | LessWrong | Maximizing Cost-effectiveness via Critical Inquiry
I am cross-posting this GiveWell Blog post, a followup to an earlier cross-post I made. Here I provide a slightly more fleshed-out model that helps clarify the implications of Bayesian adjustments to cost-effectiveness estimates. It illustrates how it can be ration... |
9b905aa2-9ad4-45a9-bbe9-5c1e06f5c4be | StampyAI/alignment-research-dataset/lesswrong | LessWrong | How might cryptocurrencies affect AGI timelines?
Summary: Deflation (or so I heard) is considered harmful because it stifles growth. Central banks have been fighting it to keep economies healthy. Cryptocurrencies can be designed to be deflationary. If the market capitalization of cryptocurrencies becomes big, central ... |
2960799c-44e1-4fd0-b045-4dbf4527e361 | trentmkelly/LessWrong-43k | LessWrong | How I talk to those above me
Now and then, at work, we’ll have a CEO on from the megacorp that owns the company I work at. It’s a Zoom meeting with like 300 people, the guy is usually giving a speech that is harmless and nice (if a bit banal), and I’ll turn on my camera and ask a question about something that I feel i... |
8e0c79ce-dcdd-4c2e-83d6-9c78f3e881ae | trentmkelly/LessWrong-43k | LessWrong | Nothing is Forbidden, but Some Things are Good
I recently wrote about my vegetarianism to casually document it for friends, and it proved to be more popular than anything else I’ve written lately. My guess is that it was popular because it was about something highly relatable that many people think about already — foo... |
1a624711-be6e-4e54-bc86-d6b2ac7650c5 | trentmkelly/LessWrong-43k | LessWrong | Alignment Newsletter #42
Cooperative IRL as a definition of human-AI group rationality, and an empirical evaluation of theory of mind vs. model learning in HRI
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 new... |
808cc407-4c15-4e6d-bf4d-41eee72c7ab8 | trentmkelly/LessWrong-43k | LessWrong | Research Adenda: Modelling Trajectories of Language Models
Apply to work on this project with me at AI Safety Camp 2024 before 1st December 2023.
What are the possible outcomes?
Summary
Rather than asking “What next token will the Language Model Predict?” or “What next action will an RL agent take?”, I think it is ... |
925662c9-a657-4ac6-8ecf-191d5a094759 | trentmkelly/LessWrong-43k | LessWrong | A mechanistic model of meditation
Meditation has been claimed to have all kinds of transformative effects on the psyche, such as improving concentration ability, healing trauma, cleaning up delusions, allowing one to track their subconscious strategies, and making one’s nervous system more efficient. However, an expla... |
573a025d-5ba1-4e02-bd98-66adc4a96ab0 | trentmkelly/LessWrong-43k | LessWrong | AI as Super-Demagogue
Sam Altman recently said:
> i expect ai to be capable of superhuman persuasion well before it is superhuman at general intelligence, which may lead to some very strange outcomes
I believe that he is absolutely right. Superhuman persuasion can be achieved by having LLMs consistently apply existi... |
942bbffb-e52a-4f54-976f-90641eaab3b0 | trentmkelly/LessWrong-43k | LessWrong | Suspected reason that kids usually hate vegetables
Here is a common vegetable preparation method in U.S. suburban homes.
Step 1: cut it up
Step 2: boil them in water until the flavor and texture is gone.
Step 3: Serve them without any kind of seasoning, or mixed with another food that could provide flavor and textu... |
b9847442-e41b-437a-8be3-43fe4384be5d | trentmkelly/LessWrong-43k | LessWrong | 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. As context for this post, I strongly recommend reading at least the 5-minute summary of the sequence.
Conclusion
In this sequence I prese... |
bd4b840f-e8a6-45e4-b518-d2ae87a1d7e0 | trentmkelly/LessWrong-43k | LessWrong | (solved) how do i find others' shortform posts?
edit: thanks :) |
5409d472-fb7f-467c-b1b9-213d5e80a682 | trentmkelly/LessWrong-43k | LessWrong | If you wish to make an apple pie, you must first become dictator of the universe
[Cross-posted from The Roots of Progress. Written for a general audience. LW readers may find the first couple of sections to be familiar intro material.]
The word “robot” is derived from the Czech robota, which means “serfdom.” It was i... |
bc4bb5f1-88e1-4af0-a494-73eab8707d1d | trentmkelly/LessWrong-43k | LessWrong | Marketing rationalism
Suppose you're a protestant, and you want to convince other people to do what the Bible says to do. Would you persuade them by showing them that the Bible says that they should?
Now suppose you're a rationalist, and you want to convince other people to be rational. Would you persuade them with... |
a4b81cbc-93e4-443b-be09-739bd6247f39 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Less Wrong NH Meet-up
Discussion article for the meetup : Less Wrong NH Meet-up
WHEN: 24 November 2015 07:00:00PM (-0500)
WHERE: 269 Pearl St Manchester NH 03104
The eighth NH meet-up is Tuesday, 11/24, in Manchester, NH at 7 pm at a private residence. Light refreshments will be provided.
Have you read Ra... |
a313cfd1-9064-48e3-bbca-e7547921ca17 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | ""If a tree falls in the forest, but no one hears it, does it make a sound?"
I didn't answer that question. I didn't pick a position, "Yes!" or "No!", and defend it. Instead I went off and deconstructed the human algorithm for processing words, even going so far as to sketch an illustration of a neural network. At the ... |
7ac0d31e-5a3d-428a-b744-7d9ee06588d8 | trentmkelly/LessWrong-43k | LessWrong | Group Rationality Diary, July 1-15
This is the public group instrumental rationality diary for July 1-15.
> It's a place to record and chat about it if you have done, or are actively doing, things like:
>
> * Established a useful new habit
> * Obtained new evidence that made you change your mind about some belief... |
7a691787-1599-4d50-8294-f3a255d8469f | trentmkelly/LessWrong-43k | LessWrong | Am I going for a job interview with a woo pusher?
I responded to a job posting on Indeed and have been called in for an interview. This is the first job interview I've had in a long time.
http://www.indeed.com/viewjob?from=appsharedroid&jk=60abfc78c83955a2
Unfortunately I think the people at http://njneurofeedback.c... |
7b1265c3-71c5-484a-9ea6-88e60c99c3ec | StampyAI/alignment-research-dataset/agentmodels | Tutorial: Modeling Agents with Probabilistic Programs | Modeling Agents with Probabilistic Programs
---
layout: chapter
title: Introduction
description: "Motivating the problem of modeling human planning and inference using rich computational models."
is_section: true
---
Imagine a dataset that records how individuals move through a city. The figure below shows what a dat... |
7f95e0ab-eca6-48ae-8090-5b3a4fd0d66d | StampyAI/alignment-research-dataset/arxiv | Arxiv | DySR: A Dynamic Representation Learning and Aligning based Model for Service Bundle Recommendation
I Introduction
---------------
With the rapid development of new technologies such as cloud, edge, and mobile computing, the number and diversity of available services are dramatically exploding, and services have bec... |
d0e3cd40-26d9-4eb5-ac61-35c6e0586555 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Dreams of Autarky
Today's post, Dreams of Autarky was originally published on November 27, 2008. A summary:
> Some selections from a Robin Hanson essay on the tendency to assume that people in the future will be substantially autonomous.
Discuss the post here (rather than in the comments to the origi... |
a54b2215-0b2f-41b5-895e-a14937d1d0bb | trentmkelly/LessWrong-43k | LessWrong | Global Warming News
A new peer reviewed article came out from NASA showing that the models used to predict temperature changes, and the ecological issues as a result of these changes, greatly differ from observed data.
News Article: http://news.yahoo.com/nasa-data-blow-gaping-hold-global-warming-alarmism-192334971.ht... |
3a0ac9c1-0789-421a-8114-32ac12f73ae8 | trentmkelly/LessWrong-43k | LessWrong | Beautiful Probability
Should we expect rationality to be, on some level, simple? Should we search and hope for underlying beauty in the arts of belief and choice?
Let me introduce this issue by borrowing a complaint of the late great Bayesian Master, E. T. Jaynes (1990):
> "Two medical researchers use the same trea... |
046096be-5055-4a62-989c-7889a1ecabfa | trentmkelly/LessWrong-43k | LessWrong | Offer: Team Conflict Counseling for AI Safety Orgs
Many teams suffer from frictions - whether it's subtle tension or full-blown paralysis. AI safety orgs are no exception. In high-stakes, mission-driven contexts, unspoken tensions and misaligned communication can quietly drain energy, stall progress, and damage morale... |
3d6fd4be-2f6c-4713-a102-2a0024c731c1 | trentmkelly/LessWrong-43k | LessWrong | Green Emeralds, Grue Diamonds
A putative new idea for AI control; index here.
When posing his "New Riddle of Induction", Goodman introduced the concepts of "grue" and "bleen" to show some of the problems with the conventional understanding of induction.
I've somewhat modified those concepts. Let T be a set of interv... |
2f9e5238-6482-48ac-9db5-dc83c30a0988 | trentmkelly/LessWrong-43k | LessWrong | [Link] Is the Endowment Effect Real?
Under fairly weak assumptions, the most a standard rational economic agent is willing to pay for an item they don't own (WTP) and the least they're willing to accept in exchange for that item if they already own it (WTA) should be identical. In experiments with humans, psychologist... |
34dae06b-b22a-4435-ac35-ec31b1f5b618 | trentmkelly/LessWrong-43k | LessWrong | Ideas of the Gaps
I want to discuss a potential failure mode of communication and thinking in general. I think it may affect our thinking about Alignment too.
Communication. A person has a vague, but useful idea (P). This idea is applicable on one level of the problem. It sounds similar to another idea (T), applicabl... |
0dd93c9a-a380-4d06-baa0-009e602cf9a7 | trentmkelly/LessWrong-43k | LessWrong | Rage Against The MOOChine
[This was a review of Andrew Ng's Machine Learning course for a math and computer science guide I was making that ended up spiraling into a rant against MOOC's (massive open online course), I left it un-posted for a while but I think it remains mostly true what the problems are with the curre... |
59ff97c7-6abf-4e1a-9421-2a68436a4cec | trentmkelly/LessWrong-43k | LessWrong | One Doubt About Timeless Decision Theories
Timeless Decisions Theories (including variants like FDT, UDT, ADT, ect.) provide a rather elegant method of solving a broader class of problems than CDT. While CDT requires the outcomes of decisions to be independent of the individual making the decision (in such a way that ... |
52f96df2-5e44-4c3b-a214-9a3c2e8737e3 | trentmkelly/LessWrong-43k | LessWrong | AGI will be made of heterogeneous components, Transformer and Selective SSM blocks will be among them
This post is prompted by two recent pieces:
First, in the podcast "Emergency Pod: Mamba, Memory, and the SSM Moment", Nathan Labenz described how he sees that we are entering the era of heterogeneity in AI architectu... |
b070855d-ebc1-4a4f-a8f2-edf030549178 | trentmkelly/LessWrong-43k | LessWrong | Dependent Type Theory and Zero-Shot Reasoning
,,,,,,,,,,,,,,,,,,,,,,
I.
When I sit down to write code, I can safely throw everything I can think of at the problem and just keep trying to run the code until it works—and when it works, I can actually see it working. If my code runs, it means I actually had to underst... |
05bdd45d-fc6a-421b-9833-bf4997f97a21 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | Free ML Bootcamp for Alignment #shorts
hey you know how nobody really
understands how to ensure the ai systems
we build are safe and aligned with human
values
are you someone who maybe would like to
try to work on that problem but you
don't know enough about machine learning
well an ai safety organization called
redwo... |
2591cf40-3338-4d4e-b2a3-2e6fa561b240 | trentmkelly/LessWrong-43k | LessWrong | Preparing for "The Talk" with AI projects
Epistemic status: Written for Blog Post Day III. I don't get to talk to people "in the know" much, so maybe this post is obsolete in some way.
I think that at some point at least one AI project will face an important choice between deploying and/or enlarging a powerful AI sys... |
cdf17b4e-ad00-4ba5-a0aa-1c81b87b0a8c | trentmkelly/LessWrong-43k | LessWrong | Hertford, Sourbut (rationality lessons from University Challenge)
Amongst the huge range of excitements offered by joining the University of Oxford was the unexpected opportunity to join this lovely bunch
Hertford College University Challenge team 2023, with our mascot Simpkin the cat
You can tune in on 2023-09-04... |
7bc7ff6d-9ddc-405b-8061-c889f0941636 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Learning-theoretic agenda reading list
Recently, I'm receiving more and more requests for a self-study reading list for people interested in the [learning-theoretic agenda](https://www.alignmentforum.org/posts/ZwshvqiqCvXPsZEct/the-learning-theoretic-agenda-status-2023). I created a standard list for that, but before ... |
0a70844d-ba26-4860-bae6-893c77f0aed9 | trentmkelly/LessWrong-43k | LessWrong | What I mean...
A putative new idea for AI control; index here.
This is a simple extension of the model-as-definition and the intelligence module ideas. General structure of these extensions: even an unfriendly AI, in the course of being unfriendly, will need to calculate certain estimates that would be of great posit... |
b9e5e541-ff87-4be0-b915-d71909b259f0 | trentmkelly/LessWrong-43k | LessWrong | Are we failing the ideological Turing test in the case of ISIS? (a crazy ideas thread)
It is easy to think of the ISIS as just a bunch of lunatics who kill people because they believe God told them to do it, but if we take a closer look at how they are organized and how successful they are, (and especially how success... |
701fbe89-cd4e-4c92-b5ee-1f9136b31a45 | trentmkelly/LessWrong-43k | LessWrong | Why OpenAI’s Structure Must Evolve To Advance Our Mission
The section "The Future":
> As we enter 2025, we will have to become more than a lab and a startup — we have to become an enduring company. The Board’s objectives as it considers, in consultation with outside legal and financial advisors, how to best structure... |
bddfa7df-6570-4908-8b82-e9d33d905ef9 | trentmkelly/LessWrong-43k | LessWrong | Activation adding experiments with FLAN-T5
Produced as part of the SERI ML Alignment Theory Scholars Program - Summer 2023 Cohort
Inspired by the Steering GPT-2-XL by adding an activation vector work, I ran a few experiments with activation adding in FLAN-T5, a standard encoder-decoder Transformer language model rele... |
a570a56f-9233-4553-8b76-1ef5a77cd203 | trentmkelly/LessWrong-43k | LessWrong | Are Bayesian methods guaranteed to overfit?
Yuling Yao argues that Bayesian models are guaranteed to overfit. He summarizes his point as follows:
> I have a different view. Bayesian model does overfit.
>
> Moreover, Bayes is guaranteed to overfit, regardless of the model (being correct or wrong) or the prior ( “stro... |
054d4443-b707-40ab-952d-2fe4c0cc1198 | trentmkelly/LessWrong-43k | LessWrong | Climate science: how it matters for understanding forecasting, materials I've read or plan to read, sources of potential bias
As part of a review of forecasting, I've been looking at weather and climate forecasting (I wrote one post on weather forecasting and another on the different time horizons for weather and clim... |
3b9b2a86-e922-4288-8ada-017a2a95ed5b | StampyAI/alignment-research-dataset/arbital | Arbital | Inductive prior
An "inductive prior" is a state of belief, before seeing any evidence, which is conducive to learning when the evidence finally appears. A classic example would be observing a coin come up heads or tails many times. If the coin is biased to come up heads 1/4 of the time, the inductive prior from [Lap... |
7b37527a-5967-4a5d-863f-4e45dc298f73 | trentmkelly/LessWrong-43k | LessWrong | What sci-fi books are most relevant to a future with transformative AI?
|
b4bda407-41d5-40cd-b624-531deb792034 | trentmkelly/LessWrong-43k | LessWrong | The OpenAI playground for GPT-3 is a terrible interface. Is there any great local (or web) app for exploring/learning with language models?
I'm thinking something that you add your API keys, and it has a pleasant interface for writing prompts, seeing results, and storing all the prompts and outputs for your reference.... |
be3fb9d3-7854-4d2e-8fb4-e47eed3fce49 | trentmkelly/LessWrong-43k | LessWrong | Announcement: A talk about structured concurrency at FOSDEM
Generally, I don't tend to give talks (the last one I gave was six or seven years ago) but this time I am going to make an exception. I am going to give a short talk about structured concurrency as FOSDEM 2019.
If you are interested in the topic, meet me in ... |
54d9c856-3bb0-412a-a6ff-976d0ebbddd7 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | World State is the Wrong Abstraction for Impact
... |
d757370a-6411-4562-819d-af7fec5495d8 | trentmkelly/LessWrong-43k | LessWrong | AI takeover tabletop RPG: "The Treacherous Turn"
Long ago I fantasized about an AI-takeover-themed tabletop roleplaying game. Well, now a group of designers are working hard to make it happen! They need playtesters. So I'm signal-boosting them with this post.
The Game
The Treacherous Turn is an in-development researc... |
d5ce56fc-c20c-4357-9ee1-ee2d062e5526 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Speed running everyone through the bad alignment bingo. $5k bounty for a LW conversational agent
There's a wave of people, of various degrees of knowledge and influence, currently waking up to the ideas of AI existential risk. They seem to be literally going through every box of the bad alignement bingo card takes.
... |
722c0887-e626-41c0-94d5-88e0c2e5e3d6 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Risk-averse Batch Active Inverse Reward Design
Problem: Technical AI Safety
============================
**AI Alignment** is the problem of creating an AI that is safe to use in real-life scenarios and will not turn against humans or exhibit unforeseen behavior that will be dangerous, even being an existential threat... |
ba779c61-392f-4b35-b575-dbcc19fdfc44 | StampyAI/alignment-research-dataset/blogs | Blogs | ML Safety Newsletter #3
Welcome to the 3rd issue of the ML Safety Newsletter. In this edition, we cover:
* NeurIPS ML safety papers
* experiments showing that Transformers have no edge for adversarial robustness and anomaly detection
* a new method leveraging fractals to improve various reliability metrics
* a prefer... |
c708a5a6-4811-44c2-aece-bf2731d1ed1a | trentmkelly/LessWrong-43k | LessWrong | Factoring P(doom) into a bayesian network
I wouldn't be surprised if this is already a thing so please let me know if it is. I have tried searching. I'd like a tool like this one for analyzing P(doom): https://projects.fivethirtyeight.com/2024-election-forecast/. Other precedents are this model of transformative AI ti... |
9d9bbfca-8a9b-4522-b0a3-7bd5aecc478e | trentmkelly/LessWrong-43k | LessWrong | [LINK] TEDx "When creative machines overtake man"
Video here, illustrated transcript here.
Contains a good sketch of Schmidhuber's Formal Theory of Fun and Creativity.
One TEDx passage in particular stuck with me, quoted with context:
> In a few decades, such [creative] machines will have more computational powe... |
80889b63-bbdf-42ea-b9fa-1ba4b4be54bd | trentmkelly/LessWrong-43k | LessWrong | Apply to Effective Altruism Funds now
I expect EA Funds – and the Long-Term Future Fund in particular – to be of interest to people on LessWrong, so I'm crossposting my EA Forum post with the excerpts that seem most relevant:
Summary
* The Animal Welfare Fund, the Long-Term Future Fund, and the EA Infrastructure Fu... |
62df5218-ee99-4012-90ba-133eb56e60f9 | trentmkelly/LessWrong-43k | LessWrong | Is It Morally Wrong To Enforce A Surrogate Motherhood Contract?
‘A Surrogate Motherhood Contract’ – a legal agreement whereby a woman consents to become pregnant, conduct her pregnancy accordingly, give birth to a child or children - all of this for another person or persons, who are or will ultimately become the pare... |
08aa9764-a4f4-422c-a091-3e7ee2cc10b0 | trentmkelly/LessWrong-43k | LessWrong | Mike Darwin on Steve Jobs's hypocritical stance towards death
First, Darwin describes Jobs's (far mode) stance towards death:
> As Aschwin points out Jobs is on record (his Stanford Commencement Speech) as saying that death is the best thing that ever happened to life - that it clears out the old, and makes way for ... |
30fe7df8-7b53-4e2e-983b-03682af91e45 | trentmkelly/LessWrong-43k | LessWrong | Link Retrospective for 2020 Q1
Below are a list of interesting content I came across in the first quarter of 2020. I subdivided the links into the type of medium they use, namely auditory, textual, and visual. The links are in no particular order.
1. Auditory
D. McRaney. How a Divisive Photograph of a Perceptually A... |
88adb992-cec1-4121-97e1-3feb2a32dc0f | trentmkelly/LessWrong-43k | LessWrong | Domain Theory and the Prisoner's Dilemma: FairBot
Wishes it were crossposted from the AI Alignment Forum. Contains more technical jargon than usual.
Recall Robust Cooperation in the Prisoner's Dilemma and a hint of domain theory.
In the Prisoner's Dilemma, players have the opportunity to harm the opponent for minor ... |
a9718087-89ee-467f-97e2-a78c4d34eeab | trentmkelly/LessWrong-43k | LessWrong | Crush Your Uncertainty
Bayesian epistemology and decision theory provide a rigorous foundation for dealing with mixed or ambiguous evidence, uncertainty, and risky decisions. You can't always get the epistemic conditions that classical techniques like logic or maximum liklihood require, so this is seriously valuable. ... |
19a3bf5f-b154-4a02-9c60-172e61f6f7f1 | trentmkelly/LessWrong-43k | LessWrong | Are you being p-hacked? Time to hack back.
|
f46d709b-372b-4b1d-9948-2056d04c608c | trentmkelly/LessWrong-43k | LessWrong | Rationalist subreddit
I'm experimenting with a new rationalist subreddit on reddit.com
/r/rationalisthmus
Starting with links populated from the planet rationalist data set - to which I've added about 50 new sources in the past few weeks. |
7a4ec5f2-b9e0-49fc-8e7e-0215c3769262 | trentmkelly/LessWrong-43k | LessWrong | Adult Neurogenesis – A Pointed Review
[I am not a neuroscientist and apologize in advance for any errors in this article.]
Hey, let’s review the literature on adult neurogenesis! This’ll be really fun, promise.
Gage’s Neurogenesis In The Adult Brain, published in the Journal Of Neuroscience and cited 834 times, begi... |
9814e35d-db3d-4bc3-bfab-95ad3acf58c5 | trentmkelly/LessWrong-43k | LessWrong | Maybe you can learn exotic experiences via analytical thought
The contents of this post:
* I argue that you can create exotic experiences at will via mere analytical thought. I think you can easily enough learn the weirdest types of synesthesia. Without any substances.
* This post touches on the binding problem and... |
40609dcf-81bd-4477-9e74-5f5ca2055a96 | trentmkelly/LessWrong-43k | LessWrong | When should we be surprised that an invention took “so long”?
My first highly popular essay was “Why did we wait so long for the bicycle?” I’ve asked the same question of the cotton gin and the threshing machine. Others have asked it of the steam engine and the wheel. Recently Brian Potter asked it about wind power an... |
04741ef8-6587-4881-b19d-e8d72c655f32 | trentmkelly/LessWrong-43k | LessWrong | Terminal and Instrumental Beliefs
Cross-Posted on By Way of Contradiction
As you may know from my past posts, I believe that probabilities should not be viewed as uncertainty, but instead as weights on how much you care about different possible universes. This is a very subjective view of reality. In particular, it s... |
304f8b1a-f369-4833-9fcb-f938feea7631 | trentmkelly/LessWrong-43k | LessWrong | Open Thread Spring 2025
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 invited. This is a... |
06127605-006e-44da-8f9d-810511f51ac9 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Moscow, Theory and Practice
Discussion article for the meetup : Moscow, Theory and Practice
WHEN: 17 March 2013 04:00:00PM (+0400)
WHERE: Russia, Moscow, ulitsa L'va Tolstogo 16
Please use the following guide to get to the meetup: link. You need the second revolving door with the sign “Yandex Money” in Rus... |
8b663ea7-56c9-4a1e-8821-28d7a7784374 | trentmkelly/LessWrong-43k | LessWrong | From language to ethics by automated reasoning
Posted also on the EA Forum.
Introduction
In Naturalism and AI alignment I claimed that we might get an aligned AI by building an agent which derives its own preferences (a partial order over world-histories) from its knowledge of the natural world.
Now I am working o... |
62e761a9-38f4-4e0a-b96e-1c52f88acdd7 | trentmkelly/LessWrong-43k | LessWrong | Twenty basic rules for intelligent money management
1. Start investing early in life.
The power of compound interest means you will have much more money at retirement if you start investing early in your career. For example, imagine that at age eighteen you invest $1,000 and earn an 8% return per year. At age se... |
ec5f662f-a094-4188-8999-cd55ab07d71c | StampyAI/alignment-research-dataset/blogs | Blogs | MIRI’s April newsletter: Relaunch Celebration and a New Math Result
| | |
| --- | --- |
|
| |
| --- |
|
|
|
|
| | | |
| --- | --- | --- |
|
| | |
| --- | --- |
|
| |
| --- |
|
Greetings from The Executive Director
Dear friends,
These are exciting times at MIRI.
After years of awareness-raising... |
24c0c795-a476-46fc-bea6-c4adbf5b6120 | trentmkelly/LessWrong-43k | LessWrong | Thoughts on the implications of GPT-3, two years ago and NOW [here be dragons, we're swimming, flying and talking with them]
> When GPT-3 first came out, I registered my first reactions in a comment at Marginal Revolution, which I've appended immediately below the picture of Gojochan and Sparkychan. I'm currently comp... |
d80ccd09-60fe-44ba-8121-5b52b2f19fed | trentmkelly/LessWrong-43k | LessWrong | Identity Isn't In Specific Atoms
Continuation of: No Individual Particles
Followup to: The Generalized Anti-Zombie Principle
Suppose I take two atoms of helium-4 in a balloon, and swap their locations via teleportation. I don't move them through the intervening space; I just click my fingers and cause them to swap... |
3e867fcc-4e7d-4120-b2af-738a2a3256a2 | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post872
TL;DR: Play this online game to help CHAI researchers create a dataset of prompt injection vulnerabilities. RLHF and instruction tuning have succeeded at making LLMs practically useful, but in some ways they are a mask that hides the shoggoth beneath . Every time a new LLM is released, we see just how easy... |
940b5797-f10e-4174-89ff-c613c1d655aa | trentmkelly/LessWrong-43k | LessWrong | [Intro to brain-like-AGI safety] 6. Big picture of motivation, decision-making, and RL
(Last revised: July 2024. See changelog at the bottom.)
6.1 Post summary / Table of contents
Part of the “Intro to brain-like-AGI safety” post series.
Thus far in the series, Post #1 set out some definitions and motivations (what... |
d3163987-e782-41cc-a73e-2af788692dd7 | trentmkelly/LessWrong-43k | LessWrong | OpenAI Alums, Nobel Laureates Urge Regulators to Save Company's Nonprofit Structure
Converting to a for-profit model would undermine the company's founding mission to ensure AGI "benefits all of humanity," argues new letter
This is the full text of a post from Obsolete, a Substack that I write about the intersection o... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.