id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
4ad1b2bb-a577-4793-89d4-ccb63a5c3deb | trentmkelly/LessWrong-43k | LessWrong | Interpersonal Entanglement
Today I shall criticize yet another Utopia. This Utopia isn't famous in the literature. But it's considerably superior to many better-known Utopias—more fun than the Christian Heaven, or Greg Egan's upload societies, for example. And so the main flaw is well worth pointing out.
This Utop... |
a1e15778-4812-47af-97d5-54952333806c | trentmkelly/LessWrong-43k | LessWrong | Leveling Up in Rationality: A Personal Journey
See also: Reflections on rationality a year out
My favorite part of Lord of the Rings was skipped in both film adaptations. It occurs when our four hobbit heroes (Sam, Frodo, Merry and Pippin) return to the Shire and learn it has been taken over by a gang of ruffians. Me... |
1a27797b-a92f-4ac9-9bac-ad0a9f5e2d94 | trentmkelly/LessWrong-43k | LessWrong | Manifold: If okay AGI, why?
Arguably the most important topic about which a prediction market has yet been run: Conditional on an okay outcome with AGI, how did that happen?
|
5e41b26b-e290-4ab1-b9fd-619639b57c35 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | There should be a public adversarial collaboration on AI x-risk
I think that [adversarial collaborations](https://en.wikipedia.org/wiki/Adversarial_collaboration) are a good way of understanding competing perspectives on an idea, especially if it is polarising or especially controversial.
The term was first [intr... |
92af10c3-576e-4ee5-afc0-2806eddf3e45 | trentmkelly/LessWrong-43k | LessWrong | Book Review: Affective Neuroscience
After years of clumsily trying to pick up neuroscience by osmosis from papers, I finally got myself a real book — Affective Neuroscience, by Jaak Panksepp, published in 1998, about the neuroscience of emotions in the (animal and human) brain.
What surprised me at first was how cont... |
15d7db97-768b-4292-976d-8c06cdb2bf65 | trentmkelly/LessWrong-43k | LessWrong | Covid 11/18: Paxlovid Remains Illegal
I had already written most of this week’s post, and also spun out a way-too-long way-too-deep dive on what happened with a retracted FLCCC paper that that I was planning to publish today but I can’t yet because the rabbit hole is still getting deeper, when Scott Alexander posted I... |
b95be419-860f-4de6-b740-32415cfe1532 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Ngo and Yudkowsky on alignment difficulty
This post is the first in a series of transcribed Discord conversations between Richard Ngo and Eliezer Yudkowsky, moderated by Nate Soares. We've also added Richard and Nate's running summaries of the conversation (and others' replies) from Google Docs.
Later conversation pa... |
7321c859-ec5b-4210-8cc7-c2121c7b3d33 | trentmkelly/LessWrong-43k | LessWrong | Agency in Politics
This is a crosspost from https://250bpm.substack.com/p/agency-in-politics
Matt Yglesias explains why history is not a steam roller with a steering wheel welded tight, unyielding and incorrigible.
> Of course, only a very naive person would see history as the unfolding of random occurrences driven ... |
491d7ff3-573d-40e5-b2a3-046b513408c9 | trentmkelly/LessWrong-43k | LessWrong | How do we learn from errors?
Mark Friedenbach's post Leaving LessWrong for a more rational life makes a few criticisms of the way LW approaches rationality. It's not focused enough on empiricism. While he grants that there's lip service payed to empiricism Mark argues that LW isn't empiric enough.
Part of empiricism ... |
d9000583-aa41-40a2-9349-d4d7680186c2 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Large Scale Adversarial Representation Learning
1 Introduction
---------------
In recent years we have seen rapid progress in generative models of visual data.
While these models were previously confined to domains with single or few modes, simple structure, and low resolution,
with advances in both modeling and ha... |
fed63383-fd35-422b-bf32-05b9ecc1a4d1 | trentmkelly/LessWrong-43k | LessWrong | What would you need to be motivated to answer "hard" LW questions?
Edit: Significantly rewritten. Original question was more specifically oriented around money-as-a-motivator.
One of the questions (ha) that we are asking ourselves on the LW team is "can the questions feature be bootstrapped into a scalable way of mak... |
7d143a0e-142c-48f8-861b-3fceaec199a9 | trentmkelly/LessWrong-43k | LessWrong | AI #26: Fine Tuning Time
GPT-3.5 fine tuning is here. GPT-4 fine tuning is only a few months away. It is about to get a lot easier to get a powerful system that does what you want it to do, and knows what you want it to know, especially for the purposes of a business or a website.
As an experiment, I am putting in bo... |
792e1e32-4a92-4c27-97d7-c4a2591c86aa | trentmkelly/LessWrong-43k | LessWrong | Neuralink and the Brain’s Magical Future
|
4bec71a9-27d8-40bf-9d4e-c9c525563c5a | trentmkelly/LessWrong-43k | LessWrong | why won't this alignment plan work?
the idea:
* we give the AI a massive list of actions
* each one is annotated with how much utility we estimate it to have
* for example, we list "giving someone sad a hug" as having, say, 6 utility, but "giving someone sad a hug | they didn't consent to it" has -4 utility or... |
a1ef02bc-141d-4606-890e-25d828ded88e | trentmkelly/LessWrong-43k | LessWrong | Mysteries of mode collapse
Thanks to Ian McKenzie and Nicholas Dupuis, collaborators on a related project, for contributing to the ideas and experiments discussed in this post. Ian performed some of the random number experiments.
Also thanks to Connor Leahy for feedback on a draft, and thanks to Evan Hubinger, Conno... |
10a5a5eb-1b00-4bb4-b821-7a3ba8a8be7d | trentmkelly/LessWrong-43k | LessWrong | Who holds all the USDT?
It seems to me like holding billions in USDT is very risky, so no self-interested actor should do so, yet we find billions of dollars in USDT out there. Who holds them and why? |
68ea4e0f-8610-448e-a08e-a92a88d1f492 | trentmkelly/LessWrong-43k | LessWrong | Weekly LW Meetups
This summary was posted to LW Main on May 29th. The following week's summary is here.
Irregularly scheduled Less Wrong meetups are taking place in:
* Ann Arbor, MI Discussion Meetup 6/13: 13 June 2015 01:30PM
* Australian Less Wrong Mega Meetup #2: 17 July 2015 07:00PM
* Australia-wide Mega-Camp... |
08075e46-8b0e-40bb-a26e-9e0eb0a434bb | trentmkelly/LessWrong-43k | LessWrong | Stop posting prompt injections on Twitter and calling it "misalignment"
"Exploits" of large language models that get them to explain steps to build a bomb or write bad words are techniques for misuse, not examples of misalignment in the model itself. Those techniques are engineered by clever users trying to make an LL... |
77151516-0cb4-4237-bb2f-dad43ed68459 | trentmkelly/LessWrong-43k | LessWrong | The Croissant Principle: A Theory of AI Generalization
I recently wrote an ML theory paper which proposes explanations for mysterious phenomena in contemporary machine learning like data scaling laws and double descent. Here's the link to the paper and the Twitter thread. I didn't get much attention and need an endors... |
346dbe77-5efd-4c29-9a81-1d59f713fa48 | trentmkelly/LessWrong-43k | LessWrong | Mathematical Futurology: From Pseudoscience to Rigorous Framework
Futurology has long been dismissed as a pseudoscience, occupying the same intellectual space as astrology in many academic circles. This skepticism isn't entirely unwarranted - much of futurism consists of unfalsifiable predictions, trend extrapolation ... |
971d7da2-a2ea-41b8-9af5-b15f198097e6 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Optimality is the tiger, and annoying the user is its teeth
Just for fun, I wanted to see how far I could get using ChatGPT to implement [Optimality is the tiger, and agents are its teeth](https://www.lesswrong.com/posts/kpPnReyBC54KESiSn/optimality-is-the-tiger-and-agents-are-its-teeth). Its obviously not a good enou... |
0f808838-a641-4cd3-b8b6-747ac98deb69 | trentmkelly/LessWrong-43k | LessWrong | Goal Alignment Is Robust To the Sharp Left Turn
A central AI Alignment problem is the "sharp left turn" — a point in AI training under the SGD analogous to the development of human civilization under evolution, past which the AI's capabilities would skyrocket. For concreteness, I imagine a fully-developed mesa-optimiz... |
574ca82b-5b8b-4858-91df-c80318307678 | trentmkelly/LessWrong-43k | LessWrong | Next PEAR Meet-Up is 8/14 Oregon Park
Hello Aspiring Rationalists of Portland,
So we had another interesting meet-up on 7/31 where we talked about Personality Tests, the status of current Genetic Technology and IVF, the idea of General Intelligence, and using Prediction Markets to judge long term policy successes. Pi... |
a630ca91-a26f-4e4b-8e22-099d2b6215ea | trentmkelly/LessWrong-43k | LessWrong | Deepfake(?) Phishing
[EDIT: I now think this probably wasn't a deepfake, but a recording the attacker made when using the same attack against the previous person. See the comments.]
I think someone just tried to phish my Facebook account, including a fake video of a FB friend. Here's the conversation:
Them, via ... |
e70b0ad5-9baa-4ead-8fda-93de2f2e0646 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Example: Markov Chain
The [previous post in this sequence](https://www.lesswrong.com/posts/zFGGHGfhYsGNnh7Kp/how-to-throw-away-information-in-causal-dags) discussed how to throw away information in causal DAGs. This post provides a detailed example using a Markov chain.
Suppose we have an n-state Markov chain (CS peo... |
7ff8120a-8375-4ece-aa32-9ca07ccaaa90 | trentmkelly/LessWrong-43k | LessWrong | the Daydication technique
I came up with a technique that I have derived much benefit from; what kids call a "lifehack" these days. I have done this for many months, found it extremely useful and the usefulness has been rising fairly steadily as I got better at it. All the friends I could get to try it gave very good ... |
00e31a2e-0d9e-450d-966e-e6f75a3e1221 | trentmkelly/LessWrong-43k | LessWrong | You Can Face Reality
> What is true is already so.
>
> Owning up to it doesn’t make it worse.
>
> Not being open about it doesn’t make it go away.
>
> And because it’s true, it is what is there to be interacted with.
>
> Anything untrue isn’t there to be lived.
>
> People can stand what is true,
>
> for they are... |
3170af5b-79cd-471e-a7ba-34e3db40cdaf | trentmkelly/LessWrong-43k | LessWrong | Creating a database for base rates
TLDR
We are creating a database to collect base rates for various categories of events. You can find the database here and can suggest new base rate categories for us to look into here.
Project Summary
The base rate database project collects base rates for different categories of e... |
7ba36b75-b69d-4ff5-b816-58bd2ede101f | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | Superintelligence -- Andrew Critch
that's just like a chess yeah we are you
might want to use the episode I'm sorry
the fa chai is dependent on has certain
chemical dependencies for cognition ah
one which is isopropyl alcohol oh yes my
own parallel process we it right um so
thanks go on for the anyway all right oh
tha... |
0277fbd3-2edb-4d82-8712-539b45787252 | trentmkelly/LessWrong-43k | LessWrong | Paper: Field-building and the epistemic culture of AI safety
Abstract
The emerging field of “AI safety” has attracted public attention and large infusions of capital to support its implied promise: the ability to deploy advanced artificial intelligence (AI) while reducing its gravest risks. Ideas from effective altrui... |
a5d787f1-2b13-4556-814f-61df37607b9f | trentmkelly/LessWrong-43k | LessWrong | [AN #111]: The Circuits hypotheses for deep learning
Alignment Newsletter is a weekly publication with recent content relevant to AI alignment around the world. Find all Alignment Newsletter resources here. In particular, you can look through this spreadsheet of all summaries that have ever been in the newsletter.
Au... |
bc6c5b31-f863-410d-a90c-ca1e7db81e79 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | How should my timelines influence my career choice?
TL;DR: Recent progress in AI has tentatively shortened my expected timelines of human-level machine intelligence to something like 50% in the next 15 years. Conditional on that being a sensible timeline (feel free to disagree in the comments), how should that influen... |
fc941828-208a-4a77-aabc-944c455b54b6 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | The genie knows, but doesn't care
**Followup to**: [The Hidden Complexity of Wishes](/lw/ld/the_hidden_complexity_of_wishes/), [Ghosts in the Machine](/lw/rf/ghosts_in_the_machine/), [Truly Part of You](/lw/la/truly_part_of_you/)
**Summary**: If an artificial intelligence is smart enough to be dangerous, we'd intuit... |
34f89250-1cdf-49c9-8121-ba703772e3a3 | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post303
This is a linkpost for a new research paper from the Alignment Evaluations team at Anthropic and other researchers, introducing a new suite of evaluations of models' abilities to undermine measurement, oversight, and decision-making. Paper link . Abstract: Sufficiently capable models could subvert human ov... |
953559c0-8855-4653-96ea-0e61f10f4449 | trentmkelly/LessWrong-43k | LessWrong | List of good AI safety project ideas?
Can we compile a list of good project ideas related to AI safety that people can work on? There are occasions at work when I have the opportunity to propose interesting project ideas for potential funding, and it would be really useful if there was somewhere I could look for proje... |
1cba6bc2-30a5-4314-bcec-983ef75bce52 | trentmkelly/LessWrong-43k | LessWrong | Is Specificity a Mental Model?
This is Part IX of the Specificity Sequence
I've recently noticed a lot of smart people publishing lists of mental models. They're apparently having a moment:
* Mental Models: The Best Way to Make Intelligent Decisions by Shane Parrish
* Mental Models I Find Repeatedly Useful and Sup... |
9c0d625f-e477-4338-a44b-0392c6a48f33 | trentmkelly/LessWrong-43k | LessWrong | Counterfactual Civilization Simulation Version -1.0 aka my application to Johannes Mayer's SPAR project
This is my "object level output" submission for Johannes Mayer's 2024 SPAR Application (the linked doc seems to be reused from the 2023 AISC application). Unless otherwise noted, all quote blocks in this post are fr... |
573e68e3-ef19-41d9-9df2-ad71b5c22c65 | trentmkelly/LessWrong-43k | LessWrong | AI Safety orgs- what's your biggest bottleneck right now?
|
775d7126-e920-4fbc-a0df-72744332aa43 | trentmkelly/LessWrong-43k | LessWrong | Variables in Arguments as a Source of Confusion
I was reading an argument happening in the comments of an article about Light Table switching to open source. The argument was about freedom in relation to software, and it went basically something like this:
> People who use OSX are less free [than Linux users], becaus... |
097f8d27-8694-4bca-b5d9-b163faee9973 | trentmkelly/LessWrong-43k | LessWrong | Causal Inference Sequence Part II: Graphical Models
(Part 2 of a Sequence on Applied Causal Inference. Follow-up to Part 1)
Saturated and Unsaturated Models
A model is a restriction on the possible states of the world: By specifying a model, you make a claim that you have knowledge about what the world does not look... |
8f6899e4-c5fa-4311-8e43-53ef697916a1 | trentmkelly/LessWrong-43k | LessWrong | Reality and reality-boxes
> We depend on our words... Our task is to communicate experience and ideas to others... The word "reality" is also a word, a word which we must learn to use correctly.
> — Niels Bohr, Philosophy of Science Vol. 37 (1934), p. 157
While trying to write about some of the new things that have ... |
f5881867-fc91-4174-8335-9167313d7bde | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Announcing the Open Philanthropy AI Worldviews Contest
**Update**: *The winners have been selected and notified and will be publicly announced no later than the end of September.*
We are pleased to announce the 2023 Open Philanthropy AI Worldviews Contest.
The goal of the contest is to surface novel considerations t... |
b69bac9e-67e9-460d-8d25-5d8895bdb446 | trentmkelly/LessWrong-43k | LessWrong | Any layperson-accessible reference posts on how to operationalize beliefs ?
I'd like to find a shortish collection of advice, "do"s/"don't"s, aimed at... rationalist-adjacent folk?... for operationalizing beliefs into concrete anticipated experiences. My searches so far have been fruitless; I'd be grateful for any poi... |
6c68626e-00a3-4779-acc0-d94f99af55bf | trentmkelly/LessWrong-43k | LessWrong | Meetup : Moscow, First New Year
Discussion article for the meetup : Moscow, First New Year
WHEN: 12 January 2014 04:00:00PM (+0400)
WHERE: Russia, Moscow, ulitsa L'va Tolstogo 16
It will be our next meet up, so there is no gathering on 5th.
We will gather at the same second entrance, but we will go to the new room... |
3b9cf3a3-9ee1-4f52-8313-20eadef9a8f1 | trentmkelly/LessWrong-43k | LessWrong | GPT-3 and concept extrapolation
At the latest EAG in London, I was challenged to explain what concept extrapolation would mean for GPT-3.
My first thought was the example from this post, where there were three clear patterns fighting each other for possible completions: the repetition pattern where she goes to work, ... |
2b88640f-afbf-47b4-bc94-694ade07d330 | trentmkelly/LessWrong-43k | LessWrong | Counterfactuals: Smoking Lesion vs. Newcomb's
We will consider a special version of the Smoking Lesion where there is 100% correlation between smoking and cancer - ie. if you have the lesion, then you smoke and have cancer, if you don't have the lesion, then you don't smoke and don't have cancer. We'll also assume the... |
94aa4982-7df0-4967-83f6-0e97c6f252f1 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Transformative AI and Compute - Reading List
This is a link post to the reading list about Transformative AI and Compute by Lennart Heim.
Readings within the list are put into the following buckets:
1. [Compute in the AI Production Function](https://docs.google.com/document/d/1DF31DIkwS9GONzmy1W3nuI9HRAwSKy8JcIbzKYX... |
3a3bcb6b-712a-4a2a-9f1c-5aee97b9d903 | trentmkelly/LessWrong-43k | LessWrong | Why I've started using NoScript
> Edit: I've updated somewhat based on Said's comment below, to think that NoScript is not a tool for everyone. I haven't decided to stop using it, but I have decided to stop strongly recommending that others use it. I especially urge you to read about the other extensions he lists at t... |
9d4942df-160f-4531-abef-0ee2d4b3bfa8 | StampyAI/alignment-research-dataset/special_docs | Other | An Agent-Based Model of Strategic Adoption of Real-Time Payments.
An Agent-Based Model of Strategic Adoption of Real-Time
Payments
Katherine Mayo
University of Michigan
kamayo@umich.eduShaily Fozdar
University of Michigan
sfozdar@umich.eduMichael P. Wellman
University of Michigan
wellman@umich.edu
ABSTRACT
Real-time p... |
b6069c61-4bd2-421a-848e-cebe81d0d909 | trentmkelly/LessWrong-43k | LessWrong | Is there a word for discrimination against A.I.?
We've all heard of racism. We've all heard of sexism. Many of us have heard of speciesism. Other than "speciesism", is there a word for discrimination against the intelligence in systems running on computing machinery? Do you think that we're going to need one? Or do yo... |
448bb7c4-ea4e-49fc-b34f-6210d2910361 | trentmkelly/LessWrong-43k | LessWrong | Acting Wholesomely
Overview of essay series
This is the first in a collection of three essays exploring and ultimately defending the idea of choosing what feels wholesome as a heuristic for picking actions which are good for the world. I'm including a summary of the series here, before getting to the essay proper.
... |
dd58b898-1dd2-4abf-bb14-3615bfe6e7a0 | StampyAI/alignment-research-dataset/special_docs | Other | Adapting a kidney exchange algorithm to align with human values.
Adapting a kidney exchange algorithm to align with human values[☆](#aep-article-footnote-id1)
=============================================================================================
Abstract
--------
The efficient and fair allocation of limited r... |
1212b7b1-0dfa-4dd1-a766-e764f7148e93 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Applications for EU Tech Policy Fellowship 2024 now open
* **What:** The [EU Tech Policy Fellowship](https://www.techpolicyfellowship.eu/) is a 7-month programme that empowers ambitious g... |
ce0ed4bd-e65f-4f34-a238-fb56f6348834 | trentmkelly/LessWrong-43k | LessWrong | NFTs, Coin Collecting, and Expensive Paintings
I‘ve tried to make this post fairly nuanced and with a lot of steelmanning, in contrast to much of the material on this subject. My opinions on crypto as a whole are more complex and deserve a separate, more in depth post. None of this is financial advice, I am not a fina... |
34416aa5-e75b-4fa0-b5b8-4ab303a3be91 | trentmkelly/LessWrong-43k | LessWrong | Avoiding strawmen
George Bernard Shaw wrote that, "the single biggest problem in communication is the illusion that it has taken place". Much of strawmanning is unconscious. One person says that it is important to be positive, the other person interprets this as it being important to be positive in *all* circumstances... |
fc422ef5-2007-4e39-ab51-465166df5842 | trentmkelly/LessWrong-43k | LessWrong | At what level of coronavirus cases in a population should the people in that population start self-quarantining?
The question and desiderata
I'm looking for a specific number here, even an equation. At what # of reported coronavirus cases (or estimated actual cases) within a population should the members of that popu... |
2dd2d54a-3102-46de-a04a-03b5c0444eea | trentmkelly/LessWrong-43k | LessWrong | The Moon is Down; I have not heard the clock
I wanted to share a quick post about something that's made me significantly happier over the past year: knowing what the phase of the moon is on any given day. Importantly, I don't do this with any kind of computer tool. It's a proxy for "am I spending enough time outside... |
72f514bc-f1f0-4679-a0ba-53e325a5b540 | StampyAI/alignment-research-dataset/special_docs | Other | ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models
ObjectNet: A large-scale bias-controlled dataset for
pushing the limits of object recognition models
Andrei Barbu
MIT, CSAIL & CBMMDavid Mayo
MIT, CSAIL & CBMMJulian Alverio
MIT, CSAILWilliam Luo
MIT, CSAIL
Christoph... |
344edfbd-1e41-4bfe-9ba1-4f149ca90d1b | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Announcing the EA Project Ideas Database
In January, David Reinstein [suggested](https://forum.effectivealtruism.org/posts/eQgKyCQW4u5CCWHXt/idea-curated-database-of-quick-win-tangible-attributable) creating a database of quick-win EA project ideas. In March, he created an [Airtable](https://airtable.com/shrNps2rJwQxR... |
a9289fb8-3a3c-4745-ad5e-15ef14cef2f4 | trentmkelly/LessWrong-43k | LessWrong | The flawed Turing test: language, understanding, and partial p-zombies
There is a problem with the Turing test, practically and philosophically, and I would be willing to bet that the first entity to pass the test will not be conscious, or intelligent, or have whatever spark or quality the test is supposed to measure.... |
4e17f0eb-1661-4af5-b0d9-87d992e4c4df | StampyAI/alignment-research-dataset/arbital | Arbital | Invisible background fallacies
Suppose that you went outdoors and jumped up into the air, and then, as you were jumping, the law of gravity suddenly switched off--for whatever weird reason, masses everywhere in the Universe stopped attracting one another. Would your feet hit the ground again?
As an initial thought a... |
2958ca6a-48ec-4059-86b5-31b952d20950 | trentmkelly/LessWrong-43k | LessWrong | Disgust and Politics
|
5d9d8ee3-b3b4-43f2-858f-ade1c1b20c94 | trentmkelly/LessWrong-43k | LessWrong | NTK/GP Models of Neural Nets Can't Learn Features
Since people are talking about the NTK/GP hypothesis of neural nets again, I thought it might be worth bringing up some recent research in the area that casts doubt on their explanatory power. The upshot is: NTK/GP models of neural networks can't learn features. By 'fe... |
0e24b226-5d5d-482e-9f23-89e7d1537804 | trentmkelly/LessWrong-43k | LessWrong | Should it be a research paper or a blog post?
The answer to this question may seem obvious to some, but let's see.
My impression is that some people write long blog posts about things that they perceive as innovative new ideas in philosophy, AI research, or whatever. So how do you decide that your idea should be a... |
1506e435-c206-40fb-ada1-c0c80c5f2e0e | trentmkelly/LessWrong-43k | LessWrong | Can AI partners make human ones pale in comparison?
We normally view AI as cold, pragmatic, and, maybe, even socially awkward. The risks we identify reflect this stereotype. Just consider the paperclip maximizer; a superintelligent AI is asked to manage a paperclip factory. As it is trying to maximize the paperclip pr... |
945b30c8-0c41-48d7-b1f6-d59411fad89f | trentmkelly/LessWrong-43k | LessWrong | Rationalist prepper thread
There are different estimates of the possible severity of the current coronavirus outbreak. One estimation is based on the straight extrapolation of the exponential growth of the infected people number, which doubles every two days. This implies that the whole population of Earth will be ill... |
78b07648-c956-48f1-8cfe-d93acd5c1bad | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Is the "Valley of Confused Abstractions" real?
Epistemic Status: Quite confused. Using this short post as a signal for discussion.
In Evan's post about [Chris Olah's views on AGI safety](https://www.alignmentforum.org/posts/X2i9dQQK3gETCyqh2/chris-olah-s-views-on-agi-safety#What_if_interpretability_breaks_down_as_AI_... |
aa8d848e-02db-45db-a42b-c5fb968a1256 | StampyAI/alignment-research-dataset/special_docs | Other | Death and pain of a digital brain
26 | NewScientist | 12 September 2015I turned off the computer as I left my office,
deleting the neural network simulation that I had been working on. Then a thought hit me: had I just killed something? I rationalised that the simulation was simpler than the systems within the bacter... |
9649f06c-aba6-4f09-ab09-43e349889382 | trentmkelly/LessWrong-43k | LessWrong | List of AI safety papers from companies, 2023–2024
I'm collecting (x-risk-relevant) safety research from frontier AI companies published in 2023 and 2024: https://docs.google.com/spreadsheets/d/10_dzImDvHq7eEag6paK6AmIdAGMBOA7yXUvumODhZ5U/edit?usp=sharing.
----------------------------------------
I was planning to g... |
ccabc858-a6d3-4f51-86cd-368c83ec996a | trentmkelly/LessWrong-43k | LessWrong | Deceptive failures short of full catastrophe.
Epistemic status: trying to unpack a fuzzy mess of related concepts in my head into something a bit cleaner.
A lot of my concern about risks from advanced AI is because of the possibility of deceptive alignment. Deceptive alignment has already been discussed in detail on t... |
2700d850-8273-47bb-802e-b7a37ab005de | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | AI alignment and Redwood Research | Buck Shlegeris (CTO)
[Music]
hello everyone my name is oliver and
welcome to the q a with redwood research
cto buck schlieres
buck previously worked at miri studied
computer science and physics at the
australian national university and grew
up in townsville australia please join
me ... |
9eaa2709-29f8-43bd-b27a-ac4d8ee71e36 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Introducing The Nonlinear Fund: AI Safety research, incubation, and funding
Summary
-------
1. **We research high leverage AI Safety interventions.** Our team of analysts generate, identify, and evaluate potentially high impact opportunities.
2. **When we find them, we make them happen.** Once a top idea has been vet... |
fceca5c1-0dbc-43e0-b344-b3841f8b9936 | trentmkelly/LessWrong-43k | LessWrong | Explanatory normality fallacy
> Only a psychologist thinks to ask why people laugh at jokes. – Someone (apparently)
A common error in trying to understand human behavior is to think something is explained because it is so intuitively familiar to you. The wrong answer to, ‘I wonder why people laugh at jokes?’ is, ‘Th... |
e2e8efac-41ed-4963-a1ad-ea893424d40c | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Classifying sources of AI x-risk
There are many potential sources of x-risk from AI, and [wide disagreement/uncertainty](https://forum.effectivealtruism.org/posts/2tumunFmjBuXdfF2F/survey-on-ai-existential-risk-scenarios-1) about which are the most important. To help move towards greater clarity, it seems valuable to ... |
acddc6cc-e10f-4bd1-a1e9-511013cc773f | StampyAI/alignment-research-dataset/arxiv | Arxiv | Transfer Reinforcement Learning across Homotopy Classes
I Introduction
---------------
One of the goals of transfer learning is to efficiently learn policies in tasks where sample collection is cheap and then transfer the learned knowledge to tasks where sample collection is expensive.
Recent deep reinforcement lea... |
4142796d-615a-4054-8800-d9261769f73a | trentmkelly/LessWrong-43k | LessWrong | Theories of Impact for Causality in AI Safety
Thanks to Jonathan Richens and Tom Everitt for discussions about this post.
The case for causality research[1] is under-stated in the broader AI Safety community. There are few convincing arguments floating around for why and how research in causality can help us understa... |
74506be9-0c93-454b-93c8-8652617ab876 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | [AN #128]: Prioritizing research on AI existential safety based on its application to governance demands
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 particu... |
b9e1bef0-4d7d-4491-8797-a1da94f612f5 | trentmkelly/LessWrong-43k | LessWrong | ChatGPT Plays 20 Questions [sometimes needs help]
Cross posted from New Savanna.
One of the questions that keeps coming up about LLMs, and certainly about ChatGPT, is: Can they reason? Well, it depends on what you mean by reason, no? One of the first things I did when I started working with ChatGPT was ask it wheth... |
a6a84a94-4ab6-45a2-b92e-3934dda67a5c | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | UK government to host first global summit on AI Safety
An exciting development in this space, it may be worth people thinking about what to organise around this summit. I've copied the press release in full below.
----------------------------------------------------------------
* Summit will bring together key count... |
5914c866-1be9-4031-971a-0569f78a7540 | trentmkelly/LessWrong-43k | LessWrong | Applications are open for CFAR workshops in Prague this fall!
tldr: CFAR’s running updated versions of our mainline rationality workshop this fall in the Prague area. Apply here.
===
CFAR workshops are back! After a nearly three-year hiatus during COVID, we're going to be running a series of four workshops this fal... |
9ebaefb2-e2a2-4868-82c7-50691338c86c | trentmkelly/LessWrong-43k | LessWrong | Meetup : Sandy, UT—Altruism Discussion
Discussion article for the meetup : Sandy, UT—Altruism Discussion
WHEN: 21 February 2015 03:00:11PM (-0700)
WHERE: 9425 Riverside Dr, Sandy, UT 84070
Topic: Altruism ========================== When: Saturday, February 21 at 3:00pm Where: Clubhouse at Legends at River Oaks in S... |
00912426-3124-4207-b120-2dd6c3cce594 | trentmkelly/LessWrong-43k | LessWrong | Burdens
[Content note: Suicide. May be guilt-inducing for people who feel like burdens. All patient characteristics have been heavily obfuscated to protect confidentiality.]
The DSM lists nine criteria for major depressive disorder, of which the seventh is “feelings of worthlessness or excessive or inappropriate guil... |
2505d7ae-8a12-48ab-8c51-b652adae9d35 | trentmkelly/LessWrong-43k | LessWrong | Interest in a Coventry/Birmingham meetup?
I'm in Coventry myself (at Warwick uni), and now that I've finished exams I'd like to see if there's sufficient interest for a meetup in the area.
(I'm actually only around for another six weeks or so, but even if we only manage to meet once or twice, that seems worth doing.)... |
16169365-34fd-4bbd-b80d-b18c8f225b67 | trentmkelly/LessWrong-43k | LessWrong | What are red flags for Neural Network suffering?
Epistemic status: High uncertainty; This is exploratory work; Our goal is to provide possible research directions rather than offering solutions.
This is shared work. Most of the part on neural correlates is by Jan. Most of the parts on behavior and high-level consider... |
6ef95ed7-e121-4b17-82a2-7cb0ddbe8232 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | GPT-2030 and Catastrophic Drives: Four Vignettes
I previously [discussed the capabilities](https://bounded-regret.ghost.io/what-will-gpt-2030-look-like/) we might expect from future AI systems, illustrated through GPT2030, a hypothetical successor of GPT-4 trained in 2030. GPT2030 had a number of advanced capabilities... |
cf92e86c-69c1-43db-9a4c-eb5efda4aeda | trentmkelly/LessWrong-43k | LessWrong | Omicron #16: Danger in China
What is happening in China?
Scott Gottlieb says we essentially don’t know the extent to which Omicron has spread in China.
What do we know?
We know China has not made great use of its time so far, and seems incapable of the loss of face necessary to get mRNA vaccines, nor does it seem t... |
fe0fb66a-fb71-4f36-b8d5-0155ec96a620 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | OPEC for a slow AGI takeoff
The topic of AI is a matter of discussion and controversy among many, including experts who cannot reach a consensus on AGI and AI safety. This is exemplified by three pioneers of deep learning and winners of the Turing Award 2018 - Yoshua Bengio, Geoffrey Hinton, and Yann Le Cunn - who hav... |
f88016af-0a54-4fbc-a00c-1888e61da2f2 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Still no Lie Detector for LLMs
Background
==========
This post is a short version of a paper we wrote that you can find [here](https://arxiv.org/abs/2307.00175). You can read this post to get the core ideas. You can read the paper to go a little deeper.
The paper is about probing decoder-only LLMs for their beliefs,... |
bd2d6eba-9300-4f7e-9a8e-ecc32c4a865c | trentmkelly/LessWrong-43k | LessWrong | When's the best time to get the 2nd dose of Pfizer Vaccine?
I guess officially it's supposed to be 3 weeks, but IIRC, I heard a bit longer (~6-8 weeks?) is ideal? |
922e37cf-e43a-4712-95ad-311b16e845a7 | trentmkelly/LessWrong-43k | LessWrong | What do superintelligences really want? [Link]
> In Conclusion:
>
> In the case of humans, everything that we do that seems intelligent is part of a large, complex mechanism in which we are engaged to ensure our survival. This is so hardwired into us that we do not see it easily, and we certainly cannot change it ver... |
46f3577f-e16e-4a76-8ce2-e188356f7f4e | trentmkelly/LessWrong-43k | LessWrong | Stream Entry
"Is this…enlightenment?" I asked.
"We use the word 'Awakening'," said the Zen Master, kindly.
"Now what?" I asked, "Every book I've read about meditation is about getting to this point. There's nothing about how to safely navigate the territory afterward—or what to do afterward—or even what happens afte... |
0757ba98-879f-4aa7-b7d2-5f3b51d81f6a | trentmkelly/LessWrong-43k | LessWrong | does there are any onther Rationalists in Quebec city
i ask because i have seen a Montreal meetup group but none for Quebec city.
if you are interested pm me and I will see what i can do. |
da1b8e13-4177-4436-bff3-7d16861a5927 | trentmkelly/LessWrong-43k | LessWrong | The Problem With the Word ‘Alignment’
This post was written by Peli Grietzer, inspired by internal writings by TJ (tushant jha), for AOI[1]. The original post, published on Feb 5, 2024, can be found here: https://ai.objectives.institute/blog/the-problem-with-alignment.
The purpose of our work at the AI Objectives Ins... |
dde4dc1b-1c11-4faa-8e0b-f12440fb8d3e | trentmkelly/LessWrong-43k | LessWrong | [Link] Self-Representation in Girard’s System U
Self-Representation in Girard’s System U, by Matt Brown and Jens Palsberg:
> In 1991, Pfenning and Lee studied whether System F could support a typed self-interpreter. They concluded that typed self-representation for System F “seems to be impossible”, but were able to ... |
6765690e-ffe4-4ed1-94f0-1fe1f03f1eb3 | trentmkelly/LessWrong-43k | LessWrong | Off to Alice Springs
Am about to pack up computer then go to the airport to start a sequence of flights to give this a try.
I already have a room in a hostel booked for a few nights for when I get there, and will see how stuff goes.
Anyways, since there's been on and off discussion on this, just thought I'd post tha... |
821f6977-3a1d-4588-8f59-130de81a68e1 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Learning Language Games through Interaction
1 Introduction
---------------
Rysunek 1:
The SHRDLURN game:
the objective is to transform the start state into the goal state.
The human types in an utterance, and the computer (which does not... |
a0b4db98-2518-496d-bbdc-bcbcf0c73487 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | You're not a simulation, 'cause you're hallucinating
I've found that the "[Simulators](https://www.lesswrong.com/posts/vJFdjigzmcXMhNTsx/simulators)" post is excellent for breaking prior assumptions about large language models - these algorithms are not agents, nor genies, nor Oracles. They are currently something ver... |
10dfbdd5-33b7-4c9d-b39b-6fa4dee66557 | trentmkelly/LessWrong-43k | LessWrong | My book: Simulating Dennett - This Wednesday in Sao Paulo
There's been somewhat frequent coverage of Daniel Dennett on Lesswrong:
How not to be a Naïve Computationalist
Dennett's "Consciousness Explained": Prelude
"Where Am I?", by Daniel Dennett
Dennett's heterophenomenology
My personal favorite: Zombies: The... |
2f0b9d57-435a-430b-87c7-3256da9174df | trentmkelly/LessWrong-43k | LessWrong | A NotKillEveryoneIsm Argument for Accelerating Deep Learning Research
TLDR: This is really just a longer version of this comment.
A metaphor
You are Rocket McRocket-Face, the CEO of Rockets Inc, the world’s largest and most reputable rocket company. Rockets Inc isn’t the only rocket company in the world, but it i... |
babd9eec-960d-42bf-bdce-fa6811c0064a | trentmkelly/LessWrong-43k | LessWrong | Proposal: we should start referring to the risk from unaligned AI as a type of *accident risk*
In the wider political sphere, a lot of people are worried about AI misuse risk. Unaligned AI is not a type of misuse. I think the clearest way to describe this is as an accident risk, in the same sense of the word as indust... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.