id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
576ca786-602b-4902-90b0-9bcb2b8939ea | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | [ASoT] Some thoughts about LM monologue limitations and ELK
*Editor’s note: I’m experimenting with having a lower quality threshold for just posting things even while I’m still confused and unconfident about my conclusions, but with this disclaimer at the top. Thanks to Kyle and Laria for discussion.*
One potential w... |
255473a1-632d-40a1-b05e-89f8d7919cc5 | trentmkelly/LessWrong-43k | LessWrong | Primitive Perspectives and Sleeping Beauty
This is another attempt to promote my solution to anthropic paradoxes (perspective-based reasoning, PBR).
I propose the first-person perspective shall be considered a primitive axiomatic fact. "I naturally know I am this particular person, yet there is no underlying reason f... |
63457c8f-7df6-406a-a511-dc2d768152d8 | trentmkelly/LessWrong-43k | LessWrong | Parasocial relationship logic
If:
1. You become like the five people you spend the most time with (or something remotely like that)
2. The people who are most extremal in good ways tend to be highly successful
Should you try to have 2-3 of your five relationships be parasocial ones with people too successful to b... |
606e1df8-fef0-4d22-8501-b8c8826d00d9 | trentmkelly/LessWrong-43k | LessWrong | Reasons to act according to the free will paradigm?
Hi, probably a newbie question for many of you, but I have some thoughts I'd like to verify publicly. My text presents two potential reasons to act according to the free will paradigm (not to believe blindly nor say it's true). Points are divided by "horizontal line"... |
d54e6d43-3410-4472-a9b1-2855d134a5ca | trentmkelly/LessWrong-43k | LessWrong | In favour of a sovereign state of Gaza
Sorry if this isn't the kind of content people want to see here. It's my regular blogging platform, so it's where I go by default when I have something I want to get off my chest, but happy to delete if that's the consensus.
Bias warning: I am Jewish and live in Israel.
The Isr... |
5fd4cc6b-8686-4209-9d5e-82614e91c1e9 | trentmkelly/LessWrong-43k | LessWrong | Meetup : San Francisco Meetup: Short Talks
Discussion article for the meetup : San Francisco Meetup: Short Talks
WHEN: 03 August 2015 06:15:00PM (-0700)
WHERE: 1061 Market St #4, San Francisco, CA 94103
We'll be meeting to give/listen to short talks. Planning isn't necessary: these are not expected to be polished.
... |
62034567-72b9-4b13-a291-a3cf51b1a96f | trentmkelly/LessWrong-43k | LessWrong | How I'd like alignment to get done (as of 2024-10-18)
Preamble
My alignment proposal involves aligning an encoding of human-friendly values and then turning on a self-improving AGI with that encoding as its target. Obviously this involve "aligning an encoding of human-friendly values" and also "turning on a self-impro... |
625643d5-d550-4485-bd0a-b53585073638 | StampyAI/alignment-research-dataset/arbital | Arbital | Executable philosophy
"Executable philosophy" is [https://arbital.com/p/+2](https://arbital.com/p/+2)'s term for discourse about subjects usually considered to belong to the realm of philosophy, meant to be applied to problems that arise in designing or [aligning](https://arbital.com/p/2v) [machine intelligence](https... |
57fe0df1-c37f-46af-8a36-a47fcbb99eb2 | trentmkelly/LessWrong-43k | LessWrong | [Linkpost] Interpretability Dreams
A brief research note by Chris Olah about the point of mechanistic interpretability research. Introduction and table of contents are below.
----------------------------------------
Interpretability Dreams
An informal note on the relationship between superposition and distributed r... |
91908ecb-2b05-45f7-b95a-c20849d0ae33 | trentmkelly/LessWrong-43k | LessWrong | Programmatic Prediction markets
I have a problem with "prediction markets" as news view. They just aren't informative enough.
If the price of oil goes down is that due to: A reduction in demand. an increase in supply, a large amount of investors finding a better investment or a large amount of investors wanting cash ... |
223d5a03-07af-4aa9-90a3-df9aa6598795 | trentmkelly/LessWrong-43k | LessWrong | AI #85: AI Wins the Nobel Prize
Both Geoffrey Hinton and Demis Hassabis were given the Nobel Prize this week, in Physics and Chemistry respectively. Congratulations to both of them along with all the other winners. AI will be central to more and more of scientific progress over time. This felt early, but not as early ... |
82ff94da-12cc-42dc-b529-31d321a11dfb | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | Isn't the real concern autonomous weapons?
Some fear that the deployment of [lethal autonomous weapons](https://en.wikipedia.org/wiki/Lethal_autonomous_weapon) could be very bad for humanity. This can be considered a type of [misuse](/?state=9B85&question=Isn't%20the%20real%20concern%20misuse%3F) of AI.
Intuitively, ... |
fc26743a-4a4d-4a17-8ecf-e77f2547f2e0 | trentmkelly/LessWrong-43k | LessWrong | A plausible story about AI risk.
This was originally supposed to be a response to the new AGI Safety FAQ-in-progress, but it got a bit too long. Anonymous writes:
> A lot of the AI risk arguments seem to come... with a very particular transhumanist aesthetic about the future (nanotech, ... etc.). I find these thing... |
99c5dcb4-e83c-496b-bdee-929d7f22fd71 | trentmkelly/LessWrong-43k | LessWrong | 12020: a fine future for these holidays
To celebrate all the possibilities of humanity during these holidays, have a possible calendar of the year 12020 of the human era (link to full calendar here).
Minor fact: in the Gregorian calendar, the days of the week cycle exactly every 400 years, so the non-time-travellers ... |
7d974ecb-3246-4489-b1d6-8f8049d24143 | trentmkelly/LessWrong-43k | LessWrong | Why I don't believe in doom
In my previous very divisive post I was said more than once that I was being downvoted because I was not providing any arguments. This is an attempt to correct that and to expand on my current model of doom and AGI. I think it can be more clear in the form of a Q and A
Q: First, what are y... |
970f8e39-2b0a-4966-b5d2-b7b73016532a | StampyAI/alignment-research-dataset/arxiv | Arxiv | Constrained Policy Optimization
1 Introduction
---------------
Recently, deep reinforcement learning has enabled neural network policies to achieve state-of-the-art performance on many high-dimensional control tasks, including Atari games (using pixels as inputs) (Mnih et al., [2015](#bib.bib16), [2016](#bib.bib17)... |
c17a3afc-33d2-43e2-b0ef-cf151c4e8415 | trentmkelly/LessWrong-43k | LessWrong | Surfing Uncertainty: Prediction, Action, and the Embodied Mind - The Future of Prediction
|
57e74320-8ec5-4c2f-bbb0-4feb930c6f88 | trentmkelly/LessWrong-43k | LessWrong | EA & LW Forums Weekly Summary (24 - 30th Oct 22')
Supported by Rethink Priorities
This is part of a weekly series - you can see the full collection here. The first post includes some details on purpose and methodology.
If you'd like to receive these summaries via email, you can subscribe here.
Podcast version: pref... |
81e6ee92-df73-4fe2-a3a6-56637af9f115 | trentmkelly/LessWrong-43k | LessWrong | Taking Ideas Seriously is Hard
Most people don’t practice taking ideas seriously. I think it’s because most people don’t know how to. I didn’t either, until I stumbled upon an implication.
For example, what would it mean to take compounding seriously?
Ugh. I can feel your aversion. You’ve already heard so much about... |
a467ae43-f0f0-4e21-a2d9-9c65495954c2 | trentmkelly/LessWrong-43k | LessWrong | Expectation-Based Akrasia Management
I'd been staying out of anti-akrasia discussion mostly because my strategy for getting things done is so different from the common one that it barely seems related, much less relevant. I've been asked, though, so here's what I have to say about it.
One of the main premises in how ... |
d6d21afc-12b5-4497-bb55-ecbe400ecbd2 | trentmkelly/LessWrong-43k | LessWrong | Utopianism
Freedom is the ability to act on a goal, a desire, to not be constrained by the world one lives in. One could formulate freedoms to life, to property, to information, to expression. Universal Declaration of Human Rights highlights 30 articles detailing rights that should at no circumstances be infringed upo... |
d00b880f-539f-47d6-b41c-186becfb1aaa | trentmkelly/LessWrong-43k | LessWrong | Can dying people "hold on" for something they are waiting for?
content note: death, old age, sickness
I've heard numerous anecdotal accounts of sick or old people who are on death's door "holding on" in a way suggestive that they were exerting some effort to do, until they had reached closure on some thing (a relativ... |
2dc7108f-1171-442c-839c-7d70f5c72600 | trentmkelly/LessWrong-43k | LessWrong | [Link] You May Already Be Aware of Your Cognitive Biases
From the article:
> Using an adaptation of the standard 'bat-and-ball' problem, the researchers explored this phenomenon. The typical 'bat-and-ball' problem is as follows: a bat and ball together cost $1.10. The bat costs $1 more than the ball. How much does th... |
69af21da-1269-4461-94dc-12e91d7c6537 | StampyAI/alignment-research-dataset/arbital | Arbital | AI safety mindset
summary(Brief): Thinking about [safely](https://arbital.com/p/2l) building [agents smarter than we are](https://arbital.com/p/2c) has a lot in common with the standard mindset prescribed for computer security. The experts first ask how proposals fail, rather than arguing that they should succeed.
... |
704b9f8e-e251-4631-ad03-ab5ad1c35f19 | StampyAI/alignment-research-dataset/blogs | Blogs | 2014 Summer Matching Challenge!
Thanks to the generosity of several major donors,† every donation made to MIRI between now and August 15th, 2014 will be **matched dollar-for-dollar**, up to a total of $200,000!
$0
... |
cfb53f47-174d-406d-8610-2477b3d3b0a1 | trentmkelly/LessWrong-43k | LessWrong | Game Theory As A Dark Art
One of the most charming features of game theory is the almost limitless depths of evil to which it can sink.
Your garden-variety evils act against your values. Your better class of evil, like Voldemort and the folk-tale version of Satan, use your greed to trick you into acting against your ... |
b609d620-1fdb-4727-b0ae-dcf113a4b49d | StampyAI/alignment-research-dataset/arbital | Arbital | P vs NP
The greatest currently open problem in complexity theory and computer science in general, which talks about the relationship between the class of efficiently solvable problems, [$P$](https://arbital.com/p/), and the class of problems with easily checkable solutions, [$NP$](https://arbital.com/p/).
It is a bas... |
e67d2dd2-a8b8-4104-acf6-0dbe76145bbe | trentmkelly/LessWrong-43k | LessWrong | Relative Value Functions: A Flexible New Format for Value Estimation
Summary
Quantifying value in a meaningful way is one of the most important yet challenging tasks for improving decision-making. Traditional approaches rely on standardized value units, but these falter when options differ widely or lack an obvious sh... |
fa42ed9d-9f77-4aae-b0ad-9fb36fec87ec | trentmkelly/LessWrong-43k | LessWrong | Trust and The Small World Fallacy
When people encounter other people they recognize, they exclaim "small world!"
I suspect that most people have 300 acquaintances or less. I probably have under 100. Still, sometimes I run into people I know and I'm tempted to say "small world".
But it's not actually a small world, i... |
3ee0768c-8fb8-4ab8-b8a7-05a2f876c028 | trentmkelly/LessWrong-43k | LessWrong | Why don’t we treat geniuses like professional athletes?
I mean in the work-environment sense, rather than the celebrity-and-endorsement-deals sense.
A professional sports team gets a lot of benefits that are designed to keep physically talented people performing at their peak. They have support for things like recove... |
45c5c275-16e3-49a7-bc6f-617c714573a0 | StampyAI/alignment-research-dataset/arbital | Arbital | Rational arithmetic all works together
We have seen [what the rational numbers are](https://arbital.com/p/4zx), and five things we can do with them:
- [addition](https://arbital.com/p/55m)
- [subtraction](https://arbital.com/p/56x)
- [multiplication](https://arbital.com/p/59s)
- [division](https://arbital.com/p/5jd)
... |
a7e53122-a391-4cea-8a4b-2a01c5876cf0 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | ‘We Must Slow Down the Race’ – X AI, GPT 4 Can Now Do Science and Altman GPT 5 Statement
there were several significant
developments in the last few days linked
to gbt4 and openai I could honestly have
done a video on each of them but
realized that it might be better to do a
single video tracing a single article
cove... |
3f336281-2a27-478f-b74e-58b414de3c9d | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Beginning resources for CEV research
I've been working on [metaethics/CEV research](http://wiki.lesswrong.com/wiki/No-Nonsense_Metaethics) for a couple months now (publishing mostly [prerequisite](http://wiki.lesswrong.com/wiki/Intuitions_and_Philosophy) [material](/lw/4z7/the_neuroscience_of_desire/)) and figured I'd... |
22be3a6c-df6a-4f0b-aee9-6a2cd4efba0d | trentmkelly/LessWrong-43k | LessWrong | GPT-175bee
Epistemic status: whimsical
Bees: a new unit of measurement for ML model size
Talking about modern ML models inevitably leads to a bunch of hard-to-intuit large numbers, especially when it comes to parameter count.
To address this, we propose that we adopt a new, human-friendly unit to measure the number... |
5ed1a42d-5288-478a-b78c-1cacd566c989 | trentmkelly/LessWrong-43k | LessWrong | "No evidence" as a Valley of Bad Rationality
Quick summary of Doctor, There are Two Kinds of “No Evidence”:
* Author has a relative with cancer. Relative is doing well after chemo and is going to a doctor to see if it's worth getting more chemo to kill the little extra bits of cancer that might be lingering.
* Doct... |
7f9d07be-b8ae-4cff-bac7-d619f9d8e717 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | MAKE IT BETTER (a poetic demonstration of the banality of GPT-3)
[Source](https://www.thetimes.co.uk/article/will-the-robot-who-can-mimic-shakespeare-make-authors-obsolete-z5blrsk9g)==========... |
e4685cf3-470e-4e35-a110-4ba22992f096 | StampyAI/alignment-research-dataset/arbital | Arbital | Utility
In the context of value alignment theory, 'Utility' always refers to a goal held by an artificial agent. It further implies that the agent is a [consequentialist](https://arbital.com/p/9h); that the agent has [probabilistic](https://arbital.com/p/) beliefs about the consequences of its actions; that the agent... |
f969e8e2-1e46-495c-82a4-7e5ca6058b55 | trentmkelly/LessWrong-43k | LessWrong | Neural nets designing neural nets
|
2e4b2bdf-cb29-4d04-9605-fe34829447e5 | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post1690
YouTube link Sometimes, people talk about making AI systems safe by taking examples where they fail and training them to do well on those. But how can we actually do this well, especially when we can’t use a computer program to say what a ‘failure’ is? In this episode, I speak with Daniel Ziegler about hi... |
65fefcc1-a18f-4d09-8508-3e13ea0c1014 | trentmkelly/LessWrong-43k | LessWrong | Is January AI a real thing?
Does anyone have experience or information about continuous glucose monitoring from "January AI"? https://january.ai/?utm_source=GoogleSearchNetwork&utm_campaign=12001902471&utm_content=121683842811&utm_term=492950869595&utm_medium=continuous glucose monitoring system-b&gclid=Cj0KCQjwl9GCBh... |
6c4ee31e-6c59-4a68-9352-ce0cfc4b82b9 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | "Safety Culture for AI" is important, but isn't going to be easy
This is a linkpost (to the EA forum version of this post, which is) for [a new preprint, entitled "Building a Culture of Safety for AI: Perspectives and Challenges,"](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4491421) and a brief explanation of... |
84d44075-cdd7-4fc1-9fe6-67b05830ebda | trentmkelly/LessWrong-43k | LessWrong | Why multi-agent safety is important
Alternative Title: Mo’ Agents, Mo’ Problems
This was a semi-adversarial collaboration with Robert Kirk; views are mostly Akbir’s, clarified with Rob’s critiques.
Target Audience: Machine Learning researchers who are interested in Safety and researchers who are focusing on Single ... |
5de2e2a2-bf15-4e1b-ab3f-a205ce0be4ec | trentmkelly/LessWrong-43k | LessWrong | Humans are not automatically strategic
Reply to: A "Failure to Evaluate Return-on-Time" Fallacy
Lionhearted writes:
> [A] large majority of otherwise smart people spend time doing semi-productive things, when there are massively productive opportunities untapped.
>
> A somewhat silly example: Let's say someone aspi... |
83854858-bf83-4294-9ae3-729a5f05dc61 | trentmkelly/LessWrong-43k | LessWrong | Overcoming suffering: Emotional acceptance
Follow-up to: Suffering as attention-allocational conflict.
In many cases, it may be possible to end an attention-allocational conflict by looking at the content of the conflict and resolving it. However, there are also many cases where this simply won't work. If you're afra... |
dd26ddd8-2711-4e58-bbc7-5d06c798d50f | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Agency and the unreliable autonomous car
*Financial status: This is independent research, now supported by a grant. I welcome* [*financial support*](https://www.alexflint.io/donate.html)*.*
*Epistemic status: I believe ~85% that the technical argument presented in this piece is correct.*
---
Outline
-------
... |
6650464a-beb8-4d0a-9b62-5e98b4030ea7 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Value is Fragile
Today's post, Value is Fragile was originally published on 29 January 2009. A summary (taken from the LW wiki):
> An interesting universe, that would be incomprehensible to the universe today, is what the future looks like if things go right. There are a lot of things that humans value... |
ec0a6eff-0964-4223-a257-7d15d06ec667 | trentmkelly/LessWrong-43k | LessWrong | The Value of Not Being an Imposter
Imagine that you are in a field filled with imposters.
* Perhaps you are a doctor or nurse who truly cares about the wellbeing of your patients, and you're in a mismanaged hospital where most doctors do little to no good at all.
* Perhaps you are a passionate software engineer i... |
2826da8c-1f2b-401f-b55e-61c60cf53be4 | trentmkelly/LessWrong-43k | LessWrong | Rapid Test Throat Swabbing?
Back in January there was a bunch of buzz around using standard rapid tests but swabbing the throat. Ex:
> On one side are well-regarded experts who argue that swabbing your throat in addition to your nose may increase the chances that a home test can detect omicron. On the other side are ... |
8fe2451b-4cfc-4d19-ac88-21eeee092918 | trentmkelly/LessWrong-43k | LessWrong | Robin Hanson’s latest AI risk position statement
“While I’ve written on this many times before, it seems time to restate my position.”
“While I agree that this is a logically possible scenario, not excluded by what we know, I am disappointed to see so many giving it such a high credence, given how crazy far it seems ... |
6e5b1ee3-32ba-4cca-b957-b7f7e50f1884 | trentmkelly/LessWrong-43k | LessWrong | Some of the most important entrepreneurship skills are tacit knowledge
Cross-posted from Future Startup.
Tacit knowledge or implicit knowledge—as opposed to formal, codified, or explicit knowledge—is knowledge that is difficult to express or extract, and thus more difficult to transfer to others by means of writing i... |
589fa364-eb83-45c4-9cc1-1796f615b8c7 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Based on a comment I made on this EA Forum Post on Burnout. Related links: Sabbath hard and go home, Bring Back the SabbathThat comment I made generated more positive feedback than usual (in that people seemed to find it helpful to read and found themselves thinking about it months after reading it), so I'm elevating ... |
f4e2bf41-e5d9-4851-b3c4-64a56f918055 | trentmkelly/LessWrong-43k | LessWrong | The Witness
“What are the roots that clutch, what branches grow
Out of this stony rubbish? Son of man,
You cannot say, or guess, for you know only
A heap of broken images-”
I wake up, feeling a strange sense of restlessness. I’m not sure why, but it's impossible to lounge around in bed like I usually do. So I get cha... |
78a34d72-1823-408e-aab6-1ef6b291bafa | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | A freshman year during the AI midgame: my approach to the next year
I recently spent some time reflecting on my career and my life, for a few reasons:
* It was my 29th birthday, an occasion which felt like a particularly natural time to think through what I wanted to accomplish over the course of the next year 🙂.
* ... |
b6840ee4-e0ec-4cd8-b61a-ccfb34be3660 | trentmkelly/LessWrong-43k | LessWrong | Considerations on Compensation
This post was prompted by the recent announcement of Lightcone Infrastructure, and particularly Elizabeth's response in a comment thread on compensation. I'd like to thank Max Wallace, Ruby, and Miranda Dixon-Luinenburg for their comments and copyediting.
Context (& disclaimer): I'm a ... |
d773f464-e8d0-4b85-b08f-39cad72b78d3 | trentmkelly/LessWrong-43k | LessWrong | What do we know about vaccinating children?
In Germany, the BioNTech vaccine has been approved for children:
> At the end of May, the Comirnaty mRNA vaccine developed by BioNTech / Pfizer was approved by the European Medicines Agency (EMA) as the first COVID-19 vaccine in this age group for children and adolescents a... |
79974d2e-3a63-41fe-a240-67f77c2dcc4a | trentmkelly/LessWrong-43k | LessWrong | To the average human, controlled AI is just as lethal as 'misaligned' AI
A few months ago I posted this understated short piece proposing, in a nutshell, that the average person has at least as much to fear from perfectly controlled advanced AI as they would from so-called 'misaligned' AI, because if automation can em... |
3aaf29d0-eb4a-46ad-8ec6-ef2bb72f7e5f | trentmkelly/LessWrong-43k | LessWrong | What was your reasoning for deciding whether to raise children?
To answer anonymously, you can write on my Admonymous and I will share the answer here |
61add69e-2c94-4eba-b8fc-c10d20576f48 | trentmkelly/LessWrong-43k | LessWrong | My day in 2035
I wake up as usual by immediately going on my phone. I reply to some of my messages - yes dad, the solar installation you have at the villa could be redundant soon, but again, it can still benefit them (even if slightly) if you comply and let them integrate it into the new grid. A grid which operates on... |
88736859-1de9-477b-9981-4659f4fad057 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | Apply to Study AI Safety Now! #shorts
after an investigation of gpg4 AI
researchers at Microsoft suggested that
the language model along with others
like charge EBT and Google's Palm could
be considered an early form of
artificial general intelligence with GPT
4's ability to solve complex tasks
across domains such as ... |
aa92ab53-1df5-4ca5-aed9-36f89e34a884 | trentmkelly/LessWrong-43k | LessWrong | Janet must die
This is a reaction to Zvi's post https://www.lesswrong.com/posts/KL2BqiRv2MsZLihE3/going-nova
The title of this post references this scene from The Good Place:
Disclaimer: I am generally pretty sanguine about the standard AI-borne x-risks. But "Going Nova" is a different issue, a clear and present d... |
3eb5c8da-f355-4887-b6f0-1e76525c245b | trentmkelly/LessWrong-43k | LessWrong | Signaling Strategies and Morality
I am far from convinced that people in general wish to be seen as caring more about morality than they actually do. If this was the case, why would the persistent claim that people are -- and, logically, must be -- egoists have so long survived strong counter-arguments? The argument... |
a28847ef-703a-46ad-9108-aca965fd43c7 | trentmkelly/LessWrong-43k | LessWrong | Worlds Where Iterative Design Fails
In most technical fields, we try designs, see what goes wrong, and iterate until it works. That’s the core iterative design loop. Humans are good at iterative design, and it works well in most fields in practice.
In worlds where AI alignment can be handled by iterative design, we p... |
e53e16b6-0125-450c-93e3-c9587be939af | trentmkelly/LessWrong-43k | LessWrong | How I Think, Part One: Investing in Fun
First of all, these blog posts are just going to be dump pages for my brain. I'm not going to worry about editing them or making sure they will be useful to people who read them. I'm going to try not to care about using professional language or anything like that. Okay, here we ... |
5b59103d-a217-42bf-a63e-a87127fc02f3 | trentmkelly/LessWrong-43k | LessWrong | The Statistician's Fallacy
[Epistemic status | Contains generalization based on like three data points.]
In grad school, I took a philosophy of science class that was based around looking for examples of bad reasoning in the scientific literature. The kinds of objections to published scientific studies we talked abou... |
e0654f9d-2f8e-473e-a78b-666d5864e919 | trentmkelly/LessWrong-43k | LessWrong | Nature: Red, in Truth and Qualia
Previously: Seeing Red: Dissolving Mary's Room and Qualia, A Study of Scarlet: The Conscious Mental Graph
When we left off, we'd introduced a hypothetical organism called Martha whose actions are directed by a mobile graph of simple mental agents. The tip of the iceberg, consisting o... |
c108dcac-7058-44a0-a78b-c3fd3d7a7459 | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | What are language models?
Language models are computer programs made to estimate the likelihood of a piece of text. "Hello, how are you?" is likely. "Hello, fnarg horses" is unlikely.
Language models can answer questions by estimating the likelihood of possible question-and-answer pairs, selecting the most likely que... |
7ce4294b-0c27-4128-9a31-15d95e95387a | trentmkelly/LessWrong-43k | LessWrong | The beginnings of a test for Rationality Quotient
In their 2011 chapter for the Cambridge Handbook of Intelligence, Stanovich et al. review the evidence suggesting that intelligence and rationality are not the same thing and that rationality is often more important than intelligence. They then lament the fact that the... |
318d552b-b1a7-4e06-baad-2d3bb4380a0f | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Does agency necessarily imply self-preservation instinct?
I have recently read some blog posts ([this](https://slatestarcodex.com/2019/08/27/book-review-reframing-superintelligence/), [this](https://www.lesswrong.com/posts/sizjfDgCgAsuLJQmm/reply-to-holden-on-tool-ai) and [this](https://gwern.net/tool-ai)) about tool ... |
882e4e57-80a5-4094-b8ee-2fd0e56eac19 | trentmkelly/LessWrong-43k | LessWrong | Dynamics Crucial to AI Risk Seem to Make for Complicated Models
This post overlaps with our recent paper Extinction Risk from AI: Invisible to Science?.
tl;dr: In AI safety, we are worried about certain problems with using powerful AI. (For example, the difficulty of value specification, instrumental convergence, and... |
124f8120-c477-4862-8b7d-4f2772fd805d | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Oracles: reject all deals - break superrationality, with superrationality
.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... |
cf23e86e-fd97-4d24-a4da-0355d4e4c43d | trentmkelly/LessWrong-43k | LessWrong | Points of Departure
Followup to: Anthropomorphic Optimism
If you've watched Hollywood sci-fi involving supposed robots, androids, or AIs, then you've seen AIs that are depicted as "emotionless". In the olden days this was done by having the AI speak in a monotone pitch - while perfectly stressing the syllables, of ... |
be4ee8ea-de6c-4743-9575-1d5cf359c6ce | trentmkelly/LessWrong-43k | LessWrong | New LW Meetup: Cologne
This summary was posted to LW Main on March 13th. The following week's summary is here.
New meetups (or meetups with a hiatus of more than a year) are happening in:
* [Basel] Effective Altruism Meetup Switzerland: 21 March 2015 06:00PM
* [Cologne] HPMOR wrap party cologne / Cologne LW meetup... |
ed64d96e-6dd8-4568-a98f-588d3df3526e | trentmkelly/LessWrong-43k | LessWrong | On the role of abstraction in mathematics and the natural sciences
I'm a mathematics undergraduate in the UK, in my final year, and I have been thinking a lot about Platonism. I largely find myself completely unconvinced by attempts to naturalise the metaphysics behind the ontology of mathematical objects, though I am... |
76bb0847-2ac8-42e2-962b-eef14a6c01d0 | trentmkelly/LessWrong-43k | LessWrong | Kids and Time
Note: this is written about normal times. With the pandemic closing schools and daycares a lot of parents have far less time than usual, and while we're lucky that this has not affected us it's not what I'm looking at this here.
When I compare my life before and after kids, the biggest change is probabl... |
cd1f4594-2e06-4458-bf6c-d73baf801b68 | trentmkelly/LessWrong-43k | LessWrong | Conspiracy Theories as Agency Fictions
Related to: Consider Conspiracies, What causes people to believe in conspiracy theories?
Here I consider in some detail a failure mode that classical rationality often recognizes. Unfortunately nearly all heuristics normally used to detect it seem remarkably vulnerable to misfir... |
a294bede-1e37-4675-ac19-d2b81382a814 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Would you join the Society of the Free & Easy?
> Summary: This post describes a peer-supported, self-directed, free (*gratis y libre*) method of self-improvement by means of practical exercises designed to deliberately instill useful habits. We have just gone public and I invite you to join us.
The “Society of the Fr... |
6b7eeedd-7820-4cc4-aa7f-74cd71e87c86 | StampyAI/alignment-research-dataset/blogs | Blogs | June 2021 Newsletter
Our big news this month is Scott Garrabrant's finite factored sets, one of MIRI's largest results to date.
For most people, the best introductory resource on FFS is likely Scott’s [Topos talk/transcript](https://www.lesswrong.com/posts/N5Jm6Nj4HkNKySA5Z/finite-factored-sets). Scott is also in th... |
a807c421-7e35-4667-aff3-3a7780479cc3 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Does SGD Produce Deceptive Alignment?
[Deceptive alignment](https://www.lesswrong.com/posts/zthDPAjh9w6Ytbeks/deceptive-alignment) was first introduced in [Risks from Learned Optimization](https://www.lesswrong.com/s/r9tYkB2a8Fp4DN8yB), which contained initial versions of the arguments discussed here. Additional argum... |
487960dd-92a6-4958-a7f7-7bb89cdb1083 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | News : Biden-Harris Administration Secures Voluntary Commitments from Leading Artificial Intelligence Companies to Manage the Risks Posed by AI
Here are the extracts naming the companies and specific commitments :
As part of this commitment, President Biden is convening seven leading AI companies at the White H... |
22ee2f07-aa30-47c6-890f-4aa9f5c2be40 | trentmkelly/LessWrong-43k | LessWrong | Fittingness: Rational success in concept formation
Epistemic status:
This post offers a philosophical argument for distinguishing truth and fittingness as parallel success concepts for two phases of rational inquiry. I have graduate degrees in philosophy, with relevant expertise in logic, type theory, epistemology, ph... |
34bd3aa9-d37b-4df8-8735-ed0abc681fb0 | trentmkelly/LessWrong-43k | LessWrong | Covid 2/4: Safe and Effective Vaccines Aplenty
The vaccine data is in. It’s pretty great.
We now have six known safe and effective Covid-19 vaccines: Pfizer, Moderna, AstraZeneca, Novavax, Johnson & Johnson and Sputnik.
Pfizer and Moderna are amazingly safe and effective. They have been approved and are being distri... |
bd2af89e-0d73-4250-970c-7ab7b90d5dc8 | trentmkelly/LessWrong-43k | LessWrong | Re: The Crux List
Really enjoyed reading Zvi's Crux List.
One really important takeaway of lists like this is "we don't know what we don't know". Namely, P(DOOM) depends intimately on a whole bunch of details about the universe that are mostly unknowable in advance.
In that spirit, here are some more cruxes that P... |
17f7e367-accd-4382-a1c7-783a86fb03b5 | trentmkelly/LessWrong-43k | LessWrong | Risques existentiels en Français
I've just been interviewed by Radio-Canada (in French) for their program "Dessine moi un Dimanche". There really wasn't enough time (the interview apparently lasted nine minutes; it felt like two), but I managed to touch upon some of the technology risks of the coming century (includin... |
86731980-b3a4-4dd0-ba2c-893b88e32c02 | trentmkelly/LessWrong-43k | LessWrong | How did experiments with lucid dreaming pan out?
I remember there was a group of enthusiasts here on Less Wrong who were interested in experimenting with lucid dreaming, including research on its impact on the quality of life. How did those experiments pan out? |
46c16a08-2e05-4074-8042-ae1386608df5 | trentmkelly/LessWrong-43k | LessWrong | On Deliberative Alignment
Not too long ago, OpenAI presented a paper on their new strategy of Deliberative Alignment.
The way this works is that they tell the model what its policies are and then have the model think about whether it should comply with a request.
This is an important transition, so this post will go... |
53b4f277-2a6b-45cb-b276-dd67d12fa7de | trentmkelly/LessWrong-43k | LessWrong | Meetup : Washington, D.C.: Create and Complete
Discussion article for the meetup : Washington, D.C.: Create and Complete
WHEN: 21 June 2015 03:00:00PM (-0400)
WHERE: National Portrait Gallery
We will congregate as usual in the courtyard between 3:00 and 3:30 p.m., to be ready to start at 3:30 p.m.
This week's meet... |
823a8440-e4d3-49a3-8d0f-968f9732ffa0 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | TDT for Humans
This is part 19 of 30 of Hammertime. Click [here](https://radimentary.wordpress.com/2018/01/29/hammertime-day-1-bug-hunt/) for the intro.
As is Hammertime tradition, I’m making a slight change of plans right around the scheduled time for Planning. My excuse this time:
Several commenters pointed out se... |
daed58cf-0cb2-484a-9d94-bf489db1eec2 | trentmkelly/LessWrong-43k | LessWrong | Invulnerable Incomplete Preferences:
A Formal Statement
Produced as part of the SERI ML Alignment Theory Scholars Program - Summer 2023 Cohort. My thanks to Eric Chen, Elliott Thornley, and John Wentworth for invaluable discussion and comments on earlier drafts. All errors are mine.
This article presents a few theor... |
1ecabbf4-0a3e-4031-af58-31c59f8655fe | trentmkelly/LessWrong-43k | LessWrong | Using humility to counteract shame
"Pride is not the opposite of shame, but its source. True humility is the only antidote to shame."
Uncle Iroh, "Avatar: The Last Airbender"
Shame is one of the trickiest emotions to deal with. It is difficult to think about, not to mention discuss with others, and gives rise to ins... |
5e2d31f3-3227-48a9-bf86-c351dbf20537 | StampyAI/alignment-research-dataset/special_docs | Other | A Regression Approach for Modeling Games with Many Symmetric Players.
A Regression Approach for Modeling Games with Many Symmetric Players
Bryce Wiedenbeck
Swarthmore College
bwieden1@swarthmore.eduFengjun Yang
Swarthmore College
fyang1@swarthmore.eduMichael P. Wellman
University of Michigan
wellman@umich.edu
Abstract... |
f4c5c2b7-ff01-464f-91c2-e141d6a19d01 | trentmkelly/LessWrong-43k | LessWrong | Inverse Scaling Prize: Second Round Winners
At the end of the second and final round of the Inverse Scaling Prize, we’re awarding 7 more Third Prizes. The Prize aimed to identify important tasks on which language models (LMs) perform worse the larger they are (“inverse scaling”). Inverse scaling may reveal cases where... |
ef52027a-ef6b-42f2-ac13-ce24619f59a2 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | Economic Growth in the Long Run: Artificial Intelligence Explosion or an Empty Planet?
so welcome to our webinar on the
governance and economics of ai
i'm glad that so many of you from all
corners
of the earth are joining us today i'm
anton kornick i'm an economist
at the university of virginia and the
topic of our we... |
ba1a7759-8258-4248-b2b3-718fbbe9dcfa | trentmkelly/LessWrong-43k | LessWrong | Why should I care about rationality?
|
606a4509-f533-48a1-aeae-e977be30ddb9 | trentmkelly/LessWrong-43k | LessWrong | Superposition Without Compression: Why Entangled Representations Are the Default
I have heard numerous claims recently that the underparameterisation of neural networks can be implied due to the polysemanticity of its neurons, which is prevalent in LLMs.
Whilst I have no doubt that polysemanticity is the only solutio... |
d6e32b87-ce52-46c9-ac83-cc90d81e0285 | trentmkelly/LessWrong-43k | LessWrong | It's (not) how you use it
Crossposted from the EA Forum: https://forum.effectivealtruism.org/posts/LwhzE3scZTqxERtNn/it-s-not-how-you-use-it
The phrase "technology isn't bad in itself, it's just how you use it" is commonplace and contains some truth. But I think it's a mistake to go straight into judging the usa... |
c588c50c-33a6-4cc1-9e39-57acfd8078f1 | trentmkelly/LessWrong-43k | LessWrong | Joy in the Merely Real
> ...Do not all charms fly
> At the mere touch of cold philosophy?
> There was an awful rainbow once in heaven:
> We know her woof, her texture; she is given
> In the dull catalogue of common things.
> —John Keats, Lamia
>
> "Nothing is 'mere'."
> —Richard Fe... |
e3e2311c-d7cc-44f2-970e-08ce59141524 | trentmkelly/LessWrong-43k | LessWrong | Economics Roundup #2
Previously: Economics Roundup #1
Let’s take advantage of the normality while we have it. In all senses.
INSANE TAX PROPOSALS
There is Trump’s proposal to replace income taxes with tariffs, but he is not alone.
So here is your periodic reminder, since this is not actually new at core: Biden’s p... |
2959625c-c1b4-430d-8465-ac7c0b66a680 | trentmkelly/LessWrong-43k | LessWrong | Don’t waste your time meditating on meditation retreats!
Do "Emotional Work Retreats" instead!
TLDR;
If your goal is therapeutic progress - the kind of progress you also hope to get from going to a therapist, i.e. become happier long term, get rid of unhealthy emotional patterns, and improve your relationships with ... |
ffc132ad-9b00-471e-8023-c186fd33d001 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Melbourne Practical Rationality Meetup
Discussion article for the meetup : Melbourne Practical Rationality Meetup
WHEN: 04 October 2013 06:30:00PM (+1000)
WHERE: Level 2, 491 King St West Melbourne 3003
Practical rationality. This meetup repeats on the 1st Friday of each month and is distinct from our mont... |
574c41e7-562c-42c2-a149-2ff0362b76d9 | trentmkelly/LessWrong-43k | LessWrong | how has this forum changed your life?
Hello! I am totally new here so please bear that in mind in the event I commit faux pas! I'm a writer who has written a LOT about rationality and when rationality eludes us. These are books like So You've Been Publicly Shamed, Them, The Psychopath Test and The Men Who Stare At Go... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.