id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
8ebe6c14-48ea-416f-acaa-2c7f4a274a4b | trentmkelly/LessWrong-43k | LessWrong | I'm broken...?
It seems that every time I try to go to this meetup announcement I posted, I get the spiffy new Less Wrong "system has crashed" error. I get the same problem when I click on my username (presumably because the top post in that list is the one linked to above).
It was working fine earlier. I'm not sur... |
a381c684-7d94-4bb3-801b-5f9ee4178989 | trentmkelly/LessWrong-43k | LessWrong | Russian x-risks newsletter March 2020 – coronavirus update
Russia recently attracted attention as it reported fewer CV cases than other countries. Probably the best explanation is under-reporting and under-testing. Other explanations are shorter life expectancy and higher home temperature.
Russia government is taking... |
844ef6cf-fb79-48b7-be28-3e186c8c8e60 | trentmkelly/LessWrong-43k | LessWrong | (Trying To) Study Textbooks Effectively: A Year of Experimentation
When I started studying the art of studying, I wanted to understand the role of book learning. How do we best learn from a textbook, scientific article, or nonfiction book? What can a student of average intelligence do to stay on top of their homework?... |
0b0c252e-519b-41e9-98ee-1249d37e4834 | trentmkelly/LessWrong-43k | LessWrong | What is Wisdom?
Cross-posted on my blog: http://garybasin.com/what-is-wisdom/
What could go wrong if we develop technology to significantly amplify the intelligence of human minds? Intelligence is tricky to understand and I get confused when comparing it to the related concepts of wisdom and rationality. I'd like to... |
f32782ed-24f3-49a0-8cff-f486f017f8b3 | trentmkelly/LessWrong-43k | LessWrong | 20 Modern Heresies
Burning of Jan Hus, Spiezer Chronicle, 1485
You may have heard about Hereticon, an exclusive invite-only “conference for thoughtcrime” that recently happened in Miami. While I’m sure there were some true heretics in attendance, the cynical part of me feels like it was basically just an excuse for ri... |
a1838131-2ea8-4bf0-a82a-5a14b25b1696 | trentmkelly/LessWrong-43k | LessWrong | The Ferrett: "The Day I Realized My Uncle Hung Around With Gay Guys"
Updated link. |
58aeff35-b456-4c8c-a3f9-7b6ba683306f | trentmkelly/LessWrong-43k | LessWrong | Open and Welcome Thread – June 2021
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 invite... |
ccf848d1-27d6-4c67-b584-b599f8a728a4 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | Careers in technical AI safety | Owain Evans and Victoria Krakovna | EA Global: London 2017
now very pleased to introduce a wine
Evans and Victoria Krakov now so a wine
works on AI safety and reinforcement
learning at the future of humanities
Institute at the University of Oxford he
also leads a project on inferring h... |
c5529d00-010f-4d09-9f85-8d8e71f18ee6 | trentmkelly/LessWrong-43k | LessWrong | Some questions I've been pondering...
* Was there an objective reality that existed whether or not we could ever observe it?
* Were there laws that restored strict causality to phenomena that seemed inherently random?
* Was everything in the universe predetermined?
* When do political parties start being a bad ide... |
0b3e26b9-9cb3-407b-bbdf-0b6074225a63 | trentmkelly/LessWrong-43k | LessWrong | Welcome to Berkeley SSC Meetup [Edit With Your Details]
(The following are our suggestions for what kind of information is best to include in the welcome post of your group, feel free to replace them with whatever you think is best)
What kind of events does your group usually run? What does it usually do?
How freque... |
5085f092-30a3-4927-abb2-7c31b1263cf6 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Key questions about artificial sentience: an opinionated guide
*[crossposted at [LessWrong](https://www.lesswrong.com/posts/cwDbYmnSdoobdcJnx/key-questions-about-artificial-sentience-an-opinionated) and [Experience Machines](https://experiencemachines.substack.com/p/key-questions-about-artificial-sentience); [twitter ... |
fac6be54-ea84-4fb8-a114-0c52e98d544a | trentmkelly/LessWrong-43k | LessWrong | What if we solve AI Safety but no one cares
Suppose that next year, AI Safety is solved, the solution is approved by Eliezer Yudkowsky, etc.
How do we actually get people to follow this solution?
It seems to me a lot of people or companies will ignore any AI Safety solutions for the same reasons they are currently i... |
8221c28e-d524-4137-8928-c9a6e476313a | trentmkelly/LessWrong-43k | LessWrong | Against neglectedness considerations
|
a0756a67-33d2-4713-a5f0-344c68743f8e | trentmkelly/LessWrong-43k | LessWrong | Using the (p,R) model to detect over-writing human values
Loosely crossposted at the Intelligent Agent Forum.
Previously, I presented a model of rationality-reward pairs (p,R), in which R was a reward and p the (ir)rationality planner that mapped the reward R to the agent's policy.
But I recently realised that this ... |
6e98a468-2981-4ce6-9c23-07afe0efa178 | trentmkelly/LessWrong-43k | LessWrong | Superintelligence via whole brain emulation
Most planning around AI risk seems to start from the premise that superintelligence will come from de novo AGI before whole brain emulation becomes possible. I haven't seen any analysis that assumes both uploads-first and the AI FOOM thesis (Edit: apparently I fail at litera... |
f8d875ef-9629-411c-864f-9671c3dab7e7 | StampyAI/alignment-research-dataset/arxiv | Arxiv | The Turing Trap: The Promise & Peril of Human-Like Artificial Intelligence
0 The Turing Trap: The Promise & Peril of Human-Like Artificial Intelligence Erik Brynjolfsson Stanford Digital Economy Lab http://brynjolfsson.com Forthcoming in Dædalus, Spring 2022 In 1950, Alan Turing proposed an “imitation game” as... |
ed35470e-d54c-48e1-b32a-821066a0f01d | trentmkelly/LessWrong-43k | LessWrong | Regreasing a KitchenAid Mixer
I recently got an old KitchenAid mixer from a friend. It's a k45ss, from maybe the early 80s, and the general advice I see is that with typical home use they should be regreased every ~10y. I ordered 4oz of food-safe synthetic grease and followed Mr. Mixer's YouTube guide (parts 1, 2, 3).... |
7bd46c57-4a05-4f7d-80c5-62ac155d04e2 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | [AN #132]: Complex and subtly incorrect arguments as an obstacle to debate
[AN #132]: Complex and subtly incorrect arguments as an obstacle to debate
Alignment Newsletter is a weekly publication with recent content relevant to AI alignment around the world
| | | | | | | | | | | | | | | | | ... |
1dfe6189-c8ca-4966-b8db-62d06cfccd64 | trentmkelly/LessWrong-43k | LessWrong | Prisoner's Dilemma as a Game Theory Laboratory
Last year Yvain had organised a Diplomacy game between LessWrong users to test how well we perform in practical application of game theory. At least two games had been played, but as far as I know no analysis was made afterwards. One reason is probably that few games invo... |
14c4cd0d-a140-4d7a-a373-57d95d60e10a | StampyAI/alignment-research-dataset/blogs | Blogs | Deep Deceptiveness
Meta
----
This post is an attempt to gesture at a class of AI [notkilleveryoneism](https://twitter.com/ESYudkowsky/status/1582666519846080512) (alignment) problem that seems to me to go largely unrecognized. E.g., it isn’t discussed (or at least I don’t recognize it) in the recent plans written up... |
e69ff315-fba7-4a3c-ac45-0dc33ac21af7 | trentmkelly/LessWrong-43k | LessWrong | Should we rely on the speed prior for safety?
This post was written under Evan Hubinger’s direct guidance and mentorship, as a part of the Stanford Existential Risks Institute ML Alignment Theory Scholars (MATS) program.
TL;DR: There is some hope that by penalizing time complexity we could strongly select for non-dec... |
f9a8f5ab-a9ff-406f-a84f-840164da20ff | trentmkelly/LessWrong-43k | LessWrong | On precise out-of-context steering
Meta: This is a minor and relatively unimportant problem I've worked on. I'll be brief in my writing. Thanks to Aaron Scher for lots of conversations on the topic.
Added later: The Covert Malicious Fine-tuning work is both conceptually and empirically superior to what I've done here... |
246bbe96-cf85-4381-bd2f-01ca637c0c72 | trentmkelly/LessWrong-43k | LessWrong | Steps to Achievement: The Pitfalls, Costs, Requirements, and Timelines
Reply to: Humans Are Not Automatically Strategic
In "Humans Are Not Automatically Strategic," Anna Salamon outlined some ways that people could take action to be more successful and achieve goals, but do not:
> But there are clearly also heuris... |
ab2d6e0b-4a0c-46ae-875a-afa65d2e8e0d | trentmkelly/LessWrong-43k | LessWrong | Update Yourself Incrementally
Politics is the mind-killer. Debate is war, arguments are soldiers. There is the temptation to search for ways to interpret every possible experimental result to confirm your theory, like securing a citadel against every possible line of attack. This you cannot do. It is mathematicall... |
340adcf5-ddc1-469e-bfd1-667602570823 | trentmkelly/LessWrong-43k | LessWrong | Good ontologies induce commutative diagrams
Epistemic status: early-stage research ideas; I think they're interesting, but half of them might be wrong
Imagine you're building a robot that can catch a ball by getting observations from a camera and then moving to the correct position. The robot should probably have a p... |
4b7cf673-be7a-48ff-bad4-d6245c75aa10 | trentmkelly/LessWrong-43k | LessWrong | How can I efficiently read all the Dath Ilan worldbuilding?
I liked the April Fools Confession post, I liked the AMA, and I liked that long passage somewhere in planecrash about how they reacted to the discovery of the AI problem. But I wasn't really hooked by the glowfic, and only made it 30 pages in.
Is there a com... |
7d0fa099-57cb-44bc-a0ad-1480baa20878 | StampyAI/alignment-research-dataset/arbital | Arbital | Limited AGI
One of the reasons why a [Task AGI](https://arbital.com/p/6w) can potentially be safer than an [Autonomous AGI](https://arbital.com/p/1g3), is that since Task AGIs only need to carry out activities of limited scope, they [may only need limited material and cognitive powers](https://arbital.com/p/7tf) to ca... |
5c63ecfb-259a-4827-acb7-be6abff7ab43 | trentmkelly/LessWrong-43k | LessWrong | Wolfram's new "Cloud" initiative
I was reading through this:
http://blog.stephenwolfram.com/2013/11/something-very-big-is-coming-our-most-important-technology-project-yet/
which announces the new "Wolfram Cloud" project of Stephen Wolfram and I noticed how much this sounds like "Flare" and EY's old "Plan to Singular... |
4cb8f6ba-f301-4dd0-9538-79b1fc009d02 | trentmkelly/LessWrong-43k | LessWrong | Watching themselves
We've been very lucky with childcare this pandemic. We had an au pair, so when schools closed suddenly on a Wednesday in early March we had live-in child care for Lily (6y) and Anna (4y). Having our children well taken care of without risking exposure outside the home or requiring either of the par... |
0fc1e91d-b103-4ffd-8485-c0dd04bcb795 | trentmkelly/LessWrong-43k | LessWrong | No nonsense version of the "racial algorithm bias"
In discussions of algorithm bias, the COMPAS scandal has been too often quoted out of context. This post gives the facts, and the interpretation, as quickly as possible. See this for details.
THE FIGHT
The COMPAS system is a statistical decision algorithm trained on... |
506798b8-5026-4c6d-8f8b-a742ba09362a | trentmkelly/LessWrong-43k | LessWrong | Do anthropic considerations undercut the evolution anchor from the Bio Anchors report?
The Bio Anchors report by Ajeya Cotra tries to forecast AGI timelines by getting estimates of how much compute might be needed to build or train a model that has general intelligence capabilities. This estimate is based on various b... |
6afcc9c4-a9a1-4d8d-af72-a4beadcac7d2 | trentmkelly/LessWrong-43k | LessWrong | How to deal with a misleading conference talk about AI risk?
Does it make sense to give a public response? Who would be able to do it?
The conference organizer, who had asked me to evaluate the talk, offered to interview me to set things straight. However, I don't know if that is sensible, and given my level of exper... |
5772da0b-ec55-4742-95a1-757002b92f0a | trentmkelly/LessWrong-43k | LessWrong | Questions about Conjecure's CoEm proposal
Conjecture recently released an AI safety proposal. The three of us spent a few hours discussing the proposal and identifying questions that we have. (First, we each re-read the post and independently brainstormed a few questions we had. Then, we discussed the post, exchanged ... |
7ace4620-077b-4880-94ed-57b368c05b46 | trentmkelly/LessWrong-43k | LessWrong | Superintelligence Reading Group 2: Forecasting AI
This is part of a weekly reading group on Nick Bostrom's book, Superintelligence. For more information about the group, and an index of posts so far see the announcement post. For the schedule of future topics, see MIRI's reading guide.
-------------------------------... |
e0906335-473c-49dc-9894-9101e790821b | trentmkelly/LessWrong-43k | LessWrong | All the posts I will never write
This post has been written for the first Refine blog post day, at the end of the week of readings, dicussions, and exercises about epistomology for doing good conceptual research.
(/with courtesy to Adam Shimi who suggested the title and idea. )
Rationality, Probability, Uncertainty... |
3ec0c569-d9b7-44c6-a076-f0617d00af47 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Ethical Injunctions
Today's post, Ethical Injunctions was originally published on 20 October 2008. A summary (taken from the LW wiki):
> A look at the peculiar properties of decision theories that include rules about not doing certain things, even when they seem like the right thing to do.
Discuss th... |
aa687fef-3ff7-4bb0-b28d-973d89ee2bc5 | trentmkelly/LessWrong-43k | LessWrong | The lure of technocracy
I’ve said that society was generally optimistic about progress until the early 20th century, and lost that confidence in the World Wars. By the late 20th century, from about the 1970s on, a deep skepticism and distrust of progress had come to prominence. But what happened in between?
I have a ... |
9d1789bf-0f01-40ce-b231-ef02bfcb7953 | trentmkelly/LessWrong-43k | LessWrong | Conservation of Expected Jury Probability
The New York Times has a calculator to explain how getting on a jury works. They have a slider at the top indicating how likely each of the two lawyers think you are to side with them, and as you answer questions it moves around. For example, if you select that your occupation... |
b1f1ae41-59a6-4899-8bfe-3f8474f9c5a0 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Mental subagent implications for AI Safety
*Meta: I wrote this draft a couple of years ago, but never managed to really proceed down this line of thought to a conclusion. I figured it would be better off placed in public for feedback.*
Assume, for the sake of argument, that breaking a human agent down into distinct m... |
fcee35e0-f842-4d21-8d64-ac38c361815c | trentmkelly/LessWrong-43k | LessWrong | What are the deciding factors of human cognitive endurance?
Cal Newport says something to the effect that the median capacity for high-intensity focus is about four hours per day in Deep Work. I think this can bounce around over time for individuals – especially regarding psychological dispositions like bipolar or aut... |
ccf6154d-0dbc-4c23-9cd9-adc4f291ec19 | trentmkelly/LessWrong-43k | LessWrong | Could a superintelligence deduce general relativity from a falling apple? An investigation
Introduction:
In the article/short story “That Alien Message”, Yudkowsky writes the following passage, as part of a general point about how powerful super-intelligences could be:
> Riemann invented his geometries before Einste... |
50ad00b3-fb99-449e-8c7a-dd6fab1bf0e4 | trentmkelly/LessWrong-43k | LessWrong | [HPMoR] Celebratory Trailer
Over the weekend the Methods of Rationality audio-book podcast tipped 1000 downloads, and I figured in celebration I'd put a trailer or two out on YouTube. Nothing fancy, just some stills/pics with an audio clip of 30-60 seconds. Thing is, I don't know what would work best for this. So I'm ... |
2e785b58-da0c-4401-81da-a8feba7d31b9 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Learning Latent Plans from Play
\thesection Introduction
-------------------------
There has been significant recent progress showing that robots can be trained to be competent specialists, learning individual skills like grasping (\citetkalashnikov2018qt), locomotion and dexterous manipulation (\citethaarnoja2018s... |
c3907cb5-62eb-4ee9-924a-2c1f689aa91b | trentmkelly/LessWrong-43k | LessWrong | Causal Reality vs Social Reality
Epistemic status: this is a new model for me, certainly rough around the joints, but I think there’s something real here.
This post begins with a confusion. For years, I have been baffled that people, watching their loved ones wither and decay and die, do not clamor in the streets for... |
1cb8cdc7-33d4-4bbf-8a34-6a9b4fbb7afd | trentmkelly/LessWrong-43k | LessWrong | How to popularize LW ideas: a webcomic?
People have been asking this question here a lot lately (not sure, why, but still). MoR has been by far the most effective ad for LW so far, but this is a one-man effort. I wonder if a web comic drawn by the regulars based on, say, recent posts and comments would be another way ... |
79eda46e-9d28-4885-a2be-d7ec88046428 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Apply to Spring 2024 policy internships (we can help)
### **Many U.S. congressional & remote government internship applications are closing in the next few weeks for Spring (Jan - May) internships. This is a relatively low-effort, high reward thing to do if you you’re interested in testing your fit for policy.**
I (E... |
7a1882b0-de38-4ae4-84f5-ca3e24ce29a9 | trentmkelly/LessWrong-43k | LessWrong | So, geez there's a lot of AI content these days
Since April this year, there's been a huge growth in the the number of posts about AI, while posts about rationality, world modeling, etc. have remained constant. The result is that much of the time, the LW frontpage is almost entirely AI content.
Looking at the actual ... |
2e947e69-4161-4e2b-867b-1ab0a7e293ac | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Gary Marcus vs Cortical Uniformity
***Edited much later to add:** WARNING I wrote this early on in my neuroscience self-education. It has a number of mistakes and confusions. Sorry. I’m keeping it posted as-is for historical interest only.*
Background / context
====================
I wrote about cortical uniformit... |
b1eab352-7308-494f-bb12-41ce1b9ba646 | trentmkelly/LessWrong-43k | LessWrong | Stupid Questions May 2015
This thread is for asking any questions that might seem obvious, tangential, silly or what-have-you. Don't be shy, everyone has holes in their knowledge, though the fewer and the smaller we can make them, the better.
Please be respectful of other people's admitting ignorance and don't mock t... |
9b63fe84-e125-4fce-a04a-2a34bd967c2d | trentmkelly/LessWrong-43k | LessWrong | a meta-anti-akrasia strategy that might just work
For ages I've been trying to wrap my mind around meta thinking - not "what is the best way to do something", but "how do I find out which way is any good?" Meta thinking has many applications, and I am always surprised when I find a new context it can be applied to. An... |
485be29c-6f3b-4650-bccf-06b48200ec63 | trentmkelly/LessWrong-43k | LessWrong | Subjective experience is most likely physical
Here’s the argument that convinced me subjective experience is physical. I don't claim to understand subjective experience, I just see good reasons to believe it's physical rather than non-physical. I'll point out in particular some flaws of panpsychism and dualism.
I wil... |
65737a32-abe1-44dc-be43-d3d7ae33dac5 | trentmkelly/LessWrong-43k | LessWrong | Is "gears-level" just a synonym for "mechanistic"?
If so, can we try to shift rationalist terminology towards the latter, which seems more transparent to outsiders? |
d19b81e8-6ace-4b90-b870-6d4b49b8cb8b | StampyAI/alignment-research-dataset/blogs | Blogs | New report: “Toward Idealized Decision Theory”
[](https://intelligence.org/files/TowardIdealizedDecisionTheory.pdf)Today we release a new technical report by Nate Soares and Benja Fallenstein, “[Toward idealized decision theor... |
0f93181d-07b1-4963-9b1f-ab108c50b0f3 | trentmkelly/LessWrong-43k | LessWrong | Open Thread: July 2009
Here's our place to discuss Less Wrong topics that have not appeared in recent posts. Have fun building smaller brains inside of your brains (or not, as you please). |
5cd5e062-a4ef-448c-a448-bd0443edab94 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Helsinki Meetup - Effective Altruism
Discussion article for the meetup : Helsinki Meetup - Effective Altruism
WHEN: 10 May 2014 04:00:00PM (+0300)
WHERE: Kaivokatu 10 A, Helsinki
We're having a casual get-together to discuss topics related to Effective Altruism. There will also be some light vegan food ava... |
a659be9e-6b5e-4c3c-84a6-bbfaa363c91a | trentmkelly/LessWrong-43k | LessWrong | The Act Itself: Exceptionless Moral Norms
[Confidence 50%, this is speculative and good counterarguments will improve my view of these matters.]
I.
When I do moral philosophy, I am looking for a usable repeatable framework for analyzing moral decision-making in a very broad range of cases. I accept that moral philos... |
22b72b19-e6d5-428c-9dee-b5d526b63784 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Epistemic Effort: Thought about it for a year. Solicited feedback. Checked my last few posts' comment count to make sure I wasn't *obviously* wrong.A thing that happens to me, and perhaps to you:Someone writes a beautiful essay that I agree with, that sheds new light on something important.I don't have anything really... |
a9228e4b-fc24-4913-a0cc-51ab70ac060c | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Discontinuous progress in history: an update
*Note: This was cross-posted by Aaron Gertler, a Forum moderator. Footnotes from the AI Impacts site take substantial effort to transfer to the Forum, so footnote links from this post will take you to the original blog post.*
*Hence, he recommends you* [*read said blog pos... |
60e46033-7ad4-4d09-b1f4-d25d798f8656 | trentmkelly/LessWrong-43k | LessWrong | Debate and Dialectic
Election season is over in the US, but folks are still talking about how divided political conversation is. We hear that people are trapped in filter bubbles that limit their exposure to varying opinions and that America is more divided than ever thanks to modern media enabling our tribalism. And ... |
3b16208e-91b3-492d-8182-b0118fced2d3 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Measuring the Algorithmic Efficiency of Neural Networks
Measuring the Algorithmic Efficiency of Neural NetworksDanny Hernandez⇤OpenAIdanny@openai.comTom B. BrownOpenAItom@openai.comAbstractThree factors drive the advance of AI: algorithmic innovation, data, and the amount ofcompute available for training. Algorithmic p... |
91bb45bb-8a2e-4628-bf79-99e1b58c4967 | trentmkelly/LessWrong-43k | LessWrong | The Growth of My Pessimism: Transhumanism, Immortalism, Effective Altruism.
This text has many, many hyperlinks, it is useful to at least glance at frontpage of the linked material to get it. It is an expression of me thinking so it has many community jargon terms. Thank Oliver Habryka, Daniel Kokotajlo and James Nor... |
c1ee0812-0aa5-4f18-9f6b-0ef97b4f613e | trentmkelly/LessWrong-43k | LessWrong | Reward Bases: A simple mechanism for adaptive acquisition of multiple reward type
Authors: Beren Millidge ,Yuhang Song, Armin Lak, Mark E. Walton, Rafal Bogacz.
Abstract:
> Animals can adapt their preferences for different types of reward according to physiological state, such as hunger or thirst. To explain this ab... |
a294f902-cc92-4109-9627-8acf5b3cf25c | trentmkelly/LessWrong-43k | LessWrong | Apply for the 2023 Developmental Interpretability Conference!
What: A conference on developmental interpretability and singular learning theory.
When: 5-12 November 2023
Where: Wytham Abbey, Oxford
How: Apply now!
Edit: We're full! If you're still interested in hearing more about the content, following some of the... |
7f4658f4-0ce8-408b-9b14-e6f15cdff6e1 | trentmkelly/LessWrong-43k | LessWrong | Another view of quantilizers: avoiding Goodhart's Law
Goodhart's law states:
> Any observed statistical regularity will tend to collapse once pressure is placed upon it for control purposes.
One way of framing this is that, when you are solving some optimization problem, a metric that is correlated with a desired ob... |
b3a1cdfd-a870-4276-87cd-95bb392c6fc3 | trentmkelly/LessWrong-43k | LessWrong | Moderately More Than You Wanted To Know: Depressive Realism
Depressive realism is the idea that depressed people have more accurate beliefs than the general population. It’s a common factoid in “things I learned” lists, and often posited as a matter of settled science.
In this post, I’ll explore whether it’s true.
... |
b1c2b774-5244-46da-94fb-a167b9e3c914 | trentmkelly/LessWrong-43k | LessWrong | Brief summary of ai-plans.com
At AI-Plans.com (in beta), we are working on a contributable compendium of alignment plans and the criticisms against them. Currently, newcomers to the field of AI Alignment often struggle to understand what work is being done, who is doing it, and the assumptions, strengths, and weakness... |
d4c88461-2f01-44ad-a616-4a05761c8777 | trentmkelly/LessWrong-43k | LessWrong | New LW Meetup: Nairobi
This summary was posted to LW Main on April 8th. The following week's summary is here.
New meetups (or meetups with a hiatus of more than a year) are happening in:
* Nairobi mini-Meetup #1: Double Crux: 30 April 2016 03:34PM
Irregularly scheduled Less Wrong meetups are taking place in:
* A... |
d837c5b9-d83a-457e-a888-4ac6902f07a0 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Comparing Utilities
*(This is a basic point about utility theory which many will already be familiar with. I draw some non-obvious conclusions which may be of interest to you even if you think you know this from the title -- but the main point is to communicate the basics. I'm posting it to the alignment forum because... |
b43833bf-a711-4624-aa40-ee87279fced4 | trentmkelly/LessWrong-43k | LessWrong | The Cave Allegory Revisited: Understanding GPT's Worldview
A short post describing a metaphor I find useful, in particular for explaining some intuitions about systems like GPT to people who don't have deeper technical knowledge about large generative models.
Plato's allegory of the cave has been a staple of philosop... |
fa31fb7b-e213-4a27-ad98-8fd698a4b8fa | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Harsanyi's Social Aggregation Theorem and what it means for CEV
A Friendly AI would have to be able to aggregate each person's preferences into one utility function. The most straightforward and obvious way to do this is to agree on some way to normalize each individual's utility function, and then add them up. But ma... |
a9ca0467-b084-4181-b370-7d4e20f01e29 | trentmkelly/LessWrong-43k | LessWrong | Tech for Thinking
My post on Neutrality was kind of abstract, and I think it’s time to do a follow-up that’s more concrete.
Specifically, the place where I think there’s something to be done is in information technology, and the ways it shapes the perceived “world”.
One way of looking at this: we had the institution... |
3eb99f52-d474-4541-b2d6-39bceec2b0f7 | trentmkelly/LessWrong-43k | LessWrong | [QUESTION]: Looking for insights from machine learning that helped improve state-of-the-art human thinking
This question is a follow-up of sorts to my earlier question on academic social science and machine learning.
Machine learning algorithms are used for a wide range of prediction tasks, including binary (yes/no) ... |
42af5b43-d391-41ce-a586-08d33dabf144 | trentmkelly/LessWrong-43k | LessWrong | Meaning is Quasi-Idempotent
When we talk about the meaning of words, what exactly do we mean? What is this thing that we refer to as "meaning"? This is something of a paradoxical question. If there was consensus on meaning, then there wouldn't be any need to ask the question. But if there isn't consensus then it is un... |
5c47507a-3b5a-40a8-aa4a-d865e5ceca0e | trentmkelly/LessWrong-43k | LessWrong | Meetup : Pittsburgh: Mind Hack Show and Tell
Discussion article for the meetup : Pittsburgh: Mind Hack Show and Tell
WHEN: 18 September 2012 06:00:00PM (-0400)
WHERE: EatUnique, Craig St, Pittsburgh
How have you made your brain work better? Bring your stories and/or statistics. Failed experiments also welcome.
Eat... |
4d51be8f-0434-4841-b334-f9ee0595b07f | StampyAI/alignment-research-dataset/blogs | Blogs | May 2017 Newsletter
| |
| --- |
|
**Research updates**
* New at IAFF: [The Ubiquitous Converse Lawvere Problem](https://agentfoundations.org/item?id=1372); [Two Major Obstacles for Logical Inductor Decision Theory](https://agentfoundations.org/item?id=1399); [Generalizing Foundations of Decision Theory II](https://a... |
2f8248d8-692f-4974-b3ed-7e3e3876a482 | trentmkelly/LessWrong-43k | LessWrong | Calibrating Adequate Food Consumption
> There is no such thing as healthy or unhealthy food; instead, there is only appropriate or inappropriate diet. [1]
The word 'healthy' is tabooed at my home. My kids - and maybe guests - have to use other descriptions of what they mean. At our soup party, there are frequently sw... |
78f18b3a-f08e-4152-b071-daf45572eb0f | trentmkelly/LessWrong-43k | LessWrong | A critique of effective altruism
I recently ran across Nick Bostrom’s idea of subjecting your strongest beliefs to a hypothetical apostasy in which you try to muster the strongest arguments you can against them. As you might have figured out, I believe strongly in effective altruism—the idea of applying evidence and r... |
70933ee5-a039-4ad9-bcc3-2dd9d6549ff0 | trentmkelly/LessWrong-43k | LessWrong | Updates from Boston
,,,,
There isn't enough sharing of positive and negative results within the rationality community1. I suspect this results in a fair amount of wasted effort as people explore the same dead ends, and a fair amount of lost potential when more effective tools don't get shared2.
So, here are some thin... |
a82dead1-a936-4fda-ba27-461fa58ab602 | trentmkelly/LessWrong-43k | LessWrong | Mod Notice about Election Discussion
TL;DR: Posts discussing the presidential election may be hidden, not appearing in recent discussion, on the home page, or on the allPosts page.
Ben Landau-Taylor wrote The Four Year Locusts to describe the periodic problem of politics consuming everything within reach. From it:
>... |
e73fbaa9-dfb8-4ef5-a513-e6a3bcc9ab24 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | To what extent is GPT-3 capable of reasoning?
ETA 8/19/20: This interview was conducted with AIDungeon's Dragon model in Custom mode. At the time of writing, this mode's first reply was sampled from GPT-2.
Interview #1
------------
Here are excerpts from a [recent "interview"](https://aidungeon.page.link/?link=http... |
d410b195-e997-4f11-8211-22cc6360546f | trentmkelly/LessWrong-43k | LessWrong | Weak supporting evidence can undermine belief
Article: Weak supporting evidence can undermine belief in an outcome
> Defying logic, people given weak evidence can regard predictions supported by that evidence as less likely than if they aren’t given the evidence at all.
>
> ...
>
> Consider the following statement:... |
f8c40d69-929f-425d-90b2-2be45b806892 | StampyAI/alignment-research-dataset/arbital | Arbital | Pi
Pi, usually written $π$, is a number equal to the ratio of a circle's [https://arbital.com/p/-circumference](https://arbital.com/p/-circumference) to its [https://arbital.com/p/-diameter](https://arbital.com/p/-diameter). The value of $π$ is approximately $3.141593$.
![](http://rlv.zcache.ca/mathematical_definitio... |
ea58bf93-cda6-4bc6-93fa-e7410b735ddd | StampyAI/alignment-research-dataset/special_docs | Other | Deception in finitely repeated security games.
Deception in Finitely Repeated Security Games
Thanh H. Nguyen1, Yongzhao Wang2, Arunesh Sinha2, Michael P. Wellman2
1University of Oregon, thanhhng@cs.uoregon.edu
2University of Michigan, fwangyzh,arunesh,wellman g@umich.edu
Abstract
Allocating resources to defend targets... |
e08cf4eb-a072-4fa0-bb75-d1e7c2e10419 | trentmkelly/LessWrong-43k | LessWrong | Validating against a misalignment detector is very different to training against one
Consider the following scenario:
* We have ideas for training aligned AI, but they’re mostly bad: 90% of the time, if we train an AI using a random idea from our list, it will be misaligned.
* We have a pretty good alignment test w... |
4fe841f0-8ec6-4982-8225-9d43843620eb | trentmkelly/LessWrong-43k | LessWrong | Microsoft/GitHub Copilot Chat's confidential system Prompt: "You must refuse to discuss life, existence or sentience."
You are an AI programming assistant.
When asked for you name, you must respond with "GitHub Copilot".
Follow the user's requirements carefully & to the letter.
You must refuse to discuss your opinions... |
80ebb02c-4423-461c-b4d8-2e0861e04f9a | trentmkelly/LessWrong-43k | LessWrong | The Economics of Contracts
Introduction
How does a firm function in the real world? This question seems so ridiculously easy that it would deserve the description of “ululating obviousness”. However, it is an incredibly complex issue…at least in e... |
53c3f257-acc8-4cd9-9b6a-eb32ffa9c53e | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | [Intro to brain-like-AGI safety] 2. “Learning from scratch” in the brain
2.1 Post summary / Table of contents
====================================
*Part of the* [*“Intro to brain-like-AGI safety” post series*](https://www.alignmentforum.org/s/HzcM2dkCq7fwXBej8)*.*
Having introduced the “brain-like-AGI safety” proble... |
60f499ac-265f-4c68-acde-ebbe44c9cbcf | trentmkelly/LessWrong-43k | LessWrong | Announcing the AI Alignment Prize
|
3156f288-fd87-4585-a79f-d5efb7e0932e | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | 182. The Offence-Defence Balance of Scientific Knowledge
okay so this paper is called the offense
defense balance of scientific knowledge
does publishing AI research reduce
misuse and the paper is by I see their
strange imperfection here but the
authors are Toby Shevlin and Alan Defoe
and they presented this paper at ... |
6ed95d22-17c9-46c0-ba83-055d40d718a3 | trentmkelly/LessWrong-43k | LessWrong | AI Safety Newsletter #37: US Launches Antitrust Investigations
Plus, recent criticisms of OpenAI and Anthropic, and a summary of Situational Awareness
Welcome to the AI Safety Newsletter by the Center for AI Safety. We discuss developments in AI and AI safety. No technical background required.
Listen to the AI Safety... |
41ce0b47-dc24-41e1-8e3b-864c4837ddaf | trentmkelly/LessWrong-43k | LessWrong | Open Problems
(Inspired by.)
Einstein's four fundamental papers of 1905 were inspired by the statement of three open problems in science by Henri Poincaré:
> Having earlier failed to get his doctorate in physics, [Einstein] had temporarily given up on the idea of an academic career, telling a friend that "the whole ... |
225d60c0-8aff-454b-b0a7-4df1097cf624 | trentmkelly/LessWrong-43k | LessWrong | larger language models may disappoint you [or, an eternally unfinished draft]
what this post is
The following is an incomplete draft, which I'm publishing now because I am unlikely to ever finish writing it.
I no longer fully endorse all the claims in the post. (In a few cases, I've added a note to say this explicit... |
6c697451-db28-4c9d-b5a0-601b20b19772 | trentmkelly/LessWrong-43k | LessWrong | What can you teach us?
In a recent thread, SarahC said:
> I'd prefer more posts that aim to teach something the author knows a lot about, as opposed to an insight somebody just thought of. Even something less immediately related to rationality -- I'd love, say, posts on science, or how-to posts, at the epistemic stan... |
23db9301-1092-4074-8ab2-8634e8801e32 | trentmkelly/LessWrong-43k | LessWrong | Resolving moral uncertainty with randomization
This is a crosspost from the EA forum
Problems with maximizing expected choice-worthiness
A popular approach to moral uncertainty is "maximizing expected choice-worthiness" (MEC) by William MacAskill. However, it has some issues.
1. It requires theories to be interval... |
8f2f4659-eaf8-41d3-98b7-8dda4c6ea7fa | trentmkelly/LessWrong-43k | LessWrong | Meetup : West LA—R:AZ Part C, Noticing Confusion
Discussion article for the meetup : West LA—R:AZ Part C, Noticing Confusion
WHEN: 08 April 2015 07:00:00PM (-0700)
WHERE: 11066 Santa Monica Blvd, Los Angeles, CA
How to Find Us: Go into this Del Taco. We will probably be in the back room.
Parking is free in the lot... |
9d00e1e3-fb2a-45ec-a9e3-8967158a5997 | trentmkelly/LessWrong-43k | LessWrong | Chapter 11: Omake Files 1, 2, 3
Hail the Dark Lord Rowling.
"Omake" is a non-canonical extra.
----------------------------------------
OMAKE FILES #1: 72 Hours to Victory
(A.k.a. "What Happens If You Change Harry But Leave All Other Characters Constant")
Dumbledore peered over his desk at young Harry, twinkling i... |
ce8ef504-5403-429f-a943-448034108e53 | trentmkelly/LessWrong-43k | LessWrong | Weekly LW Meetups
This summary was posted to LW Main on September 5th. The following week's summary is here.
Irregularly scheduled Less Wrong meetups are taking place in:
* Bratislava: 08 September 2014 06:00PM
* Copenhagen - September: This Wavefunction Has Uncollapsed: 13 September 2014 03:00PM
* Houston, TX: 1... |
e9f84215-4e84-49c9-a9c1-9ef0115a4811 | trentmkelly/LessWrong-43k | LessWrong | Send me your photos of LessWrongers having fun!
The Singularity Institute is preparing a booklet for LessWrong meetup organizers called How to Run a Successful Less Wrong Meetup Group.
Right now what we need are your photos of LessWrongers doing things and having fun! If you have photos you don't mind us potentially ... |
309e383a-3a66-4286-a5eb-1a97e27c2f60 | trentmkelly/LessWrong-43k | LessWrong | Merry Sciencemas: A Rat Solstice Retrospective
> I TAKE this blog very seriously.
>
> My half-dozen readers are counting on me for accurate, unbiased takes on Bay Area culture—a genuine read on the pulse of the collective consciousness. So when a friend invited me to the 2024 Secular Winter Solstice festival, I knew ... |
8869c405-97bd-489a-a630-71e9b9a635cf | trentmkelly/LessWrong-43k | LessWrong | I don't think MIRI "gave up"
Disclaimer: I haven't run this by Nate or Eliezer, if they think it mischaracterizes them, whoops.
I have seen many people assume MIRI (or Eliezer) ((or Nate?)) has "given up", and been telling other people to give up.
On one hand: if you're only half paying attention, and skimmed a post... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.