id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
704403f1-9b5d-4c93-89b2-a6a21d517491 | trentmkelly/LessWrong-43k | LessWrong | GWWC Reporting Attrition Visualization
A few weeks ago Giving What We Can published their impact evaluation. As an organization that supports people in making long term altruistic commitments, the question of how much people stick to those commitments is pretty important. We don't know what people are actually doing, ... |
eba08967-8135-46a7-8f9f-2ed66810c135 | trentmkelly/LessWrong-43k | LessWrong | Coalescence - Determinism In Ways We Care About
(epistemic status: all models are wrong but some models are useful; I hope this is at least usefully wrong. also if someone's already done things like this please link me their work in the comments as it's very possible I'm reinventing the wheel)
I think utility functio... |
6a2fe275-6018-4f4c-804b-65e181446269 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | 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... |
7a2c5c97-4b28-4ce4-b032-3bfda992786d | trentmkelly/LessWrong-43k | LessWrong | There aren't enough smart people in biology doing something boring
Note: this essay is co-written with Eryney Marrogi, who helped seed the initial idea and edited this piece a fair bit. On a related note, I’m helping him run an NYC meetup event on Wednesday, November 20th in Williamsburg, you should sign up here to co... |
4dd8fc13-5248-43fa-b315-01b093e40fc0 | trentmkelly/LessWrong-43k | LessWrong | Any Trump Supporters Want to Dialogue?
It's that time of year - the time when rationality seems increasingly scarce as political tensions rise. I find myself wishing I could have one of the people I see reaching super different conclusions shoot me with a POV gun so I could understand what it's like being on the othe... |
ac1ca588-44c2-4dca-8f68-1faf25fb1ef5 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | How to use AI speech transcription and analysis to accelerate social science research
Summary
=======
* AI tools like OpenAI Whisper and GPT-3 can be used to improve social science research workflows by helping to collect and analyse speech and text data.
* In this article, I describe two worked examples where I appl... |
db44b847-645a-4723-8c08-c2a11f4ba588 | trentmkelly/LessWrong-43k | LessWrong | What If It Rains?
Follow Up To: Full Service
Gas stations in New Jersey do not have awnings to protect customers from the rain. Let us presume for the moment that due to some combination of inertia, regulations and initial costs, it is not practical for them to create such awnings in the short term. Now suppose that ... |
3750a0fc-ffe4-4b4e-ba7a-872e9b700054 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Previously: Short Termism and Quotes from Moral Mazes
Epistemic Status: Long term
My list of quotes from moral mazes has a section of twenty devoted to short term thinking. It fits with, and gives internal gears and color to, my previous understanding of of the problem of short termism.
Much of what we think of as a S... |
9ea4d462-bda3-40dd-ab20-b87a3dc58d85 | trentmkelly/LessWrong-43k | LessWrong | [LINK] The NYT on Everyday Habits
The New York Times just published this article on how companies use data mining and the psychology of habit formation to effectively target ads.
> The process within our brains that creates habits is a three-step loop. First, there is a cue, a trigger that tells your brain to go into... |
8b889e73-7e5e-4e6f-bcff-fca93d89cae6 | trentmkelly/LessWrong-43k | LessWrong | AXRP Episode 38.2 - Jesse Hoogland on Singular Learning Theory
YouTube link
You may have heard of singular learning theory, and its “local learning coefficient”, or LLC - but have you heard of the refined LLC? In this episode, I chat with Jesse Hoogland about his work on SLT, and using the refined LLC to find a new c... |
9e38b489-1ff3-4813-9eaf-419c168f406e | trentmkelly/LessWrong-43k | LessWrong | Edge Cases in AI Alignment
This post is a report on the benchmark I produced as part of the ML Alignment & Theory Scholars Program (Winter 2024-25 Cohort) under the mentorship of Evan Hubinger.
Key Points
* A living benchmark for unusual but impactful scenarios in AI alignment
* ~800 prompts covering 32 topics
* ... |
c6b85115-63e2-4255-b32c-4e8583fcf1ba | trentmkelly/LessWrong-43k | LessWrong | What is the strongest argument you know for antirealism?
Other questions you can answer:
What is the strongest argument against moral realism?
If you think nothing is "valuable in itself" / "objectively valuable", why do you think so?
How do you know that disinterested (not game-theoretic or instrumental) altruism ... |
8e43c5ac-2a51-4355-9884-c10362a1bba8 | trentmkelly/LessWrong-43k | LessWrong | Requiem for the hopes of a pre-AI world
A few months from now, I turn 55. I've been a transhumanist since my teens in the late 1980s; since I got online in the 1990s, I have participated remotely in the talking shops and virtual salons of Internet transhumanism and, later, rationalism. The upheavals of 21st century po... |
0ebd0fa0-6238-4aef-b516-0ac7ef0e858b | trentmkelly/LessWrong-43k | LessWrong | Following human norms
So far we have been talking about how to learn “values” or “instrumental goals”. This would be necessary if we want to figure out how to build an AI system that does exactly what we want it to do. However, we’re probably fine if we can keep learning and building better AI systems. This suggests t... |
2ddb0515-e4e3-47de-9b6b-edfb47caf758 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Moscow: keynote for the first Kocherga year, text analysis, rationality applications discussion
Discussion article for the meetup : Moscow: keynote for the first Kocherga year, text analysis, rationality applications discussion
WHEN: 18 September 2016 02:00:00PM (+0300)
WHERE: Москва, ул. Большая Дорогомило... |
0b1a93f0-c2a0-4fef-934e-5cde38a84dd9 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | List of requests for an AI slowdown/halt.
About this document
===================
There has been a recent flurry of letters/articles/statements/videos which endorse a slowdown or halt of colossal AI experiments via (e.g.) regulation or coordination.
This document aspires to collect all examples into a single central... |
dc4685ff-1e50-4dd5-b117-f421a78d93a0 | trentmkelly/LessWrong-43k | LessWrong | Analyzing the Historical Rate of Catastrophes
To communicate risks, we often turn to stories. Nuclear weapons conjure stories of mutually assured destruction, briefcases with red buttons, and nuclear winter. Climate change conjures stories of extreme weather, cities overtaken by rising sea levels, and crop failures. P... |
1d53e604-655f-4af7-87d0-843bcbd4a8a9 | trentmkelly/LessWrong-43k | LessWrong | The Future of Humanity Institute could make use of your money
Many people have an incorrect view of the Future of Humanity Institute's funding situation, so this is a brief note to correct that; think of it as a spiritual successor to this post. As John Maxwell puts it, FHI is "one of the three organizations co-sponso... |
aee75276-7f32-481a-bb41-3d4655ac2924 | StampyAI/alignment-research-dataset/blogs | Blogs | Forecasting potential misuses of language models for disinformation campaigns and how to reduce risk
Generative Language Models and Automated
Influence Operations:
Emerging Threats and Potential Mitigations
Josh A. Goldstein1,3, Girish Sastry2, Micah Musser1,
Renée DiResta3, Matthew Gentzel2, and Katerina Sedova1
1Ge... |
faf5317d-dc67-46ae-aa92-0c1478659ab7 | trentmkelly/LessWrong-43k | LessWrong | Torture vs Specks: Sadist version
Suppose that instead of the classic version of torture vs specks where the choice is between specks in the eyes of 3^^^3 people or one person tortured for 50 years, there are no specks but rather there are 3^^^3 people who just want the one guy to be tortured. (No particular reason, t... |
a9c21008-8e7b-4d73-9822-0fbfe323c6de | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | A world in which the alignment problem seems lower-stakes
The danger from power-seeking is not *intrinsic* to the alignment problem. This danger also depends on [the structure of the agent's environment](https://www.lesswrong.com/posts/b6jJddSvWMdZHJHh3/environmental-structure-can-cause-instrumental-convergence).
In... |
75477c81-7f4e-471d-9cf8-39a946148446 | trentmkelly/LessWrong-43k | LessWrong | Emergent Misalignment & Realignment
Reproduction, Extension & Mitigations
Authors: Elizaveta Tennant, Jasper Timm, Kevin Wei, David Quarel
In this project, we set out to explore the generality of Emergent Misalignment (via a replication and some extensions) and how easy it is to mitigate. This project was conducted... |
0cd286e2-ffd9-4f96-8504-2c8d2d1ff61a | trentmkelly/LessWrong-43k | LessWrong | Interpreting the Biobot Spike
Boston has a really interesting program where it measures covid RNA frequency during sewage treatment. It's been running since the beginning of the pandemic:
One thing I really like about this as a source of data is that it avoids some of the problems with tracking tests. It has no dep... |
86cf693a-b723-46bb-ab42-3f0fbdc684e8 | StampyAI/alignment-research-dataset/blogs | Blogs | Interviews on plausibility of AI safety by default
This is a list of interviews on the plausibility of AI safety by default.
Background
----------
AI Impacts conducted interviews with several thinkers on AI safety in 2019 as part of a project exploring arguments for expecting advanced AI to be safe by default. The... |
08b3d351-85c7-4e44-ae01-07c53e6e09a8 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Vingean Agency
I've been involved with several discussions about different notions of agency (and their importance/relationships) lately, especially with the PIBBSS group including myself, Daniel, Josiah, and Ramana; see [here](https://www.lesswrong.com/posts/rQDYQrDjPGqjrf8Mk/bridging-expected-utility-maximization-an... |
12a5325e-5232-4d5a-a8b9-134cd265990a | trentmkelly/LessWrong-43k | LessWrong | Detecting out of distribution text with surprisal and entropy
When large language models (LLMs) refuse to help with harmful tasks, attackers sometimes try to confuse them by adding bizarre strings of text called "adversarial suffixes" to their prompts. These suffixes look weird to humans, which raises the question: do... |
cababb1d-c72d-40ac-9b63-b8f7aec948d2 | trentmkelly/LessWrong-43k | LessWrong | K-complexity is silly; use cross-entropy instead
None |
4a9cfd68-c685-493f-bebe-76a683cd34eb | trentmkelly/LessWrong-43k | LessWrong | Meetup : Fort Collins, Colorado Meetup Wedneday 7pm
Discussion article for the meetup : Fort Collins, Colorado Meetup Wedneday 7pm
WHEN: 29 February 2012 07:00:00PM (-0700)
WHERE: 144 North College Avenue, Fort Collins, CO 80524
What are your cool projects?
Come meet interesting people and up your game.
Discussi... |
a8816c83-5c93-4edc-9844-508dcf4e4a05 | trentmkelly/LessWrong-43k | LessWrong | Intelligence Is Not Magic, But Your Threshold For "Magic" Is Pretty Low
A while ago I saw a person in the comments to Scott Alexander's blog arguing that a superintelligent AI would not be able to do anything too weird and that "intelligence is not magic", hence it's Business As Usual.
Of course, in a purely technica... |
5f8bb3f5-825f-4996-b131-1dcaad760b73 | trentmkelly/LessWrong-43k | LessWrong | Learned helplessness about "teaching to the test"
I keep wondering why is there so much learned helplessness about "teaching to the test".
It is often used as an example of Goodharting (e.g. here), and the implied conclusion seems to be... that it is wrong to try testing students systematically, because it is known t... |
ad16acca-f274-43c1-8628-0fa3e461c96e | trentmkelly/LessWrong-43k | LessWrong | Distinguishing logistic curves: visual
I wrote a post about distinguishing between logistic curves, specifically for finding their turning points.
That post was highly mathematical; but here is a visual "proof" of the "theorem":
* Figuring out the turning point of a logistic curve before hitting that turning point ... |
3bf9e71e-33df-42eb-8e49-2f6b142d3d7a | StampyAI/alignment-research-dataset/lesswrong | LessWrong | The Dark Side of Cognition Hypothesis
It is sometimes claimed that the ultimate, unifying goal of artificial intelligence research is to instantiate human-level cognition in a computational system (e.g., Minsky, 1961; Lake et al, 2017). If artificial general intelligence (AGI) of this sort is ever successfully develop... |
6e79b1f3-e9c3-4574-a78c-30e36eb96181 | trentmkelly/LessWrong-43k | LessWrong | Software for Critical Thinking, Prof. Geoff Cumming
Prof. Geoff Cumming has done some interesting work. Of particular relevance to the LW community, he has studied software for enhancing critical thinking.
> My past research: I worked on Computer tools for enhancing critical thinking, with Tim van Gelder. We stud... |
1011438a-2ee2-4f44-a01a-d6fc92fffc16 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "I have watched more than one conversation—even conversations supposedly about cognitive science—go the route of disputing over definitions. Taking the classic example to be "If a tree falls in a forest, and no one hears it, does it make a sound?", the dispute often follows a course like this: If a tree falls in the fo... |
21829624-3e2b-4cfa-962e-083826da3907 | trentmkelly/LessWrong-43k | LessWrong | Why we need better science, example #6,281
Avorn (2004) reports:
> In a former British colony, most healers believed the conventional wisdom that a distillation of fluids extracted from the urine of horses, if dried to a powder and fed to aging women, could act as a general tonic, preserve youth, and ward of a variet... |
9d06551c-431a-4eb1-94c1-5361fe84aee4 | trentmkelly/LessWrong-43k | LessWrong | Diana Fleischman and Geoffrey Miller - Audience Q&A
Cross-posted from Putanumonit.
----------------------------------------
This is the audience Q&A with Diana Fleischman and Geoffrey Miller at the NYC Rationality meetup, following up on my own interview which you can find here.
Content note: the audience compris... |
6507b96a-65a6-4e85-9127-9beb379633ce | trentmkelly/LessWrong-43k | LessWrong | Lies on the internet
After a visit to the dentist, you go home and search up "numbers read off during dental exam."
What were they measuring? You think.
A website that looks like a legitimate dental company tells you these numbers are measurements of gum disease.
When I saw this, alarm bells went off. First of all... |
7d6cda9c-283d-43d3-9522-b0a2457cd7a1 | trentmkelly/LessWrong-43k | LessWrong | Act into Uncertainty
It’s only been recently that I’ve been thinking about epistemics in the context of figuring out my behavior and debiasing. Aside from trying to figure out how I actually behave (as opposed to what I merely profess I believe), I’ve been thinking about how to confront uncertainty—and what it feels l... |
9e94adf6-729c-476a-89ec-e29ebc89ced5 | trentmkelly/LessWrong-43k | LessWrong | Which headlines and narratives are mostly clickbait?
Or: What do superforecasters tend to think of the topics that get tweets and airtime these days? The following questions get put into my attention (consensually and otherwise) and I am genuinely uncertain about the answers.
* Is Trump really gearing up for a fas... |
062d3767-e621-4aea-b890-81d5f9bb9967 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Causal Scrubbing: a method for rigorously testing interpretability hypotheses [Redwood Research]
*\* Authors sorted alphabetically.*
Summary: This post introduces causal scrubbing, a principled approach for evaluating the quality of mechanistic interpretations. The key idea behind causal scrubbing is to test inter... |
3343ec6e-31e0-4674-a88b-c1cd036e7be0 | trentmkelly/LessWrong-43k | LessWrong | A Gamification Of Education: a modest proposal based on the Universal Decimal Classification and RPG skill trees
While making the inventory of my personal library and applying the Universal Decimal System to its classification, I found myself discovering a systematized classification of fields of knowledge, nested an... |
564b91b2-654f-4d8b-a5fd-c8e09af28ec0 | trentmkelly/LessWrong-43k | LessWrong | What's the effective R for the Delta variant of COVID-19?
I have the impression that R for COVID-19 overall matters at the moment relatively little. What's matters is the R for the Delta variant. When Googling I can't find any such data for the US, the UK or any European state. I'm not sure whether this is due to inco... |
f202e3dc-b2bc-4a1c-8e18-b07e43c57976 | trentmkelly/LessWrong-43k | LessWrong | Quick Poll: Booster Reactions
Lots of people are getting covid boosters now. To help myself and others plan I did an extremely informal poll on Twitter and Facebook about how people’s booster side effects compared to their second dose. Take home message: boosters are typically easier than second shots, but they’re bad... |
f66c8a8a-97a0-44e2-b903-a64c6ac06484 | trentmkelly/LessWrong-43k | LessWrong | Does hormetism work? Opponent process theory.
To the fun theory, hedonic treadmill sequences.
http://gettingstronger.org/hormesis/
TL;DR stoicism with science.
Key idea: OPT, Opponent Process Theory: http://gettingstronger.org/2010/05/opponent-process-theory/
Research, PDF: http://gettingstronger.org/wp-content/up... |
eef5bf12-9c8b-40f4-b7de-283f7ceb5035 | trentmkelly/LessWrong-43k | LessWrong | Lifehack Ideas January 2015
> Life hacking refers to any trick, shortcut, skill, or novelty method that increases productivity and efficiency, in all walks of life.
— Wikipedia
This thread is for posting any promising or interesting ideas for lifehacks you've come up with or heard of. If you've successfully implem... |
4b85c27b-732d-43fd-a820-298fc74590c4 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | [Short version] Information Loss --> Basin flatness
This is an overview for advanced readers. Main post: [Information Loss --> Basin flatness](https://www.lesswrong.com/posts/wPudaEemohdYPmsye/information-loss-greater-than-basin-flatness)
**Summary:**
Inductive bias is related to, among other things:
* Basin flatn... |
7f5f72f1-1ca2-4034-b384-ea02cdb0e641 | trentmkelly/LessWrong-43k | LessWrong | David Krueger on AI Alignment in Academia, Coordination and Testing Intuitions
David Krueger is an assistant professor at the University of Cambridge and got his PhD from Mila. His research group focuses on aligning deep learning systems, but he is also interested in governance and global coordination. He does not hav... |
b44ae31d-e525-48e3-8ca6-f5f4d84d2f31 | trentmkelly/LessWrong-43k | LessWrong | Random variables and Evidential Decision Theory
This post is inspired by the recent discussion I had with IlyaShpitser and Vaniver on EDT.
A random variable only ever has one value
In probability theory, statistics and so on, we often use the notion of a random variable (RV). If you go look at the definition, you wi... |
38ba1bc1-5bf2-45bd-9b15-81fb85310ee4 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Can Transformers Reason About Effects of Actions?
1 Introduction
---------------
Giving the long pursued goal of AI - starting with McCarthy’s Advice Taker (McCarthy [1959](#bib.bib17)) - of having systems that can reason with explicitly given general knowledge as a motivation, the recent work (Clark, Tafjord, and
... |
05ab072c-504e-481b-bcae-31aba9cf5a19 | trentmkelly/LessWrong-43k | LessWrong | Election Preparation
Historically, uncertainty about who is the rightful leader has often led to violence. While I think the most likely outcome for the coming election in the US is a peaceful transition from Trump to Biden, the range of possibilities is wide enough that it's worth making some preparations for worse o... |
98ef9d44-44a4-426c-8b7f-90d2bd498d3b | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | What does the Project Management role look like in AI safety?
Project Management (PM) is a common role in the tech industry. However, I cannot find much information about this role in the AI safety field other than this earn-to-give focused 80k [career review](https://80000hours.org/career-reviews/product-manager-in-t... |
496cdd61-f7c7-4670-8d24-ba2c0162aa39 | trentmkelly/LessWrong-43k | LessWrong | What are we assuming about utility functions?
I often notice that in many (not all) discussions about utility functions, one side is "for" their relevance, while others tend to be "against" their usefulness, without explicitly saying what they mean. I don't think this is causing any deep confusions among researchers h... |
fdb1ea00-fce7-41b6-b7b6-665797bb4df2 | trentmkelly/LessWrong-43k | LessWrong | Meetup : MelbLW: January Social Meetup
Discussion article for the meetup : MelbLW: January Social Meetup
WHEN: 16 January 2015 06:30:00PM (+0800)
WHERE: The Bull & Bear Tavern, 347 Flinders Lane, Melbourne
January's social meetup is scheduled for this Friday (16th January) at 6:30pm as usual. This month, we will be... |
d45a8678-4e6b-472d-a58f-174afadf03db | trentmkelly/LessWrong-43k | LessWrong | Beyond Optimization by Proxy
Followup to: Is Google Paperclipping the Web? The Perils of Optimization by Proxy in Social Systems
tl;dr: In this installment, we look at methods of avoiding the problems related to optimization by proxy. Many potential solutions cluster around two broad categories: Better Measures, and ... |
6883c64f-531a-48cf-98c3-d3d2010dc940 | trentmkelly/LessWrong-43k | LessWrong | The Polarity Problem [Draft]
This is a draft written by Cameron Domenico Kirk-Giannini, assistant professor at Rutgers University, and Simon Goldstein, associate professor at the Dianoia Institute of Philosophy at ACU, as part of a series of papers for the Center for AI Safety Philosophy Fellowship's midpoint. Dan hel... |
12b3126a-da12-48e1-b0c0-38f4455546fe | trentmkelly/LessWrong-43k | LessWrong | Where is all this evidence of UFOs?
In his latest blog, Robin Hanson writes
> There have been over 100K UFO sightings reported worldwide since 1940. Roughly 5% or so are “strong” events, which seem rather hard to explain due to either many witnesses, especially reliable witnesses, physical evidence, or other factors.... |
7b538128-4ed3-48fa-b90c-c4a19b8fd1be | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post438
Sometimes people talk about two AIs being “the same” or “different” AIs. We think the intuitive binary of “same vs. different” conflates several concepts which are often better to disambiguate. In this post, we spell out some of these distinctions. We don’t think anything here is particularly novel; we wro... |
be585644-f3f8-4a7e-911b-6171f5bff453 | trentmkelly/LessWrong-43k | LessWrong | Auditing failures vs concentrated failures
TL;DR: If you want to notice when powerful AIs are behaving badly, a reasonable strategy is to carefully audit a small fraction of AI actions. This kind of strategy has two kinds of failures which can be tackled somewhat independently: auditing failures, where the audits fail... |
54cf2913-028a-4027-a182-2b92cf42ba1e | trentmkelly/LessWrong-43k | LessWrong | 1689: Uncovering the World New Institutionalism Created
The Glorious Revolution is a celebrated event in English history. The bloodless overthrow of the autocratic James II by a grand coalition of civic-minded nobles has inspired the prose of three centuries of writers, all marveling at this great effusion of freedom,... |
bff159bc-3821-45f3-bba6-7cf6f8b72b14 | trentmkelly/LessWrong-43k | LessWrong | Is veganism morally correct?
The first argument I've heard mainly comes down to showing that there aren't meaningful distinguishing factors between animals and humans, so that if you're fine eating animals, you should also be fine eating humans under some circumstances.
Another argument I've heard is that if you acc... |
e6af75fb-5be7-48e4-9fd1-eab8da186cbc | trentmkelly/LessWrong-43k | LessWrong | AI 2027 - Rogue Replication Timeline
I envision a future more chaotic than portrayed in AI 2027. My scenario, the Rogue Replication Timeline (RRT), branches off mid-2026. If you haven’t already read the AI 2027 scenario, I recommend doing so before continuing.
You can read the full version on my blog, but I have copi... |
b291aa78-9ee0-4082-9988-a68583c11529 | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | Can't we limit damage from AI systems in the same ways we limit damage from companies?
Suppose you ask a household robot to stick a knife in your dishwasher, but it malfunctions and sticks the knife in you instead. That's bad, but you or your surviving family members can sue the manufacturer and buy a different brand ... |
237b6441-11fd-47d1-bc78-89e4e2113e91 | trentmkelly/LessWrong-43k | LessWrong | My third-of-life crisis
I've been wanting to post this for a while, but it always felt too embarrassing. I've contributed next to nothing to this community, and I'm sure you have better problems to work on than my third-of-life crisis. However, the kind of problems I'm facing may require more brainpower than my meatsp... |
301d1a60-1691-4d8f-980c-3cd57086cf6a | trentmkelly/LessWrong-43k | LessWrong | AMA: Earning to Give
This week the Effective Altruism Forum is running an Effective Giving Spotlight, and they asked if I could post an Ask Me Anything (AMA) on my experience earning to give.
Some background:
* I was earning to give from 2009 to 2022, except for a few months in 2017 when I worked on expanding acc... |
9951d886-5e4d-4d52-91df-4bb3dce90f95 | trentmkelly/LessWrong-43k | LessWrong | Should I post technical ideas here or on LessWrong 2.0?
Which would reach the most relevant people? |
c523ceb3-3089-4428-9829-ecf03862f200 | trentmkelly/LessWrong-43k | LessWrong | [LINK] Matrix-Style Learning
http://io9.com/5867113/scientists-say-theyre-paving-the-way-towards-matrix+style-learning--but-is-it-safe
Researchers learned to change people's brain structures to make them better at certain tasks. But... They weren't aware of getting better at those tasks! Creepy!
I'd love to see a ... |
93c2c357-c694-46d8-bcec-ef632dbf8437 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | [AN #143]: How to make embedded agents that reason probabilistically about their environments
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/). In particular, you can lo... |
358b081f-65df-4361-af65-08c348d6178c | StampyAI/alignment-research-dataset/arbital | Arbital | Goodness estimate biaser
A "[goodness](https://arbital.com/p/55) estimate [biaser](https://arbital.com/p/statistical_bias)" is a system setup or phenomenon that seems [foreseeably](https://arbital.com/p/6r) likely to cause the actual goodness of some AI plan to be systematically lower than the AI's estimate of that pl... |
645a55bc-4571-4717-affe-e5186caa7c69 | trentmkelly/LessWrong-43k | LessWrong | Generalizing From One Example
Related to: The Psychological Unity of Humankind, Instrumental vs. Epistemic: A Bardic Perspective
"Everyone generalizes from one example. At least, I do."
-- Vlad Taltos (Issola, Steven Brust)
My old professor, David Berman, liked to talk about what he called the "typical mind fall... |
d3eafe5a-142d-4f8c-80e4-910530c7925f | trentmkelly/LessWrong-43k | LessWrong | Productive Mistakes, Not Perfect Answers
This post is part of the work done at Conjecture.
I wouldn’t bet on any current alignment proposal. Yet I think that the field is making progress and abounds with interesting opportunities to do even more, giving us a shot. Isn’t there a contradiction?
No, because research pr... |
a95cb63b-98fb-4a82-9163-9504987d3143 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Reinforcement Learning of Implicit and Explicit Control Flow Instructions.
1 Introduction
---------------
An important goal in artificial intelligence is developing flexible and
autonomous agents capable of accomplishing tasks that humans specify in
forms that are expressive to the agent and convenient for the huma... |
7f3032b1-61e3-4d71-84a6-3c2c197e2048 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Using GPT-3 to augment human intelligence
A blog post is a very long and complex search query to find fascinating people and make them route interesting stuff to your inbox.
It is like summoning an alien intelligence. I post at night, before crawling into bed next to my kids, and wake in the morning to find my inbox ... |
d92f7040-aef3-49c5-b165-5d49e629bc07 | StampyAI/alignment-research-dataset/special_docs | Other | What the Baldwin Effect affects depends on the nature of plasticity.
What the Baldwin Effect affects depends on the nature of plasticity
===================================================================
Abstract
--------
In a process known as the Baldwin Effect, developmental plasticity, such as learning, has been... |
73c50f9b-9296-4a88-a177-c44995dddb8f | trentmkelly/LessWrong-43k | LessWrong | When should we expect the education bubble to pop? How can we short it?
I won't attempt to summarise the case for there being an education bubble here (see links below for some pointers). Rather, my questions are:
1) assuming there is an education bubble, when will it -- as bubbles tend to do -- pop?
(This plausibl... |
304317e7-1578-4a86-ba4d-6ecfc14be1a7 | trentmkelly/LessWrong-43k | LessWrong | Improving the World
What are we doing to make this world a better (epistemically or instrumentally) place?
Some answers to this question are already written in Bragging Threads and other places, but I think they deserve a special emphasis. I think that many smart people are focused on improving themselves, which is a... |
31736741-fa58-4826-9125-c8f8dfc45f2c | StampyAI/alignment-research-dataset/arxiv | Arxiv | Reasoning About the Transfer of Control
Journal ofArtificial Intelligence Research 37(2010) 437–477 Submitted 8/09; published 3/10
Reasoning abouttheTransferofControl
Wiebe vanderHoek WIEBE.VAN-DER-HOEK@LIV.AC.UK
Dirk Walther DWALTHER@LIV.AC.UK
Michael Wooldridge MJW@LIV.AC.UK
Department ofComputer Science
Univer sityo... |
98a66b56-03c4-427a-9847-e37d2e32aadc | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | Stuart Russell – AI: The Story So Far – CSRBAI 2016
good morning everybody and welcome to
the colloquium series so I'm really
excited for today's lineup of
distinguished speakers starting with
professor Stuart Russell the professor
of computer science and the Smith is a
professor in engineering here at the
University ... |
a1672cb0-1916-45d9-a8e3-46dc089411fb | trentmkelly/LessWrong-43k | LessWrong | An observation on cryocrastination
Why do people cryocrastinate? The most common explanation I’ve heard from intelligent people for not getting cryonics is that the money is better spent on some altruistic cause. By itself there is nothing wrong with this belief, but irrationality lies near.
Before I continue, I am n... |
784b0db3-dedf-4fc0-9985-5b07dd892ac8 | trentmkelly/LessWrong-43k | LessWrong | Counting-down vs. counting-up coherence
[Metadata: crossposted from https://tsvibt.blogspot.com/2022/10/counting-down-vs-counting-up-coherence.html. First completed 25 October 2022.]
Counting-down coherence is the coherence of a mind viewed as the absence of deviation downward in capability from ideal, perfectly effi... |
f424d5bd-314a-4336-9c48-89619f42d16d | trentmkelly/LessWrong-43k | LessWrong | [Linkpost] Human-narrated audio version of "Is Power-Seeking AI an Existential Risk?"
There's now a human-narrated audio version of my report on existential risk from power-seeking AI (text version here). You can find the audio here, or by searching for "Joe Carlsmith Audio" on your podcast app.
Thanks to the folks a... |
ed1a02ac-e042-41cc-96ea-fd74090ea988 | trentmkelly/LessWrong-43k | LessWrong | Weak HCH accesses EXP
This post is a follow-up to my “Alignment proposals and complexity classes” post. Thanks to Sam Eisenstat for helping with part of the proof here.
Previously, I proved that imitative amplification with weak HCH, approval-based amplification, and recursive reward modeling access PSPACE while AI s... |
a82a7e0e-b3df-4328-b17e-a00632b82582 | trentmkelly/LessWrong-43k | LessWrong | "Cheat to Win": Engineering Positive Social Feedback
This post outlines a very simple strategy that's been working for me lately. It may be obvious to some, but it only clicked for me recently.
Positive social stimulation is fun for humans, right? We like to be liked. It makes us cheerful. We're motivated to do thing... |
3b385904-f4ca-4eb9-959c-db8a50ea5922 | trentmkelly/LessWrong-43k | LessWrong | Meetup : London
Discussion article for the meetup : London
WHEN: 01 May 2012 06:30:00PM (+0100)
WHERE: Shakespeares Head, 64-68 Kingsway. Holborn, London, WC2B 6BG
Let's talk about what we want out of meetups! I'd like to encourage everyone to read How to Run a Successful Less Wrong Meetup http://lesswrong.com/r/di... |
b4f312c7-8058-4b0a-9b97-f03b332c0a53 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Models Modeling Models
**I - Meanings of words**
Now that we have[more concrete thinking](https://www.lesswrong.com/posts/z2BPxcFfhKho89D8L/goodhart-ethology) under our belt, it's time to circle back to Goodhart's law for value learners. What sorts of bad behavior are we imagining from future value-learning AI? What ... |
f22daf23-13a9-4597-a13b-809755a1f7d0 | trentmkelly/LessWrong-43k | LessWrong | Privileged Snuff
So one is asked, "What is your probability estimate that the LHC will destroy the world?"
Leaving aside the issue of calling brown numbers probabilities, there is a more subtle rhetorical trap at work here.
If one makes up a small number, say one in a million, the answer will be, "Could you make a m... |
87b18673-300e-4ef0-b130-6c1434ba6f74 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | The other side of the tidal wave
I guess there’s maybe a 10-20% chance of AI causing human extinction in the coming decades, but I feel more distressed about it than even that suggests—I think because in the case where it doesn’t cause human extinction, I find it hard to imagine life not going kind of off the rails. S... |
ba43b8bc-4980-4222-9e53-b74665f47a88 | trentmkelly/LessWrong-43k | LessWrong | Superrationality in arbitrary games
This post is an informal summary of ideas that Scott and I discussed on my recent visit to Los Angeles, meant to serve as a temporary "savepoint" and reference. The approach outlined here, albeit very promising in my opinion, requires a more work to become mature.
Abstract
We intr... |
c8d4038d-c8cd-4cfc-aaca-1c15fcee717b | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Alexander and Yudkowsky on AGI goals
This is a lightly edited transcript of a chatroom conversation between Scott Alexander and Eliezer Yudkowsky last year, following up on the [Late 2021 MIRI Conversations](https://www.lesswrong.com/s/n945eovrA3oDueqtq). Questions discussed include "How hard is it to get the right go... |
c537658e-397c-428e-bc1c-c02475abfec7 | trentmkelly/LessWrong-43k | LessWrong | Attach Receipts to Credit Card Transactions
If you log into your credit card account you'll see a list of charges, each with a date, amount, and merchant. It would be helpful if this also included receipt data:
* If you didn't recognize a charge, seeing what it was for could remind you.
* If you needed a receipt... |
d475f450-b13f-4d4e-8c02-59f4d553a90e | trentmkelly/LessWrong-43k | LessWrong | AI #93: Happy Tuesday
You know how you can sometimes have Taco Tuesday… on a Thursday? Yep, it’s that in reverse. I will be travelling the rest of the week, so it made sense to put this out early, and incorporate the rest of the week into #94.
TABLE OF CONTENTS
1. Language Models Offer Mundane Utility. The price... |
2aff575b-f869-4189-abd8-32e1f9be2010 | trentmkelly/LessWrong-43k | LessWrong | OpenAI Boycott Revisit
Note: An initial proposal and some good discussion already existed on LW here. I’m spurring this here as a post instead of a comment due to length, the need for a fresh look, and a specific call to action.
Summary
I think a petition-style boycott commitment could reach critical mass enough ... |
bc40b93b-f6b4-43dd-8dcf-4c5a5b42131c | trentmkelly/LessWrong-43k | LessWrong | Towards Hodge-podge Alignment
ABSTRACT: What could AI alignment look like if we had 6000+ full-time researchers and software developers? I've spent a few days thinking about that question, and this report is my first-draft attempt to answer it. This report sketches a highly-scalable research agenda: studying the hodge... |
91c970b0-d2d5-47e0-a4f5-0a130b5578ef | trentmkelly/LessWrong-43k | LessWrong | Bet or update: fixing the will-to-wager assumption
(Warning: completely obvious reasoning that I'm only posting because I haven't seen it spelled out anywhere.)
Some people say, expanding on an idea of de Finetti, that Bayesian rational agents should offer two-sided bets based on their beliefs. For example, if you th... |
54fbba7c-a5c5-4a73-b49e-a6a0bfd2cf58 | StampyAI/alignment-research-dataset/special_docs | Other | The history and future of AI.
Abstract
--------
The standard model for developing AI systems assumes a fixed, known objective that the AI system is required to optimize through its actions. Systems developed within the standard model have been increasingly successful. I briefly summarize the state of the art and its... |
59d2811b-9876-4977-be59-cddb946aad1e | trentmkelly/LessWrong-43k | LessWrong | MIRI's 2015 Winter Fundraiser!
MIRI's Winter Fundraising Drive has begun! Our current progress, updated live:
Donate Now
Like our last fundraiser, this will be a non-matching fundraiser with multiple funding targets our donors can choose between to help shape MIRI’s trajectory. The drive will run until Decem... |
c13b1b7d-ac64-4cbd-ba9e-5d730c3ebe4e | trentmkelly/LessWrong-43k | LessWrong | Naval Ravikant and Chris Dixon Didn't Explain Any Web3 Use Cases
This is a followup to Chris Dixon's Crypto Claims Are Logically Flimsy.
It's becoming popular for thought leaders in the investing and crypto world to make bold claims that aren't backed up by any specific examples. The latest person to prominently do t... |
bff0dac7-c61e-4320-b756-820067e81994 | trentmkelly/LessWrong-43k | LessWrong | Martin Seligman’s “Authentic Happiness”
Martin E.P. Seligman (W) is a pioneer of “positive psychology” (W). His book Authentic Happiness (2002) is a pop-psych examination of how people can use positive psychology in their lives (I've put page number references in superscript below).
Positive psychology
Positive psyc... |
b7fcc1d5-c447-4bd5-aa74-4349056ae147 | trentmkelly/LessWrong-43k | LessWrong | What I Would Do If I Were Working On AI Governance
I don’t work in AI governance, and am unlikely to do so in the future. But various anecdotes and, especially, Akash’s recent discussion leave me with the impression that few-if-any people are doing the sort of things which I would consider sensible starting points, an... |
601d6bce-6b43-4cde-b3a6-2bdebc133d46 | trentmkelly/LessWrong-43k | LessWrong | The Problem With The Current State of AGI Definitions
The following includes a fictionalized account of a conversation had with professor Viliam Lisý at EAGx Prague, with most of the details just plain made up because I forgot how it actually went. Special thanks to professor Dušan D. Nešić, who I mistakenly thought I... |
7ad35495-e1be-4c37-9896-ae2d34d0c564 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | The Happy Dance Problem
*[[Cross-posted from IAFF.]](https://agentfoundations.org/item?id=1713)*
Since the invention of logical induction, people have been trying to figure out what logically updateless reasoning could be. This is motivated by the idea that, in the realm of Bayesian uncertainty (IE, empirical uncert... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.