id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
4971ec0f-1ec0-404e-81d4-f8440fe31b6c | trentmkelly/LessWrong-43k | LessWrong | 🇫🇷 Announcing CeSIA: The French Center for AI Safety
Executive Summary
The Centre pour la Sécurité de l'IA[1] (CeSIA, pronounced "seez-ya") or French Center for AI Safety is a new Paris-based organization dedicated to fostering a culture of AI safety at the French and European level. Our mission is to reduce AI risk... |
f026b91a-21ab-49ee-8012-e5ba2bbc3a54 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Conditioning Generative Models with Restrictions
*This is a followup to* [*Conditioning Generative Models*](https://www.alignmentforum.org/posts/nXeLPcT9uhfG3TMPS/conditioning-generative-models) *based on further discussions with Evan Hubinger, Nicholas Schiefer, Abram Demski, Curtis Huebner, Hoagy Cunningham, Derek S... |
0d3be2f0-d404-4d1c-83af-f42fc3b0da49 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Incentives affecting alignment-researcher encouragement
My hypothesis: I think the incentives for "cultivating more/better researchers in a preparadigmatic field" lean towards "don't discourage even less-promising researchers, because they could luck out and suddenly be good/useful to alignment in an unexpected way".
... |
6d94df24-3d13-4827-ac68-4d6e82ff97d3 | trentmkelly/LessWrong-43k | LessWrong | Politics are not serious by default
[This is part of a series I’m writing on how to convince a person that AI risk is worth paying attention to.]
tl;dr: People’s default reaction to politics is not taking them seriously. They could center their entire personality on their political beliefs, and still not take them s... |
2456d71e-f2cd-4833-b12c-346671fe83e6 | trentmkelly/LessWrong-43k | LessWrong | The medical test paradox: Can redesigning Bayes rule help?
A great coverage of one of my favorite Youtuber's of the (on LessWrong) classical reformulation of Bayes rule in terms of odds instead of probabilities. I expect to link a bunch of people to this, in particular if they get stuck reading Eliezer's intuitive exp... |
34b01731-757b-47bf-9139-e66141c98bab | trentmkelly/LessWrong-43k | LessWrong | The Dead Planet Theory
Hi, this is my first post on LessWrong but I have been in rationalist adjacent circles for the last three or four years thanks to Twitter. Like many others here I read HPMOR in high school and thought it was fascinating. I was heavily into forum culture growing up but it was focused on competiti... |
e493abe2-ce91-4d70-9065-9700f5e8c82d | trentmkelly/LessWrong-43k | LessWrong | So, just why do GPTs have to operate by continuing an existing string?
Cross-posted from New Savanna.
Why can’t they, you know, just come out with it, like we do?
Yeah, I know, that’s how they’re trained; they’re trained to predict the next token. I’m not sure what that tells me.
So, when I give ChatGPT the prompt... |
21d70f04-751d-4412-997e-445752428601 | StampyAI/alignment-research-dataset/arxiv | Arxiv | An Offline Risk-aware Policy Selection Method for Bayesian Markov Decision Processes
An O ine Risk-aware Policy Selection Method for Bayesian
Markov Decision Processes
Giorgio Angelottia,b,, Nicolas Drougarda,b, Caroline P. C. Chanela,b
aANITI - Artificial and Natural Intelligence Toulouse Institute, University of To... |
b39779f8-a1b9-413e-951b-1653c050e8cc | StampyAI/alignment-research-dataset/lesswrong | LessWrong | IMO challenge bet with Eliezer
Eliezer and I publicly stated some predictions about AI performance on the IMO by 2025. In honor of OpenAI's post [Solving (Some) Formal Math Problems](https://openai.com/blog/formal-math/), it seems good to publicly state and clarify our predictions, have a final chance to adjust them, ... |
3002628f-e8b6-41c7-8575-66a34b27cbe4 | trentmkelly/LessWrong-43k | LessWrong | The ‘strong’ feature hypothesis could be wrong
NB. I am on the Google Deepmind language model interpretability team. But the arguments/views in this post are my own, and shouldn't be read as a team position.
> “It would be very convenient if the individual neurons of artificial neural networks corresponded to cl... |
4bddd547-57bb-4986-9866-7260f90ec61d | trentmkelly/LessWrong-43k | LessWrong | Automated theorem proving by learning from examples
Does anyone know of work that attempts to build a theorem prover by learning-from-examples? I'm imagining extracting a large corpus of theorems from back issues of mathematical journals, then applying unsupervised structure discovery techniques from machine learning ... |
e99dc917-6fbf-4d2d-a4e7-8b79b675e1dc | trentmkelly/LessWrong-43k | LessWrong | A Conflicted Linkspost
Over the last couple of years, I’ve been trying to skill up a lot at resolving community complaints. This is a really irritating field to get good at. When I want to get better at writing code, I can sit down and write more code more or less whenever I feel like it. When I want to get better at... |
9363ed35-045e-4919-a1f0-648db73dd910 | trentmkelly/LessWrong-43k | LessWrong | Help the Brain Preservation Foundation
(First time poster, long time reader)
I'm currently volunteering for the Brain Preservation Foundation (http://www.brainpreservation.org/), and I'd like to ask for your help.
The purpose of the BPF is to incentivize and evaluate the development of technology which can preserve... |
70144b07-3123-45e1-bd88-96b1e95fc6d5 | trentmkelly/LessWrong-43k | LessWrong | Meetup : SF Meetup: Revealed New Year's Resolutions
Discussion article for the meetup : SF Meetup: Revealed New Year's Resolutions
WHEN: 09 January 2017 06:15:22PM (-0800)
WHERE: 1769 15th St., SF
It's a yearly tradition!
Instead of talking about what we've resolved to do in the New Year, we'll talk about, from lo... |
e40f85ed-ca5d-4bad-8b38-ec4ca1ec7254 | trentmkelly/LessWrong-43k | LessWrong | Solar Production Data
We have solar panels on our house, configured so that we can have backup power in a blackout. In talking about generators and power outages I wanted to figure out how much power we might expect to be able to draw.
Our system is a bit weird. We have 14 panels, rated for 360W each. Most of them (1... |
997dc2c2-4a40-4676-928c-74756a026acb | trentmkelly/LessWrong-43k | LessWrong | How to cheat Löb's Theorem: my second try
In his open problems talk, Eliezer explains how Löb's theorem prevents you from having a consistent proof system P with an axiom schema that anything P proves is actually true, and asks how we can then "build an AI that could completely rewrite itself, without decreasing the a... |
48fd1dcb-aa24-4c10-9871-0c59da31fdb2 | trentmkelly/LessWrong-43k | LessWrong | Passing through St. Louis
I'm Alex, the coordinator for the Kansas City Rationalists. I'll be passing through St Louis for brunch/lunch on May 17th, and would love to network with anyone who's available. My community is highly varied; we run a game night, a dojo, and an SSC meetup. I'd love to share my experiences if ... |
b4e4c73c-80a6-487b-8846-5ea78019d3f6 | trentmkelly/LessWrong-43k | LessWrong | Mistakes I’ve made, part 1: greedy altruism
I have made many mistakes. Unfortunately, for some of my older, larger mistakes, it becomes hard to remember or imagine why I would have made them. The alternative position comes to seem literally inconceivable. At the same time, I forget that I ever conceived of it. This is... |
ef5613f1-ea27-462d-afef-b65c2fa252cc | trentmkelly/LessWrong-43k | LessWrong | Reasons compute may not drive AI capabilities growth
How long it will be before humanity is capable of creating general AI is an important factor in discussions of the importance of doing AI alignment research as well as discussions of which research avenues have the best chance of success. One frequently discussed mo... |
e2c817aa-418e-4a85-b6db-f0d9cc54b89a | trentmkelly/LessWrong-43k | LessWrong | Mixed-Strategy Ratifiability Implies CDT=EDT
I provide conditions under which CDT=EDT in Bayes-net causal models.
----------------------------------------
[Epistemic status: Thanks to a discussion with Benja, I'm much less optimistic about the general thrust of this. In particular, the framework here isn't expressiv... |
c0164359-3db6-43e1-b0a7-3b87bff85c03 | trentmkelly/LessWrong-43k | LessWrong | Exploring vocabulary alignment of neurons in Llama-3.2-1B
(This is cross-posted from my blog at https://grgv.xyz/blog/neurons1/. I'm looking for feedback: does it makes sense at all, and if there is any novelty. Also, if the folloup questions/directions make sense)
While applying logit attribution analysis to transfo... |
9f777e49-e83d-447c-820a-7007e3de0f1d | trentmkelly/LessWrong-43k | LessWrong | Making computer systems with extended Identity
We often assume that an AI will have an identity and goals of its own. That it will be some separate entity from a human being or group of humans.
In physics there are no separate entities, merely a function evolving through time. So any identity needs to be constructed... |
1a829b59-ef58-4c3c-a8f1-d5cb7bd2d393 | trentmkelly/LessWrong-43k | LessWrong | Drug development costs can range over two orders of magnitude
This is a cross-post from my new newsletter, where I intend to post about clinical trials and biotech, and from my personal blog, where I intend to go on posting about all other sorts of topics as well.
I also recently went on the Complex Systems podcast, ... |
421768f9-ecb9-4291-a7c6-6b576e1374fc | trentmkelly/LessWrong-43k | LessWrong | The Road to Evil Is Paved with Good Objectives: Framework to Classify and Fix Misalignments.
Abstract
There are numerous examples of AI models exhibiting behaviours that are totally unintended by their creators. This has direct implications on how we can deploy safe-to-use AI. Research on solving the 'alignment probl... |
19f8256c-8ad7-4f98-94cb-7db58b1fc6fe | trentmkelly/LessWrong-43k | LessWrong | Booster shots from same vs different vaccines
What is the current thinking on whether it's safe and effective to get a COVID booster shot from a different vaccine than the one you originally received? For example, getting a Pfizer shot if you originally got J&J. Is it more effective than getting a booster shot of the ... |
13a81dd0-1046-446a-9778-f5a83c047bd0 | trentmkelly/LessWrong-43k | LessWrong | European Links (30.04.25)
Pan-Iberian blackout
Works in Progress is no news source, but they’ve managed to publish an article on the topic within 24 hours:
> Every country in the world has a grid designed around the large rotating generators used in nuclear, coal, and gas power plants. They rely on heat boiling water... |
91d58290-2ef3-418f-be75-f3ad6f0272f9 | trentmkelly/LessWrong-43k | LessWrong | Get Curious
> Being levels above in [rationality] means doing rationalist practice 101 much better than others [just like] being a few levels above in fighting means executing a basic front-kick much better than others.
- lessdazed
> I fear not the man who has practiced 10,000 kicks once, but I fear the man who has ... |
43180af2-14d4-4390-babb-eacee48ba064 | trentmkelly/LessWrong-43k | LessWrong | As Many Ideas
Summary: One person announces a problem to the room at large. Everyone else comes up with as many ideas as they can to solve the problem.
Tags: Repeatable, Medium, Investment, Experimental
Purpose: The purpose is twofold. Firstly, you may walk away with actionable solutions to your problems. Secondly, ... |
ccc64b40-4f38-481f-96f0-6b950445bfd9 | trentmkelly/LessWrong-43k | LessWrong | Two types of mathematician
This is an expansion of a linkdump I made a while ago with examples of mathematicians splitting other mathematicians into two groups, which may be of wider interest in the context of the recent elephant/rider discussion. (Though probably not especially wide interest, so I'm posting this to m... |
0800449f-d0c3-4908-bd02-65ae2d8fd428 | trentmkelly/LessWrong-43k | LessWrong | Practical tools and agents
Presently, the 'utility maximizers' work as following: given a mathematical function f(x) , a solver finds the x that corresponds to a maximum (or, typically, minimum) of f(x) . The x is usually a vector describing the action of the agent, the f is a mathematically defined function which may... |
6d8ed7e0-fc37-4761-82d2-035a7029a5a2 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Reader-generated Essays
### 1.
An essay is made up of two layers: the ideas, and the language in which they are expressed. *The story of Red Riding Hood*, and the words of a particular retelling of that story. *The idea of a fully programmable blockchain*, and the language that Vitalik Buterin used to carry that id... |
2f648d43-e5bc-4226-aab7-944c26f8ed27 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Proofs Section 1.2 (Mixtures, Updates, Pushforwards)
.mjx-chtml {display: inline-block; line-height: 0; text-indent: 0; text-align: left; text-transform: none; font-style: normal; font-weight: normal; font-size: 100%; font-size-adjust: none; letter-spacing: normal; word-wrap: normal; word-spacing: normal; white-space:... |
f7fd9f7d-88f7-4311-92f6-09de493871e5 | trentmkelly/LessWrong-43k | LessWrong | Dan Luu on "You can only communicate one top priority"
h/t to rpglover64 who pointed me towards this twitter thread in this comment.
Here's Dan Luu's take on what happens when orgs try to communicate nuanced priorities. (Related to my You Get About Five Words post)
> One thing it took me quite a while to understand... |
15fd71e8-f528-428b-9753-706dc4d94e73 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Yoshua Bengio: How Rogue AIs may Arise
[I think this is noteworthy, as Yoshua Bengio is a famous ML expert, and he presents his arguments for AI xrisk here. I copied the whole blogpost below.]
The rise of powerful AI dialogue systems in recent months has precipitated debates about AI risks of all kinds, wh... |
c1491a59-e1c1-4186-97a2-37670407efe4 | trentmkelly/LessWrong-43k | LessWrong | Group Rationality Diary, October 16-31
This is the public group instrumental rationality diary for October 16-31.
> 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... |
a4145029-e682-47b5-b1cb-9f1e0be1ed36 | trentmkelly/LessWrong-43k | LessWrong | 8 PRIME IDENTITIES
- An analisis
What is this about?
This project seeks to reduce the cognitive complexity involved in self-evaluating moments, goals, habits, and tasks among incarcerated individuals. I propose a discontinuous self-assessment system grounded in a model of eight intersecting identities.
With some par... |
66b000ae-9b58-45e4-9d56-c82bd9fbf569 | trentmkelly/LessWrong-43k | LessWrong | Action derivatives: You’re not doing what you think you’re doing
I want to look at a category of weird mental tricks that we sometimes play on ourselves—you might be familiar with the individual examples, but when considered together they reveal a pattern that I think deserves more attention. I’m going to do the Scott... |
dd9de003-2da1-4568-b4fb-941ae1adb15b | trentmkelly/LessWrong-43k | LessWrong | Moving Data Around is Slow
Data locality is a key part of writing fast data science code.
The core idea is simple: your data starts out in RAM (or disk), and to actually do anything useful with it, you need to move it to the CPU. This is actually pretty slow, so you want to minimize this transfer.
Say you have pairs... |
68c513a9-6c55-4f54-a75b-4fa3f37da676 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | [Event] Join Metaculus Tomorrow, March 31st, for Forecast Friday!
**Are you interested in how top forecasters predict the future? Curious how other people are reacting to the forecasts on Metaculus?... |
ef1b1ba2-76e6-4558-97f8-3dbc454f0b4f | trentmkelly/LessWrong-43k | LessWrong | Tentative tips for people engaged in an exercise that involves some form of prediction or forecasting
Note: This is the concluding post of my LessWrong posts related to my forecasting work for MIRI. There are a few items related to forecasting that I didn't get time to look into and might return to later. I might edit... |
c1ec2827-3a4c-40e6-8e11-d6086541c566 | trentmkelly/LessWrong-43k | LessWrong | [Crosspost] ACX 2022 Prediction Contest Results
Original here.
> Submission statement/relevance to Less Wrong: This forecasting contest confirmed some things we already believed, like that superforecasters can consistently outperform others, or the "wisdom of crowds" effect. It also found a surprising benefit of pred... |
468306c1-5058-4c84-9020-ea1a836db471 | trentmkelly/LessWrong-43k | LessWrong | The akrasia doom loop and executive function disorders: a question
There’s a lot of productivity advice on LW, or more specifically advice on how to beat procrastination and akrasia (see this one, this one, this one, this one, this one, this one, this one, this one, this one, … — all of those are pretty good and you s... |
6ec6dd89-77c6-402c-9ef9-e27f76d223d6 | trentmkelly/LessWrong-43k | LessWrong | Rational lies
If I were sitting opposite a psychopath who had a particular sensitivity about ants, and I knew that if I told him that ants have six legs then he would jump up and start killing the surrounding people, then it would be difficult to justify telling him my wonderful fact about ants, regardless of whether ... |
07f07c46-9a5e-4329-8202-ba48d8c780c3 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | The impact of whole brain emulation
At some point in the future we may be able to scan someone's brain at very high resolution and "run" them [on a computer](https://en.wikipedia.org/wiki/Mind_uploading). [1] When I first heard this as a teenager I thought it was interesting but not hugely important. Running people fa... |
6e3717d6-f862-41f5-836c-ec187b2d0f29 | trentmkelly/LessWrong-43k | LessWrong | The Self: Momentary vs Lifetime
When you think of the Self, do you imagine it as something growing and changing, or consistent over a person's life? The definition of the Self is arguably one of the biggest differences between classical and postmodern psychology. Classical theories have their basis in the idea of a Tr... |
ca164e63-42b2-41c1-a04c-b15b455c1bc1 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | AGI Predictions
I recommend [this LessWrong post](https://www.lesswrong.com/posts/YMokuZdoY9tEDHjzv/agi-predictions), which lets you make public predictions about various questions related to AI safety and AI timelines, and see existing predictions by other users. |
3fd0ce90-268a-4a93-a625-3ce15f37550b | trentmkelly/LessWrong-43k | LessWrong | When Anthropomorphism Became Stupid
It turns out that most things in the universe don't have minds.
This statement would have provoked incredulity among many earlier cultures. "Animism" is the usual term. They thought that trees, rocks, streams, and hills all had spirits because, hey, why not?
I mean, those lumps ... |
98c27e8d-cfa8-4cd5-b593-3e31de6aca2a | trentmkelly/LessWrong-43k | LessWrong | How to have a happy quarantine
As you may have noticed, things in the world are a bit cuckoo bananas right now. Social distancing is becoming increasingly widespread, which means that people are going to be experiencing social isolation at an unprecedented level. In this age of global connectedness, this seems really ... |
16e5ac62-ebe7-4966-8cfd-dfc2137f57c4 | trentmkelly/LessWrong-43k | LessWrong | Add "Meetups" to top navigation bar?
I think the impulse to promote all meetups was a good idea but now adding to much noise to the "PROMOTED" feed. Of the 10 "PROMOTED" feeds 8 are adverts for meetups.
I propose adding Meetups to the navigation bar and only adding them to "PROMOTED" when they are especially signific... |
19d5bbc0-ad1a-48cb-bff9-3acc576c292c | trentmkelly/LessWrong-43k | LessWrong | Air-gapping evaluation and support
This blog post was written fast to communicate a concept I think is important. I may edit this post for legibility later.
I think evaluation and support mechanisms should be somewhat “air-gapped,” or isolated, in their information-gathering and decision-making processes. The incenti... |
f20e4c91-689c-4b67-811c-5227e3e0f288 | trentmkelly/LessWrong-43k | LessWrong | The cone of freedom (or, freedom might only be instrumentally valuable)
Many policies with nontrivial points in their favour — as e.g. thorough environmental protection, public-dominant transportation, communal acoustic improvement — are swiftly rejected sith They Restrict Freedom, and People Value Freedom. (This obje... |
401fa9bb-dad6-4cf7-bfb3-d5663c700d25 | trentmkelly/LessWrong-43k | LessWrong | [Link] New SEP article on Bayesian Epistemology
The Stanford Encyclopedia of Philosophy has a brand new article on Bayesian Epistemology, replacing the previous entry on that topic.
https://plato.stanford.edu/entries/epistemology-bayesian/
Table of Contents:
* 1. A Tutorial on Bayesian Epistemology
* 1.1 A Case... |
04b20a76-8ade-4f3b-ac4c-6d578577b24c | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Does a LLM have a utility function?
There's a lot of discussion and research into AI alignment, almost always about variants of how to define/create a utility function (or meta-function, if it changes over time) that is actually aligned with ... something. That something is at least humanity's survival, but often som... |
ed32db43-372c-4928-b5fd-fea696ff1906 | trentmkelly/LessWrong-43k | LessWrong | The Neuroscience of Pleasure
The scientific approach to self-help suggests that a better understanding of who we are can help us achieve happiness and other goals. Most centrally, it will be helpful to understand our brains, because it is our brains that generate happiness and goals.
In particular, I'd like to explor... |
a5073cb4-c6cf-472e-995c-7d5ac585dd29 | trentmkelly/LessWrong-43k | LessWrong | Two meetups in Denver/Boulder Colorado
There will be a rationalist meetup in Denver tomorrow at 7:00 pm at Darcy's Pub, 4955 S Ulster St. #103 Denver, CO 80237
This Saturday I'll be giving a presentation on the control problem for superintelligent agents. It'll be from 2-4 at the Boulder Hacker Space, 1965 33rd St... |
e55dda7a-4f40-4746-8b8c-2034279499dc | trentmkelly/LessWrong-43k | LessWrong | New music powers
Original post: http://bearlamp.com.au/new-music-powers/
----------------------------------------
I have written before about how I am pretty terrible at canvassing music in my head. This lends to the appalling ability (to musically oriented people) to be able to do things like listen to the same so... |
f24e31f8-14ae-445b-abaf-ce0406ffb44d | StampyAI/alignment-research-dataset/arxiv | Arxiv | Towards Autonomous Grading In The Real World
I Introduction
---------------
Recent years have seen a dramatic rise in demand for automation in the construction industry. Bulldozers play a key role at most construction sites and are the go-to machinery for many tasks. While hand-operated bulldozing is a well establi... |
96c33a7b-e9f2-47a1-a839-5fc55e087fc0 | trentmkelly/LessWrong-43k | LessWrong | Meetup : MelbLW: November Social Meetup
Discussion article for the meetup : MelbLW: November Social Meetup
WHEN: 21 November 2014 06:30:00PM (+0800)
WHERE: Bull & Bear Tavern, 347 Flinders Lane, Melbourne
November's social meetup is scheduled for this Friday (21st November) as usual. This month, we will be trying o... |
01862099-5ddb-4058-9afb-69e4411a4723 | trentmkelly/LessWrong-43k | LessWrong | Large Language Models can Strategically Deceive their Users when Put Under Pressure.
Results of an autonomous stock trading agent in a realistic, simulated environment.
> We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strateg... |
38a2a92e-0955-4249-991e-8676e6ab95ee | trentmkelly/LessWrong-43k | LessWrong | The Rationalistsphere and the Less Wrong wiki
Hi everyone!
For people not acquainted with me, I'm Deku-shrub, often known online for my cybercrime research, as well as fairly heavy involvement in the global transhumanist movement with projects like the UK Transhumanist Party and the H+Pedia wiki.
For almost 2 years ... |
fb893b54-e1a7-449f-95a3-b813d70c13b9 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Compositional preference models for aligning LMs
*This post summarizes the main results from our recently released paper*[*Compositional preference models for aligning LMs*](https://arxiv.org/abs/2310.13011) *and puts them in the broader context of AI safety. For a quick summary of the paper, take a look at our*[*Twit... |
d7897363-924d-435f-8037-3958c162cc78 | trentmkelly/LessWrong-43k | LessWrong | Google and charity
They seem to have money they don't know what to do with.
This doesn't mean SIAI is a good match, but it might be worth thinking about.
I'd say the most obvious choice for google and existential threats would be (if feasible) applying cloud computing to watching for potential asteroid strikes. |
fd116c48-34a8-426b-be4f-63ed8a17638a | StampyAI/alignment-research-dataset/special_docs | Other | Risks of Astronomical Future Suffering
Risks of Astronomical Future Suffering
Brian Tomasik
Center on Long-Term Risk
brian.tomasik@longtermrisk.org
Abstract
It’s far from clear that human values will shape an Earth-based space-colonization wave, but even if
they do, it seems more likely that space colonization will incr... |
fb87158b-8932-4de8-8a58-00521ea8e178 | trentmkelly/LessWrong-43k | LessWrong | LessWrong Community Weekend 2023 Updates: Keynote Speaker Malcolm Ocean, Remaining Tickets and More
Update: Phase 2 closed on June 12th and results will be sent out on June 21st. You can still submit applications as there will be a small number of tickets remaining (including last minute cancellations) we will need to... |
945a8b50-6a73-4c0a-b812-7dc1a88ab739 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Stability AI releases StableLM, an open-source ChatGPT counterpart
Stability AI are the people behind Stable Diffusion.
Currently only 7B version is available, but they are currently training versions up to 65B, with 175B model planned. 7B version already seems to be quite capable.
Good for capabilities, but quite... |
ea342868-d1a1-45bf-9963-49491e616b36 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Durham HPMoR Discussion, chapters 15-17
Discussion article for the meetup : Durham HPMoR Discussion, chapters 15-17
WHEN: 17 November 2012 11:00:00AM (-0500)
WHERE: Foster's Market, 2694 Durham-Chapel Hill Blvd., Durham, NC
We will meet and discuss HPMoR, chapters 15-17 (approx 55 pages). Main discussion w... |
d8157ff7-dfbf-4fc9-b106-385b35f26161 | trentmkelly/LessWrong-43k | LessWrong | Monthly Shorts 8/21
Arts
Highlights from the stock phrase to start a fairytale in other languages
> Back in the days when it was still of help to wish for a thing —German
>
> Cross seven countries, through the sea of Operencia, through the glass mountains, where the curly-tailed pig delves —Hungarian
>
> I remember... |
62e6ef11-bc55-40f8-9211-4ae6057ab7d8 | trentmkelly/LessWrong-43k | LessWrong | Utility is unintuitive
EDIT: My original post was wrong. I will leave it quoted at the end for the purposes of preserving information, but it is now replaced with a new post that correctly expresses my sentiments. The original title of this post was "expected utility maximization is not rational".
As many people are ... |
1cbc9d87-0d4d-4cce-8492-974e90f2e7fc | trentmkelly/LessWrong-43k | LessWrong | Is there a guide to 'Problems that are too fast to Google'?
It seems to me like problems come in a variety of required response speeds, but there's a natural threshold to distinguish fast and slow: whether or not you can Google it. The slow ones, like getting an eviction notice from your landlord or a cancer diagnosis... |
dfd86cc3-b62c-4bc0-b32b-c12377131c61 | trentmkelly/LessWrong-43k | LessWrong | Don't fall for ontology pyramid schemes
Pyramid schemes work by ambiguating between selling a product, and selling shares in the profit from the sale of that product. It's a kind of sleight of hand that saves the shills from having to explicitly say "our company is valuable because other people think it's valuable", w... |
8b092f13-a1c4-42c4-96b3-b08e22e2a18f | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | The case for aligning narrowly superhuman models
*I wrote this post to get people’s takes on a type of work that seems exciting to me personally; I’m not speaking for Open Phil as a whole. Institutionally, we are very uncertain whether to prioritize this (and if we do where it should be housed and how our giving shoul... |
ea0725f7-8231-4abc-8c2e-fee7e6fb99f8 | trentmkelly/LessWrong-43k | LessWrong | Science like a chef
Alice: Hey honey, I made pasta with tomato sauce!
Bob: Great, let's eat!
Bob: Mmmmm, that's fantastic! It's even better than last time. It's got a sweeter, deeper flavor, which I like.
Alice: Thanks. Last time I only sautéed onions and garlic before adding the tomato puree, but this time I added... |
0f120da6-7582-4a08-a23d-ef8a6a93770e | trentmkelly/LessWrong-43k | LessWrong | AXRP Episode 10 - AI’s Future and Impacts with Katja Grace
YouTube link
This podcast is called AXRP, pronounced axe-urp and short for the AI X-risk Research Podcast. Here, I (Daniel Filan) have conversations with researchers about their papers. We discuss the paper and hopefully get a sense of why it’s been written a... |
9b577f51-344a-4b3a-863e-abbf323a08f3 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Ideal governance (for companies, countries and more)
*Cross-posted from [Cold Takes](https://www.cold-takes.com/ideal-governance-for-companies-countries-and-more/)*
*Click lower right to download or find on Apple Podcasts, Spotify, Stitcher, etc.*
I'm interested in the topic of **ideal governance:** what kind of g... |
fc7d401e-1055-4a93-b2a9-58e1830b69d3 | trentmkelly/LessWrong-43k | LessWrong | How To Raise Others’ Aspirations in 17 Easy Steps
Title taken from Tyler Cowen: The high-return activity of raising others’ aspirations
This is taken from a twitter thread (which I also wrote up on my website) that I was - aptly for the content - encouraged to put in non-Twitter places. Thanks for the encouragement!
... |
16b40986-f7b2-4251-84bd-cad30a69560b | trentmkelly/LessWrong-43k | LessWrong | Rationality Quotes 22
"Two roads diverged in the woods. I took the one less traveled, and had to eat bugs until Park rangers rescued me."
-- Jim Rosenberg
"Lying to yourself about specific actions is easier than re-defining the bounds of your imagined identity... When I see once-ethical men devolve into mor... |
242a63e1-a8d6-4740-8487-58c93c43700e | StampyAI/alignment-research-dataset/arbital | Arbital | Strategic AGI typology
A list of [advanced agent](https://arbital.com/p/2c) types, in classes broad enough to correspond to different *strategic scenarios* - AIs that can do different things, can only be built under different circumstances, or are only desirable given particular background assumptions. This typology ... |
c2b7c273-29a2-44a6-9379-94fc478669bf | trentmkelly/LessWrong-43k | LessWrong | Rationality and Cancer
Today, my dentist found a possible oral cancer.
I'm 31, a non-smoker, in good health. I know the research showing that doctors ignore base rates and overestimate your chances of cancer. (I asked the doctor the base rate, he didn't know.) I know that we grossly overprescribe biopsies and surgeri... |
c4bce85d-815e-48a9-a37b-c450bc302c03 | trentmkelly/LessWrong-43k | LessWrong | Beware Trivial Fears
Does the surveillance state affect us? It has affected me, and I didn't realize that it was affecting me until recently. I give a few examples of how it has affected me:
1. I was once engaged in a discussion on Facebook about Obama's foreign policy. Around that time, I was going to apply for a U... |
21e91725-c455-4669-a9fb-4553650a2a0f | StampyAI/alignment-research-dataset/arxiv | Arxiv | Evidence with Uncertain Likelihoods
Evidence with Uncertain Likelihoods
Joseph Y. Halpern
Cornell University
Ithaca, NY 14853 USA
halpern@cs.cornell.eduRiccardo Pucella
Cornell University
Ithaca, NY 14853 USA
riccardo@cs.cornell.edu
Abstract
An agent often has a number of hypotheses, and
mustchooseamongthembasedonobse... |
09f60003-aa1c-4e9c-89ed-8e1028ccdb70 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | How to pursue a career in technical AI alignment
**This guide is written for people who are considering direct work on technical AI alignment.** I expect it to be most useful for people who are not yet working on alignment, and for people who are already familiar with the arguments for working on AI alignment. If you ... |
fc447270-bf32-40c4-a3c1-dc08391b107d | trentmkelly/LessWrong-43k | LessWrong | Bikes and Babies
In MA, the only legal way [1] to travel by bike with a baby is with a trailer: they're still too floppy for a child bike seat and the law doesn't consider options involving the box of a cargo bike. Since they're so small, you can use a car seat to make sure they're properly supported and protected.
W... |
add7c8b7-0600-4bee-9b42-d76f46744970 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Atlanta December Meetup - Game Night!
Discussion article for the meetup : Atlanta December Meetup - Game Night!
WHEN: 27 December 2014 07:00:00AM (-0500)
WHERE: 2388 Lawrenceville Highway Unit L, Norgate Manor, Decatur, GA 30033
Come join us for a get together! We'll be playing games and having a low key s... |
11ea7470-c766-4611-9cbb-343c10b8a90e | trentmkelly/LessWrong-43k | LessWrong | Contrived evaluations are useful evaluations
Anthropic released research today showing that carefully designed prompts can elicit blackmail, corporate espionage, and other harmful strategic behaviors from AI models across the industry. The researchers placed AI models in corporate scenarios where they had access to se... |
e4767a79-6e36-47c7-aac3-f42c4f2ab006 | trentmkelly/LessWrong-43k | LessWrong | Covid 7/1: Don’t Panic
The case numbers this week were clearly bad news. The raw count was somewhat bad news, and the positive test percentage increase was very bad news. It would be easy to treat the whole shift as fully ‘real,’ attribute it all to Delta, and panic.
I do not think that is the correct interpretation... |
f9a8e4d7-86ba-4567-b1b4-af3139d1af32 | trentmkelly/LessWrong-43k | LessWrong | Paradigm-building from first principles: Effective altruism, AGI, and alignment
Introduction
If we are interested in the theoretical foundations that motivate work in AGI safety research, it seems worthwhile to clarify the philosophical and practical relationships of big-picture ideas in effective altruism (EA) to AGI... |
d027a7bb-16f7-46d7-8cd4-c3711c3063c2 | trentmkelly/LessWrong-43k | LessWrong | How do you improve the quality of your drinking water?
Water quality can have surprisingly high impact on QoL (just as air purifiers can significantly improve QoL), and some steps (like getting the right pitcher have very high return on time/attention invested). There still isn't a LW thread on water quality so I'll p... |
2ccd6ea6-a249-4f73-9892-b04a6dba64ec | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | Oxford professor on Transcendence: how could you get a machine intelligence?
one can also ask how could we get there
like what are the possible paths that
could take us from ariana
to human level machine intelligence in
the movie it occurs
through uploading a person and
they've done previous experiments on a
macaque m... |
e6efa313-800d-4376-8472-d57de8d5f4af | trentmkelly/LessWrong-43k | LessWrong | Turning Your Back On Traffic
We do a lot of walking around the neighborhood with kids, which usually involves some people getting to intersections a while before others. I'm not worried about even the youngest going into the street on their own—Nora's been street trained for about a year—but we have to be careful abou... |
3d4afc35-2400-41c7-b9fe-22a89796c7af | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Bayesian Evolving-to-Extinction
*The present discussion owes a lot to Scott Garrabrant and Evan Hubinger.*
In [Defining Myopia](https://www.alignmentforum.org/s/HeYtBkNbEe7wpjc6X/p/qpZTWb2wvgSt5WQ4H), I formalized *temporal* or *cross-instance* myopia / non-myopia, but I claimed that there should also be some kind o... |
b81b356d-0b32-4963-a093-f24db5b0099c | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | AI Impacts Quarterly Newsletter, Jan-Mar 2023
News
====
### AI Impacts blog
We moved our [blog](https://blog.aiimpacts.org/) to Substack! We think this platform has many advantages, and we’re excited for the blog to live here. You can now easily [subscribe](https://blog.aiimpacts.org/subscribe) to the blog to receiv... |
3434101a-5b9d-44f1-b022-305f76298020 | trentmkelly/LessWrong-43k | LessWrong | Memory Decoding Journal Club: Systems consolidation reorganizes hippocampal engram circuitry
Join Us for the Memory Decoding Journal Club!
A collaboration of the Carboncopies Foundation and BPF Aspirational Neuroscience
This time, we’re diving into a groundbreaking paper:
"Systems consolidation reorganizes hippocam... |
8e14b507-c667-4adf-80dd-29ac2a21015c | trentmkelly/LessWrong-43k | LessWrong | [Fiction] IO.SYS
https://www.datapacrat.com/IO.SYS.html
----------------------------------------
IO.SYS
BY DATAPACRAT
----------------------------------------
If this has all been a VR, I’d like to be connected to reality when I wake up, please.
----------------------------------------
I lived around the tur... |
1a5d69bb-f0da-4732-80bd-8d4f149b9d9a | trentmkelly/LessWrong-43k | LessWrong | How can guesstimates work?
[Epistemic status: background is very hand-wavy, but I'd rather post a rough question than no question at all. I'm very confident that the two ingredients -- illegible cultural evolution and guesstimation -- are real and important things. Though the relation between the two is more uncertain... |
1e9e8576-369f-489b-8464-335f11a6d4dd | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | [Link] Training Compute-Optimal Large Language Models
New LM scaling paper from DeepMind ([abs](https://arxiv.org/abs/2203.15556), [pdf](https://arxiv.org/pdf/2203.15556.pdf)).
Abstract (my emphasis):
> We investigate the optimal model size and number of tokens for training a transformer language model under a gi... |
4d3ade07-7d41-47c1-9804-4f61a73299d3 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | AI as a Civilizational Risk Part 5/6: Relationship between C-risk and X-risk
The general model presented in the previous parts suggests that the US and potentially other parts of the world will suffer some form of civilizational collapse, potentially as early as 10 years from now. In the absence of decisive action to... |
89b9fabd-a960-4021-b51b-6a6403bbfa38 | trentmkelly/LessWrong-43k | LessWrong | An attempt to steelman OpenAI's alignment plan
I don't actually think my attempted steelman is what they currently have in mind, this isn't an attempted Intellectual Turing Test. I take more hope from the resources they are committing to the project and their declared willingness to change their minds as they go t... |
5e20b644-4c7b-434e-bf0b-7453a572f3e7 | trentmkelly/LessWrong-43k | LessWrong | Looking for an intuitive explanation of expected outcome
I'll first explain how I see expected outcome, because I'm not sure my definition is the same as the widely accepted definition.
If I have 50% chance to win 10$, I take it as there are two alternative universes, the only difference being that in one of them, I ... |
39d6f4f8-cb48-4299-bfb6-f8f7e9dc683a | trentmkelly/LessWrong-43k | LessWrong | Is LessWrong dying?
An old joke;
"What bar should we go to?"
"Oh, I like Bar X"
"No-one goes there anymore, it's too crowded"
I suspect that LessWrong is getting too crowded for many people to come here. We're well above Dunbar's number, and most of us can't get to know the other active users without a large in... |
d76f50f8-61d6-4ae0-904c-17c97601472e | trentmkelly/LessWrong-43k | LessWrong | A model of decision-making in the brain (the short version)
(UPDATE: For a revised-and-improved version of this post, see this later post I wrote (especially Section 6.2.2).)
I’ve been playing around with a hypothesis about how decision-making is laid out in the human brain. Regular readers of my posts have seen this... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.