id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
36638b90-f8dc-4202-b695-f8b977dabc96 | trentmkelly/LessWrong-43k | LessWrong | Autonomy as taking responsibility for reference maintenance
I think semantics – specifically, maintaining reference relationships – is a core component of intelligent behaviour. Consequently, I think a better understanding of semantics would enable a better understanding of what machine intelligence that is “trying to... |
7c8663da-c38a-44ce-ab9c-79675aa99a79 | trentmkelly/LessWrong-43k | LessWrong | Can We Align AI by Having It Learn Human Preferences? I’m Scared (summary of last third of Human Compatible)
Epistemic status: I am just learning about alignment and just read Human Compatible. Below is a summary of the paradigm he outlines for aligning AI in the last third of his book, and the questions I have of th... |
cee68554-386a-4fad-925d-6c65ab0e8905 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Fixing Insider Threats in the AI Supply Chain
Summary
=======
Insider threats are security risks caused by an organisation's staff. **Careless and intentional insider threats cause 25+% of cyber breaches**.[[1]](#fn2om770gv8d2)
In a [survey of existential risks involving cybersecurity and AI](https://forum.effective... |
1210f3cd-7cca-4d5b-bead-9a25fcc08ffd | StampyAI/alignment-research-dataset/agisf | AGI Safety Fund | [Week 2] “Learning from human preferences” (Blog Post) by Dario Amodei, Paul Christiano & Alex Ray
We present a learning algorithm that uses small amounts of human feedback to solve modern RL environments. Machine learning systems with human feedback [have](https://papers.nips.cc/paper/4805-a-bayesian-approach-for-pol... |
6eab3b6f-0c42-42c1-971f-cfd3e3aac23e | trentmkelly/LessWrong-43k | LessWrong | Truthfulness, standards and credibility
-1: Meta Prelude
While truthfulness is a topic I’ve been thinking about for some time, I’ve not discussed much of what follows with others. Therefore, at the very least I expect to be missing important considerations on some issues (where I’m not simply wrong).
I’m hoping this ... |
ced09c1d-11bf-4b78-9bc4-c9f3972fc633 | trentmkelly/LessWrong-43k | LessWrong | The Efficient Market Hypothesis in Research
A classic economics joke goes like this:
> Two economists are walking down a road, when one of them notices a $20 bill on the ground. He turns to his friend and exclaims: "Look, a $20 bill!" The other replies: "Nah, if there's a $20 on the bill on the ground, someone would'... |
910b88fa-8d28-4dac-aee4-80d30ad2bf11 | trentmkelly/LessWrong-43k | LessWrong | Peer review me
I wrote an article that I hoped to post on the main page, but then I got stage fright and was afraid to even put it here. So I guess I'm just going to show it to whichever of you is willing to review it privately.
Any takers? Qualifications: must be a fan of Z-movies. |
c6fbfac7-d8eb-45a8-b0d0-5fa149cad155 | trentmkelly/LessWrong-43k | LessWrong | A framework for thinking about wireheading
[Epistemic status: Writing down in words something that isn't very complicated, but is still good to have written down.]
A great deal of ink has been spilled over the possibility of a sufficiently intelligent AI noticing that whatever it has been positively reinforced for se... |
99ac66fc-721a-4ab7-80f6-c4bbb3cc60f4 | StampyAI/alignment-research-dataset/arbital | Arbital | Safe but useless
"This type of safety implies uselessness" (or conversely, "any AI powerful enough to be useful will still be unsafe") is an accusation leveled against a proposed AI safety measure that must, to make the AI safe, be enforced to the point that it will make the AI useless.
For a non-AI metaphor, conside... |
a177eaea-4d1b-4f25-a1d1-ae1dcc07c695 | StampyAI/alignment-research-dataset/arxiv | Arxiv | More Data Can Hurt for Linear Regression: Sample-wise Double Descent
1 Introduction
---------------
Common statistical intuition suggests that more data should never harm the performance of an estimator.
It was recently highlighted in [[17](#bib.bib1 "Deep double descent: where bigger models and more data hurt")] t... |
eae5c766-fe0c-47b6-9c67-d0da1f6d3679 | trentmkelly/LessWrong-43k | LessWrong | 'Empiricism!' as Anti-Epistemology
(Crossposted by habryka after asking Eliezer whether I could post it under his account)
i.
"Ignore all these elaborate, abstract, theoretical predictions," the Spokesperson for Ponzi Pyramid Incorporated said in a firm, reassuring tone. "Empirically, everyone who's invested in Ber... |
f141d662-723f-452f-8fe3-a56e4a4d2f7e | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Why not constrain wetlabs instead of AI?
Most of the object-level stories about how misaligned AI goes wrong involve either nanotechnology or bio-risk or both. Certainly I can (and have, and will again) tell a story about AI x-risk that doesn't involve anything at the molecular level. A sufficient amount of (macroscal... |
7d523894-3300-41a6-8bf8-389359824060 | trentmkelly/LessWrong-43k | LessWrong | [Link]: KIC 8462852, aka WTF star, "the most mysterious star in our galaxy", ETI candidate, etc.
KIC 8462852, or the WTF (Where's the Flux?) star, is an F-type main sequence star about 1,480 ly away. It's a little larger and more massive than the sun, and a few times brighter. Age is uncertain, but probably older ra... |
376ba8ec-8e54-46af-ada2-5630351264e1 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Iterative Learning with Open-set Noisy Labels
1 Introduction
---------------
The success of Convolutional Neural Networks (CNNs) [[20](#bib.bib20)] is highly tied to the availability of large-scale annotated datasets, *e.g*., ImageNet [[10](#bib.bib10)]. However, large-scale datasets with high-quality label annotat... |
1bbcfaa5-bee9-4b73-b562-e2d0fd260771 | trentmkelly/LessWrong-43k | LessWrong | New study on choice blindness in moral positions
Change blindness is the phenomenon whereby people fail to notice changes in scenery and whatnot if they're not directed to pay attention to it. There are countless videos online demonstrating this effect (one of my favorites here, by Richard Wiseman).
One of the most a... |
cf170c25-79e5-4e03-8428-b3d29de67f56 | trentmkelly/LessWrong-43k | LessWrong | The Power to Teach Concepts Better
This is Part VIII of the Specificity Sequence
When you teach someone a concept, you’re building a structure in their mind by connecting up some of their mental concepts in a certain way. But you have to go in through their ears. It’s kind of like building this ship-in-a-bottle LEGO ... |
e09943e6-4a29-40cc-a7f2-0a4f2138ba88 | trentmkelly/LessWrong-43k | LessWrong | Bi-Weekly Rational Feed
===Highly Recommended Articles:
Bring Up Genius by Viliam (lesswrong) - An "80/20" translation. Positive motivation. Extreme resistance from the Hungarian government and press. Polgar's five principles. Biting criticism of the school system. Learning in early childhood. Is Genius a gift or cur... |
62213d70-51b1-4a0e-917a-826bfc8740bf | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Paper+Summary: OMNIGROK: GROKKING BEYOND ALGORITHMIC DATA
There is a new paper by Liu et al. that claims to have understood the key mechanism underlying grokking (potentially even generalization more broadly).
**They argue:**
1. Grokking can be explained via the norm of the weights. They claim that there is a c... |
1fa3edec-a7da-4f93-ab9d-a58b84ccfd30 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Some work on connecting UDT and Reinforcement Learning
|
07ca7343-41cf-4bc6-a740-9ae5a3fc2b87 | trentmkelly/LessWrong-43k | LessWrong | The Personal Implications of AGI Realism
Superintelligence Is On The Horizon
It’s widely accepted that powerful general AI, and soon after, superintelligence, may eventually be created.[1] There’s no fundamental law keeping humanity at the top of the intelligence hierarchy. While there are physical limits to intel... |
45fc6dd0-bb01-4a39-830b-914f19458c72 | StampyAI/alignment-research-dataset/blogs | Blogs | A canonical and efficient byte-encoding for ints
A canonical and efficient byte-encoding for ints
------------------------------------------------
the internet has a bunch of efficient byte-encodings for fixed-length integers, from [LEB128](https://en.wikipedia.org/wiki/LEB128) to arguably [UTF-8](https://en.wikiped... |
e02c8904-2815-4bde-b078-59addc7b70ef | trentmkelly/LessWrong-43k | LessWrong | Meetup : Sydney Rationality Dojo - March
Discussion article for the meetup : Sydney Rationality Dojo - March
WHEN: 06 March 2016 04:00:00PM (+1100)
WHERE: 10 Shepherd Street, Chippendale
After a great session working on our values in February, we'll be following up to ensure we're working on goals that fulfill them... |
d61abd5d-33ba-49ea-8ab7-44cff67d09fa | trentmkelly/LessWrong-43k | LessWrong | Misleading the witness
Related: Trust in Math
I was reading John Allen Paulos' A Mathematician Plays the Stock Market, in which Paulos relates a version of the well-known "missing dollar" riddle. I had heard it once before, but only vaguely remembered it. If you don't remember it, here it is:
> Three people stay in ... |
d00f2f3d-f525-41e0-8d23-93284034a063 | trentmkelly/LessWrong-43k | LessWrong | Open thread, March 13 - March 19, 2017
Notes for future OT posters:
1. Please add the 'open_thread' tag.
2. Check if there is an active Open Thread before posting a new one. (Immediately before; refresh the list-of-threads page before posting.)
3. Open Threads should start on Monday, and end on Sunday.
4. Unflag ... |
906c1ba6-a780-4939-b05c-b5f2ba4066d8 | trentmkelly/LessWrong-43k | LessWrong | Cryonics-adjacent question
(This question involves my somewhat bizarre "mind backup" project, that was inspired by Rudy Rucker's "Lifebox" idea.)
Unfortunately, I made some HUGE blunders last year involving my life savings and the market (bonds, though I almost wish it was crypto). It's painful to admit this involved... |
d81654e8-6114-4935-80bd-0de06a3893fd | trentmkelly/LessWrong-43k | LessWrong | Weekly LW Meetups: Austin, Madison, NYC
This summary was posted to LW Main on July 27th, and has been moved to discussion.
There are upcoming irregularly scheduled Less Wrong meetups in:
* Dublin, Ireland Meetup: 05 August 2012 03:00PM
* Washington DC Biased Boardgames meetup: 05 August 2012 03:00PM
* Brussels me... |
96581ec0-ac84-4232-830e-11a391c24531 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Combining experts’ causal judgments.
1 Introduction
---------------
Consider a policymaker who is trying to decide which intervention,
that is, which actions,
should be implemented in order to bring about a desired outcome,
such as preventing violent behavior in prisons or reducing famine mortality in
some country.... |
b3895a58-fc86-4ffe-ae57-8b4de5d6b939 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "A fiction-writing trick I find particularly compelling are open loops.A cliffhanger is an example: you want to know how the hero survives, so your thoughts keep looping back to the situation, trying to figure out what happens next. But you need the author to tell you.Really good writing uses open loops at the sentence... |
f35032b0-bad0-4cd7-8b0f-713c0671d38e | StampyAI/alignment-research-dataset/lesswrong | LessWrong | A simple presentation of AI risk arguments
[Here is a draft of an accordion-style AGI risk FAQ.](https://workflowy.com/s/faq-why-would-ai-be/2kHollRW8uqinUsV)
I'm interested in three types of feedback:
1. The best place to host a similar format
2. Feedback on content
3. Thoughts about this general approach
The goal... |
d2d81123-ccda-4ede-918c-4a4516c28aa0 | trentmkelly/LessWrong-43k | LessWrong | New LW Meetup: Kyiv, New Hampshire
This summary was posted to LW Main on July 10th. The following week's summary is here.
New meetups (or meetups with a hiatus of more than a year) are happening in:
* New Hampshire Inaugural Meet-up: 14 July 2015 07:00PM
* Kyiv, Ukraine: 24 July 2015 06:30PM
Irregularly scheduled... |
3d610d26-1320-449d-b41e-b0b9468519c6 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Followup to: Evolutions Are Stupid (But Work Anyway), Evolutionary Psychology
Biological organisms in general, and human brains particularly, contain complex adaptations; adaptations which involve many genes working in concert. Complex adaptations must evolve incrementally, gene by gene. If gene B depends on gene A to... |
4b26a8c2-c173-4a48-8fac-c0899954f493 | trentmkelly/LessWrong-43k | LessWrong | [linkpost] Better Without AI
David Chapman (of Meaningness and In the Cells of the Eggplant fame) has written a new web-book about AI. Some excerpts from the introduction, Only you can stop an AI apocalypse:
> Artificial intelligence might end the world. More likely, it will crush our ability to make sense of the wor... |
667cf473-8f84-449f-a078-d8667a2bda89 | trentmkelly/LessWrong-43k | LessWrong | Define Rationality
I would like to suggest that we try to come up with several defintions of rationality. I don't feel we have exhausted this search area by any means. Robin has suggested, "More "rational" means better believing what is true, given one's limited info and analysis resources". Other commenters have emph... |
957a2444-b300-4a66-aff9-3ab92907c7d1 | trentmkelly/LessWrong-43k | LessWrong | Propagandizing Meta-Ethics in an Essay Contest
So someone I follow on Facebook linked to this essay contest on the subject of: How Should Humanity Steer the Future? My urge to make a joke of it immediately kicked in. The impulse to joke turned into an impulse to actually submit an essay when the words "steering the ... |
c6f5bab0-2889-4641-abe9-b874c6d29abe | trentmkelly/LessWrong-43k | LessWrong | Progress links and short notes, 2025-03-10
Much of this content originated on social media. To follow news and announcements in a more timely fashion, follow me on Twitter, Notes, Farcaster, Bluesky, or Threads.
Contents
* d/acc Day
* My writing (ICYMI)
* Praise for Progress Conference 2024
* Job opportunities
... |
3613741f-cbd7-4137-9ca6-f2ef24894f16 | trentmkelly/LessWrong-43k | LessWrong | Rationalist Magic: Initiation into the Cult of Rationatron
I am curious on the perspective of a rationalist discussion board (this seems like a good start) on the practice of magic. I introduce the novel, genius concept of "rationalist magic", i.e. magic practiced by rationalists.
Why would rationalists practice mag... |
54409c7e-4de3-48ad-a8ec-71e65dbc72a7 | trentmkelly/LessWrong-43k | LessWrong | What's the Deal with Logical Uncertainty?
I notice that reasoning about logical uncertainty does not appear more confusing to me than reasoning about empirical one. Am I missing something?
Consider the classical example from the description of the tag:
> Is the googolth digit of pi odd? The probability that it is od... |
5e68fb4b-aee4-45fd-bd6e-bd058d126a4e | trentmkelly/LessWrong-43k | LessWrong | Link: blog on effective altruism
Over the last few months I've started blogging about effective altruism more broadly, rather than focusing on AI risk. I'm still focusing on abstract considerations and methodological issues, but I hope it is of interest to others here. Going forward I intend to cross-post more often t... |
a128d095-fc79-4aa6-b04d-56ae39575085 | trentmkelly/LessWrong-43k | LessWrong | Why do aphorisms and cynicism go together?
Why are aphorisms cynical more often than books are for instance?
A good single sentence saying can’t require background evidencing or further explanation. It must be instantly recognizable as true. It also needs to be news to the listener. Most single sentences that people ... |
c0ebfe27-e6a4-477a-acb8-dfb4a01959c5 | trentmkelly/LessWrong-43k | LessWrong | The median and mode use less information than the mean does
Epistemic status: Unsure. I had this in drafts from a year ago, and am posting it for Goodhart day. (Though it's April 1, all the arguments and statements in this post are things I think are true, with no jokes). I'm interested in arguments against this thesi... |
6b108049-4450-49f6-a99a-26651965a577 | StampyAI/alignment-research-dataset/arxiv | Arxiv | What Makes for Good Views for Contrastive Learning?
1 Introduction
---------------
It is commonsense that how you look at an object does not change its identity. Nonetheless, Jorge Luis Borges imagined the alternative. In his short story on *Funes the Memorious*, the titular character becomes bothered that a “dog a... |
b8a55d48-fb53-4362-9061-7bfccf862fb1 | trentmkelly/LessWrong-43k | LessWrong | Free holiday reading?
I'm going on holiday tomorrow. What freely downloadable reading do people recommend? I'm after both more serious things related to Less Wrong or SIAI/FHI's mission, or more lightweight stuff that is the sort of thing an LW participant like me would enjoy. Thanks! |
4efddb24-3290-4580-a3ea-4c24789f31da | trentmkelly/LessWrong-43k | LessWrong | Thoughts on Toy Models of Superposition
This post explores some of the intuitions I developed whilst reading Anthropic’s Toy Models of Superposition paper. I focus on motivating the shape of the model and interpreting the visualisations used in the paper. Their accompanying article is thoughtfully written, and I'd hig... |
60a82a73-36c9-4cf3-992d-9b4113bef7e1 | trentmkelly/LessWrong-43k | LessWrong | Is there a way to view "read" LessWrong posts?
I want to be able to see the LessWrong posts that I've already read/visited, like in a list. I mainly just want to be able to re-save some ones that I really liked but deleted from my bookmarks.
I didn't vote on all the posts I read (it's kind of like a habit I had to bu... |
1f98dc2a-657d-4917-99d5-2eec8c3ea654 | StampyAI/alignment-research-dataset/blogs | Blogs | MIRI’s April 2014 Newsletter
| | |
| --- | --- |
|
| |
| --- |
|
[Machine Intelligence Research Institute](http://intelligence.org)
|
|
|
| | |
| --- | --- |
|
| |
| --- |
|
**Research Updates**
* New technical report: “**[Botworld 1.0](http://intelligence.org/2014/04/10/new-report-botworld/)**.”
* 9 ... |
ba5f80ea-2994-4dd9-abfe-3dbb5cb9ad84 | trentmkelly/LessWrong-43k | LessWrong | Vaccination with the EMH
Part 1. Is "1,000 True Fans" reasonable?
> To be a successful creator you don’t need millions. You don’t need millions of dollars or millions of customers, millions of clients or millions of fans. To make a living as a craftsperson, photographer, musician, designer, author, animator, app make... |
1a2facb4-5737-4818-a4a5-87cbca260f55 | trentmkelly/LessWrong-43k | LessWrong | The way AGI wins could look very stupid
> Computers don't have any sense of aesthetics or patterns that are standard the way people learn how to play chess. They play what they think is the objectively best move in any position, even if it looks absurd, and they can play any move no matter how ugly it is." - Murray Ca... |
525c37f8-e73b-464c-849b-6ae22bc51670 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | [ASoT] Consequentialist models as a superset of mesaoptimizers
**TL;DR**: I split out mesaoptimizers (models which do explicit search internally) from the superset of consequentialist models (which accomplish goals in the world, and may or may not use search internally). This resolves a bit of confusion I had about me... |
132b6cfe-47ba-4fae-9780-7f8c5bff8d5b | trentmkelly/LessWrong-43k | LessWrong | [META] [POLL] Comment author/Post author?
I'm noticing that comments are now shown with 'Comment author:' besides the commenter's name while posts appear to be shown with 'Post author:' beside the author's name (on the actual page of the post, not the 'New' page). This is mildly aesthetically displeasing to me. I'm cu... |
d885ad99-c312-4196-a9bf-48f6bbc6b904 | trentmkelly/LessWrong-43k | LessWrong | Language Models and World Models, a Philosophy
This is my submission for Blue Dot Impact's AI Alignment Fundamentals Course. In this post I explore computational policy, collaborative development of policy with AI, and how linking Language Models with World Models can lead to more precise training data, novel insights... |
0f4a5aa7-3568-4c5c-9d90-46cee05a4f31 | trentmkelly/LessWrong-43k | LessWrong | D&D.Sci Hypersphere Analysis Part 4: Fine-tuning and Wrapup
As before, this is extreme spoilers for this D&D.Sci scenario, if you want to solve on your own try that first!
Last time we got a solution that I'm pretty sure will work. Everything from here on is just showing off a bit, and seeing if we can find any stu... |
48d53392-62b5-4703-8c0c-c5f26e500a62 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Hindsight Bias
Title: [SEQ RERUN] Hindsight Bias
Tags: sequence_reruns
Today's post, Hindsight Bias was originally published on 16 August 2007. A summary (taken from the LW wiki):
> Hindsight bias makes us overestimate how well our model could have predicted a known outcome. We underestimate the cost of... |
ffba2575-bd03-49c3-9fce-b7e0a3e41d0b | StampyAI/alignment-research-dataset/arxiv | Arxiv | Can rationality be measured?
Can rationality be measured ?
Tshilidzi Marwala
University of Johannesburg
South Africa
Email: tmarwala@gmail.com
Abstract
This paper studies whether rationality can be computed . Rationality is defined as the use of
complete information , which is processed with a perfect b... |
14162153-0bac-4559-bfb5-8b5c6e4b0bb9 | trentmkelly/LessWrong-43k | LessWrong | What's the actual evidence that AI marketing tools are changing preferences in a way that makes them easier to predict?
I've encountered this claim multiple times over the years (most recently on this AXRP episode), but I can't trace its origins (it doesn't seem to be on Wikipedia). Quoting Evan from the episode:
> A... |
9289194e-704a-4ea2-a9b7-0dba92f3b2e7 | trentmkelly/LessWrong-43k | LessWrong | 'Dumb' AI observes and manipulates controllers
The argument that AIs provided with a reward channel will observe their controllers and learn to manipulate them is a valid one. Unfortunately, it's often framed in a way that feels counterintuitive or extreme, especially to AI designers. It typically starts with the stan... |
977cff57-d92e-4e5e-a7e5-48cc6a7b02e9 | trentmkelly/LessWrong-43k | LessWrong | Compute Thresholds: proposed rules to mitigate risk of a “lab leak” accident during AI training runs
1. There should be two thresholds on compute graph size:
1. the Frontier threshold, beyond which oversight during execution is mandatory
2. the Horizon threshold, beyond which execution is forbidden by default... |
2c559233-924f-423b-8997-1076014c6d42 | trentmkelly/LessWrong-43k | LessWrong | Freedom Is All We Need
Introduction
The rapid advancements in artificial intelligence (AI) have led to growing concerns about the threat that an artificial superintelligence (ASI) would pose to humanity.
This post explores the idea that the best way to ensure human safety is to have a single objective function for a... |
019e8119-9007-40cc-af81-c82367cdf526 | trentmkelly/LessWrong-43k | LessWrong | Can we hold intellectuals to similar public standards as athletes?
Professional athletes are arguably the most publicly understood meritocracy around. There are public records of thousands of different attributes for each player. When athletes stop performing well, this is discussed at length by enthusiasts, and it's ... |
f4b44a37-7851-44aa-b6f8-d6b0a51c09f0 | trentmkelly/LessWrong-43k | LessWrong | [LINK] Up Vs Down is the new Left vs Right
This is a great article at Aeon magazine. The author argues that the new ideological dichotomy is going to be between people who have great faith in technology and human innovation (Up) and the people who believe that humans are much more tied to their biology and the Earth (... |
93a25502-7927-4c2a-bed2-7438582ab96a | trentmkelly/LessWrong-43k | LessWrong | Don't encourage prisoners dilemmas
Donating money to political causes is a waste of resources
A lot of money is donated towards political causes. Most of these causes though are pretty much zero sum games. The democrats and republicans both raise vast amounts of money, but only one of them will win the election. Most ... |
58d0d137-4f59-4df0-9cea-6e563129e0a9 | trentmkelly/LessWrong-43k | LessWrong | Citability of Lesswrong and the Alignment Forum
This post is short: as far as I know, there is no easy support to cite lesswrong or the alignment forum in academic papers. I think this should exist. This idea is related to the one on putting Alignment Forum/Lesswrong posts on arxiv.
Such support already exists elsew... |
f299102d-7780-4e9c-92e6-8b2e569261dc | trentmkelly/LessWrong-43k | LessWrong | Speaking off-meta
I'm sure you have been in this situation:
You want to say something, but it doesn't sound right. So you reword it in a way that
* gets the point across,
* you feel better about saying and
* is strangely worded.
So you say it.
This is very common.
But why say it so oddly?
Is it because you w... |
c6c4a063-a4fa-4846-aad0-d0bd7dc368f3 | trentmkelly/LessWrong-43k | LessWrong | [RETRACTED] It's time for EA leadership to pull the short-timelines fire alarm.
[EDIT 4/10/2022: This post was rash and ill-conceived, and did not have clearly defined goals nor meet the vaguely-defined ones. I apologize to everyone on here; you should probably update accordingly about my opinions in the future. In re... |
56d1e597-53e4-43fb-b1c6-4d2fda3000ef | trentmkelly/LessWrong-43k | LessWrong | 5-Minute Advice for EA Global
This 5-minute post is perfect advice for me, but YMMV
Week Before
1. Update your profile (pic, bio, contact). ~20 minutes
2. Schedule 20 one-on-ones - these are 10x more important than talks. Filter people by interests/stage in career/etc and cp-paste "Hey, I'm bob who works on [X]. Wo... |
60d496c1-532d-4fb1-bb7d-6c4b98f6e396 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Brussels November meetup: Hell and existential risks
Discussion article for the meetup : Brussels November meetup: Hell and existential risks
WHEN: 08 November 2014 01:00:00PM (+0100)
WHERE: Rue des Alexiens 55 1000 Bruxelles
Hi all,
As on every second Saturday of the month, it's meetup time. It's approxi... |
4280468a-7d87-47c4-aafe-1f6bff37f421 | trentmkelly/LessWrong-43k | LessWrong | Question: MIRI Corrigbility Agenda
MIRI's reading list on corrigbility seems out dated, and I can't find a centralised list Does anyone have, or know of, one?
As a side note, has MIRI stopped updating their reading list? It seems like that's the case.
EDIT:
Links given in the comment section to do with corrigibil... |
57277c5a-bd21-4307-8b8b-f0c85acf577e | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | What does (and doesn't) AI mean for effective altruism?
*In this 2017 talk, The Future of Humanity Institute's* [*Owen Cotton-Barratt*](https://www.fhi.ox.ac.uk/team/owen-cotton-barratt/) *discusses what strategy effective altruists ought to adopt with regards to the development of advanced artificial intelligence. He... |
e093118d-7765-41f2-b04c-57f03c15c051 | trentmkelly/LessWrong-43k | LessWrong | Clarifying The Malignity of the Universal Prior: The Lexical Update
[UPDATE: looks like the lexical update is real after all; see Paul's comment and my reply]
In Paul's classic post What does the universal prior actually look like? he lays out an argument that the universal prior, if it were to be used for important ... |
0b7f1041-42cf-4a8b-a333-ce8df6c0b8ad | trentmkelly/LessWrong-43k | LessWrong | How accurate is the quantum physics sequence?
Prompted by Mitchell Porter, I asked on Physics StackExchange about the accuracy of the physics in the Quantum Physics sequence:
What errors would one learn from Eliezer Yudkowsky's introduction to quantum physics?
Eliezer Yudkowsky wrote an introduction to quantum physi... |
39f060f2-f354-4639-ba2d-cb72e0f011be | trentmkelly/LessWrong-43k | LessWrong | Sentience matters
Short version: Sentient lives matter; AIs can be people and people shouldn't be owned (and also the goal of alignment is not to browbeat AIs into doing stuff we like that they'd rather not do; it's to build them de-novo to care about valuable stuff).
Context: Writing up obvious points that I find my... |
ea5528e7-b7df-4d63-8ef0-bfd650346bb9 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Localizing Model Behavior With Path Patching
1 Introduction
---------------
Deep neural networks can perform many complex tasks, but our ability to reason about their behavior is limited (Räuker et al., [2023](#bib.bib21 "Toward transparent ai: a survey on interpreting the inner structures of deep neural networks")... |
8b930495-1e32-48d3-bc56-184e0da89932 | trentmkelly/LessWrong-43k | LessWrong | AGI 2010 videos - link
http://vimeo.com/channels/agi10 |
b9dd35b2-358d-43f2-9cb3-e247d99e4bef | trentmkelly/LessWrong-43k | LessWrong | Kialo -- an online discussion platform that attempts to support reasonable debates
|
b63fc6d2-a6d6-4c1e-ad3c-848c547577d1 | trentmkelly/LessWrong-43k | LessWrong | Solomonoff induction without perfect memory
In this post I construct a variant of Solomonoff induction which allows for agents with imperfect memory.
Solomonoff induction is a mathematical formalization of Occam's razor, and is supposed to be a "master equation" of epistemic rationality. In order words, forming ratio... |
a733013c-0688-473d-b462-cde1b4a8605d | StampyAI/alignment-research-dataset/blogs | Blogs | July 2018 Newsletter
#### Updates
* A new paper: “[Forecasting Using Incomplete Models](https://intelligence.org/2018/06/27/forecasting-using-incomplete-models/)“
* New research write-ups and discussions: [Prisoners’ Dilemma with Costs to Modeling](https://www.lesswrong.com/posts/XjMkPyaPYTf7LrKiT/prisoners-dilemma-... |
d1688a0f-7981-4367-b5c0-6d0d5a95bce3 | StampyAI/alignment-research-dataset/blogs | Blogs | AI hopes and fears in numbers
*By Katja Grace, 28 June 2017*
People often wonder what AI researchers think about AI risk. A [good collection of quotes](http://slatestarcodex.com/2015/05/22/ai-researchers-on-ai-risk/) can tell us that worry about AI is no longer a fringe view: many big names are concerned. But withou... |
1db13d0a-91c5-4ef5-b06c-081d91a8dbf3 | trentmkelly/LessWrong-43k | LessWrong | Sunday September 20, 12:00PM (PT) — talks by Eric Rogstad, Daniel Kokotajlo and more
This Sunday at 12pm (PT), we're running another session of "lightning talks" by curated LessWrong authors (see here for previous weeks' transcripts).
* For the first hour, we will have a series of lightning talks each lasting about ... |
22f40a7c-0f22-41bd-a590-dcb5a363ab4f | trentmkelly/LessWrong-43k | LessWrong | Lloyd's of London and less-than-catastrophic risk
I recently found that Lloyd's has a number of interesting resources on risk. One is the City Risk Index, the methodology for which comes from Cambridge's Judge Business School.
The key metric is something they call GDP@Risk. Despite the name, it is not simply an appli... |
1b53afcb-a3f9-4c61-a1ea-64de868925e0 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "I just got home from a six day meditation retreat and began writing.
The catch is that I arrived at the retreat yesterday. I knew going in that it was a high variance operation. All who had experience with such things warned us we would hate the first few days, even if things were going well. I was determined to push ... |
cbff5ad3-dcc8-495d-9d05-f4364171302d | trentmkelly/LessWrong-43k | LessWrong | [LINK] Cantor's theorem, the prisoner's dilemma, and the halting problem
I wouldn't normally link to a post from my math blog here, but it concerns a cute interpretation of Cantor's theorem that showed up when I was thinking about program equilibria at the April MIRI workshop, so I thought it might be of interest here... |
9eb798a8-0368-472e-8922-cbeaac43b94c | trentmkelly/LessWrong-43k | LessWrong | [Video] Intelligence and Stupidity: The Orthogonality Thesis
> Can highly intelligent agents have stupid goals?
> A look at The Orthogonality Thesis and the nature of stupidity.
A good popular introduction to the Orthogonality Thesis from Robert Miles. |
545c1ab9-10c5-4a41-b455-21316162db89 | trentmkelly/LessWrong-43k | LessWrong | How Multiverse Theory dissolves Quantum inexplicability
This is a link post for https://viderationale.blog/2024/05/04/quantum-path-to-the-multiverse/
Much of the arguments here comes from David Deutsch's two books The Beginning of Infinity and The Fabric of Reality. I try to explain parts of it in more detail and h... |
9b68695a-0dbc-4eda-a2ff-92ad8ce6ce11 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | A rant against robots
What comes to your mind when you hear the word "*artificial intelligence"* (or "*artificial general intelligence"*)? And if you want to prepare the future, what should come to your mind?
It seems that when most people hear AI, they think of *robots*. Weirdly, this observation includes both layme... |
a637fb36-e9fa-489c-8181-5370e2b89686 | trentmkelly/LessWrong-43k | LessWrong | The utility curve of the human population
> "Whoever saves a single life, it is as if he had saved the whole world."
>
> —The Talmud, Sanhedrin 4:5
That was the epigraph Eliezer used on a perfectly nice post reminding us to shut up and multiply when valuing human lives, rather than relying on the (roughly) logarit... |
258d94f6-3d54-4c4c-8f47-213f748395ce | trentmkelly/LessWrong-43k | LessWrong | Meetup : Rationality Meetup Vienna
Discussion article for the meetup : Rationality Meetup Vienna
WHEN: 18 October 2014 03:00:00PM (+0200)
WHERE: Kaisermühlenstraße 24/2, 1220 Wien, meeting room behind the building
location: When arriving by U2 or Schnellbahn train: take the exit towards Kaisermühlenstraße, cross th... |
66778466-6bc3-4e2b-9bff-345397f0996a | trentmkelly/LessWrong-43k | LessWrong | Lessons from weather forecasting and its history for forecasting as a domain
This is the first of two (or more) posts that look at the domain of weather and climate forecasting and what we can learn from the history and current state of these fields for forecasting as a domain. It may not be of general interest to the... |
8bf331de-5394-4ff5-b237-899489966823 | trentmkelly/LessWrong-43k | LessWrong | Anthropic rewrote its RSP
Canonical linkpost: https://www.lesswrong.com/posts/Q7caj7emnwWBxLECF/anthropic-s-updated-responsible-scaling-policy.
Anthropic's new version of its RSP is here at last.
> Today we are publishing a significant update to our Responsible Scaling Policy (RSP), the risk governance framework we ... |
959e17b0-b404-4d77-9e90-b377c43a9885 | trentmkelly/LessWrong-43k | LessWrong | Single-bit reflective oracles are enough
The latest version on this forum of the reflective oracle formalism uses multibit oracles. These oracles are defined on probabilistic oracle machines with advance-only output tapes, and answer queries of the form, "Does machine M, when run on this same oracle, produce output st... |
bf25f23e-4386-4515-ba81-3596e69c8a2f | trentmkelly/LessWrong-43k | LessWrong | ChatGPT: First Impressions
ChatGPT is OpenAI’s newest language model based on the GPT-3.5 series of LLMs, optimised for dialogue. It is trained using Reinforcement Learning from Human Feedback; human AI trainers provide supervised fine-tuning by playing both sides of the conversation.
It is evidently better than GPT-... |
067cbd39-51df-4b52-aad2-2d6eb34139cd | trentmkelly/LessWrong-43k | LessWrong | How to brainstorm effectively
> Mr. Malfoy is new to the business of having ideas, and so when he has one, he becomes proud of himself for having it. He has not yet had enough ideas to unflinchingly discard those that are beautiful in some aspects and impractical in others; he has not yet acquired confidence in his ow... |
9020fa3a-6356-4697-8f38-091aace54aca | trentmkelly/LessWrong-43k | LessWrong | o3, Oh My
OpenAI presented o3 on the Friday before Christmas, at the tail end of the 12 Days of Shipmas.
I was very much expecting the announcement to be something like a price drop. What better way to say ‘Merry Christmas,’ no?
They disagreed. Instead, we got this (here’s the announcement, in which Sam Altman says ... |
fe151cd0-d082-4afa-b1b4-ebdc07f76f16 | trentmkelly/LessWrong-43k | LessWrong | More metal less ore
Epistemic status: musings on advice from three different spaces, all with a similar tactic to improve your life. This discovery is told through a semi-fictional story.
I am not the happiest person.
Rather than accepting this, I research it, I make it my job to change that fact.
My research b... |
6390751e-8cb8-400f-8e46-d24a35f64cc1 | trentmkelly/LessWrong-43k | LessWrong | Group Rationality Diary, Dec. 1-13, 2015
This is the public group rationality diary for December 1-13, 2015. 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
* D... |
3e7ad499-2417-4a75-b5ee-90de089edf47 | trentmkelly/LessWrong-43k | LessWrong | Paths To High-Level Machine Intelligence
This post is part 3 in our sequence on Modeling Transformative AI Risk. We are building a model to understand debates around existential risks from advanced AI. The model is made with Analytica software, and consists of nodes (representing key hypotheses and cruxes) and edges (... |
157bfc28-d828-4420-9c53-20f67cd83100 | trentmkelly/LessWrong-43k | LessWrong | New AI safety treaty paper out!
Last year, we (the Existential Risk Observatory) published a Time Ideas piece proposing the Conditional AI Safety Treaty, a proposal to pause AI when AI safety institutes determine that its risks, including loss of control, have become unacceptable. Today, we publish our paper on the to... |
50ecc660-93af-4631-a652-641a46cd9841 | trentmkelly/LessWrong-43k | LessWrong | Formalizing informal logic
As an exercise, I take a scrap of argumentation, expand it into a tree diagram (using FreeMind), and then formalize the argument (in Automath). This towards the goal of creating "rationality augmentation" software. In the short term, my suspicion is that such software would look like a grou... |
06b90506-4620-4be4-abf5-6d6a5abf6166 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Autoregressive Latent Video Prediction with High-Fidelity Image Generator.
1 Introduction
---------------
Figure 1: Selcted 256×256 video sample generated by HARP on RoboNet (Dasari et al., [2019](#bib.bib13 "Robonet: large-scale multi-robot learning")... |
76fd9862-80c5-4f29-9def-68501099e886 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Brussels - Calibration and other games
Discussion article for the meetup : Brussels - Calibration and other games
WHEN: 08 March 2014 01:00:00PM (+0100)
WHERE: Rue des Alexiens 55 1000 Bruxelles
This month we're stealing an idea from the Atlanta group: using Wits & Wagers for confidence calibration (and a ... |
a406a96a-00aa-49fa-9a41-aadc6d461630 | trentmkelly/LessWrong-43k | LessWrong | [LINK] How Long Does Habit Formation Take?
Related: Common failure modes in habit formation
I ran across this bit of pop-sci (a review of Jeremy Dean's Making Habits, Breaking Habits), which claims that habits typically take around 66 days to form, not the 21 days that self-help articles tend to cite. The somewhat su... |
6286ef61-0672-4503-ba48-32064f3e1771 | StampyAI/alignment-research-dataset/blogs | Blogs | March 2021 Newsletter
#### MIRI updates
* MIRI's Eliezer Yudkowsky and Evan Hubinger [comment in some detail](https://www.lesswrong.com/posts/AyfDnnAdjG7HHeD3d/miri-comments-on-cotra-s-case-for-aligning-narrowly) on Ajeya Cotra's [The Case for Aligning Narrowly Superhuman Models](https://www.lesswrong.com/posts/PZts... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.