id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
49483577-f022-4be8-9278-478155064439 | trentmkelly/LessWrong-43k | LessWrong | The True Epistemic Prisoner's Dilemma
I spoke yesterday of the epistemic prisoner's dilemma, and JGWeissman wrote:
> I am having some difficulty imagining that I am 99% sure of something, but I cannot either convince a person to outright agree with me or accept that he is uncertain and therefore should make the choic... |
909ee634-c868-402e-a133-6761765cf16b | trentmkelly/LessWrong-43k | LessWrong | Doomsday argument for Anthropic Decision Theory
tl;dr: there is no real Doomsday argument in ADT. Average utilitarians over-discount the future compared with total utilitarians, but ADT can either increase or decrease this effect. The SIA Doomsaday argument can also be constructed, but this is simply a consequence of ... |
a0f2121e-2096-4f8b-b610-b15a31a5e7bd | trentmkelly/LessWrong-43k | LessWrong | Death vs. Suffering: The Endurist-Serenist Divide on Life’s Worst Fate
Author’s Note
Longtime LW lurker, occasional contributor (under other aliases). This post introduces a taxonomy of preferences centered on one question: What do agents treat as the "worst thing"?
Core Framework:
* Endurists: Death as the ultim... |
a33d5550-6ef1-4ce3-8225-18662192b7e2 | trentmkelly/LessWrong-43k | LessWrong | Your favorite pdfs?
I just got an iPad, which means that for the first time in my life it's convenient for me to read long documents from the internet. I've often looked at things and thought, oh, if I ever have some capability to read that, I should. However, I haven't made a list.
So. What documents in pdf form, or... |
1e7df8c0-e85e-4487-bf59-8ba8fb23b944 | trentmkelly/LessWrong-43k | LessWrong | Knowing what you want is a prerequisite to getting what you want
Frequently, we decide on a goal, and then we are ineffective in working towards this goal, due to factors wholly within our control. Failure modes include giving up, losing interest, procrastination, akrasia, and failure to evaluate return on time. In al... |
b8e07e92-d03b-4a32-b6c8-429958623492 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Less Wrong: Cleveland
Discussion article for the meetup : Less Wrong: Cleveland
WHEN: 09 December 2012 03:00:23PM (-0500)
WHERE: Cleveland
Four of us will be meeting on the 9th. If you're interested and in the area, send an email!
Discussion group: https://groups.google.com/forum/?fromgroups#!forum/less-w... |
9f500bca-f777-4594-b730-06ce13a7e7ba | trentmkelly/LessWrong-43k | LessWrong | The Ethical Status of Non-human Animals
There's been some discussion on this site about vegetarianism previously, although less than I expected. It's a complicated topic, so I want to focus on a critical sub-issue: within a consequentialist/utilitarian framework, what should be the status of non-human animals? Do only... |
96ec9357-d622-40dd-a8e3-ac83bb9f967c | trentmkelly/LessWrong-43k | LessWrong | Please share your reading habits/techniques/strategies
I'm looking to build up a “tool-box” of strategies/techniques/habits for reading non-fiction effectively and efficiently. I'm looking for methods to help me retain concepts, locate main ideas, make connections, etc.
If anyone has posted about this topic previou... |
f97d733b-2204-4139-8ef1-d90daf314601 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Worse Than Random
Today's post, Worse Than Random was originally published on 11 November 2008. A summary (taken from the LW wiki):
> If a system does better when randomness is added into its processing, then it must somehow have been performing worse than random. And if you can recognize that this is ... |
f0385759-c186-4e31-8a3a-0d25efeeba90 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Durham/RTLW HPMoR discussion, chapters 94-96
Discussion article for the meetup : Durham/RTLW HPMoR discussion, chapters 94-96
WHEN: 02 November 2013 12:00:00PM (-0400)
WHERE: 726 Rigsbee Avenue, Durham, NC 27701
Bring a question, an observation, or any other thing you might like to discuss from chapters 94... |
29514527-1322-48d2-a8b4-3d4b5db820ae | trentmkelly/LessWrong-43k | LessWrong | Thoughts on the REACH Patreon
Note: My views have updated since this post, but I haven't yet written them up.
I moved from NY to the Bay several months ago.
In many senses, the Berkeley community is much bigger than NYC. There's a few hundred members instead of around 30. I had several friends in the Bay before movi... |
5492159f-4aab-4f92-b089-bbde0653e96a | trentmkelly/LessWrong-43k | LessWrong | Gradations of Inner Alignment Obstacles
The existing definitions of deception, inner optimizer, and some other terms tend to strike me as "stronger than necessary" depending on the context. If weaker definitions are similarly problematic, this means we need stronger methods to prevent them! I illustrate this and make ... |
dd5553ea-4c7e-438a-85b7-2993acc9d617 | trentmkelly/LessWrong-43k | LessWrong | A Very Simple Case For Giving To Shrimp
Crossposted from my blog.
(I think this is an important article, so I’d really appreciate you sharing and restacking it—especially with people who are very rich).
I’ve elsewhere written more words about why you should give to shrimp welfare than are contained in a typical An... |
756fbcdd-62fa-46a2-ab4a-4a7754f6e9da | trentmkelly/LessWrong-43k | LessWrong | We’ve stepped over the threshold into the Fourth Arena, but don’t recognize it
First there was the world of inanimate matter, the First Arena. Life arose from that, the Second Arena. Only 100s of thousands of years ago humans evolved from higher primates and the Third Arena, human culture, appeared. We are now on the... |
3a70284a-b68f-4283-9d8e-062402fa0fe5 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
1 Introduction
---------------
Image classification is a fundamental problem in computer vision and serves as the foundation of multiple tasks such as object detection, image segmentation, object tr... |
5c6977a9-f841-4eda-8a90-a83fa27debb3 | trentmkelly/LessWrong-43k | LessWrong | Mistakes #5: Blinded by winning
(Mistakes #1, #2, #3, #4)
I used to be a practicing atheist. I figured I had strong arguments against God’s existence. I talked to some Christians, and found that they were both ill-prepared to defend their views and shockingly uninterested in the fact that they couldn’t. This made the... |
3e38adb4-79ee-42be-b7d7-7dda772061e6 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Moscow: epistemology, framing, new project announcement
Discussion article for the meetup : Moscow: epistemology, framing, new project announcement
WHEN: 31 May 2015 02:00:00PM (+0300)
WHERE: Russia, Moscow, L'va Tolstogo 16
We're meeting at Yandex, at 7.Nebo (Extropolis is taken this time).
Please fill t... |
4b92fb98-07b4-4c6e-b683-c077bf087c80 | trentmkelly/LessWrong-43k | LessWrong | LessWrong: After Dark, a new side of LessWrong
The LessWrong team has obviously been hard at work putting out their debut album. But another LessWrong feature also seems to have been released today, to less fanfare: LessWrong: After Dark, a branch of the site devoted to explicit discussion of sex and sexuality, where ... |
472de248-f462-4ae7-909e-0508d3f9cd14 | trentmkelly/LessWrong-43k | LessWrong | Layers of Expertise and the Curse of Curiosity
Epistemic status: oversimplification of a process I'm confident about; meant as proof of concept.
Related to: Double-Dipping in Dunning-Kruger
Expertise comes in different, mostly independent layers. To illustrate them, I will describe the rough process of a curious min... |
0f860218-2b65-4f9f-9934-a15cae2027f7 | trentmkelly/LessWrong-43k | LessWrong | Panel with Israeli Prime Minister on existential risk from AI
Israeli Prime Minister, Musk, Tegmark and Brockman discuss existential risk from AI.
Nothing truly revolutionary was said. I think the most interesting bits are that the Prime Minister seems to be taking AI risk seriously, has in mind exponential progress,... |
059bf6b0-8abd-4262-babb-65c1eae177ce | trentmkelly/LessWrong-43k | LessWrong | What is/are the definition(s) of "Should"?
My Model
Consider an AI. This AI goes out into the world, observing things and doing things. This is a special AI, though. In converting observations into actions, it first transforms them into beliefs in some kind of propositional language. This may or may not be the opt... |
17e1003c-00fa-4a7d-bda7-0d5aaddf6194 | trentmkelly/LessWrong-43k | LessWrong | Coronavirus as a test-run for X-risks
On the 27th February, I, like many of us, became fully aware of the danger humanity was facing (let’s thank ‘Seeing the Smoke’) and put my cards on the table with this:
> This is partly a test run of how we'd all feel and react during a genuine existential risk. Metaculus current... |
7105eddc-1d2a-489d-a3e2-1e23a5317419 | trentmkelly/LessWrong-43k | LessWrong | Adjusting Effort to Barely Meet Standards
There is sometimes an observed inverse correlation between a student's inherent talent/intelligence and the amount of effort expended. The trend is one that I see everywhere in high school. Smart students just sort of shrug and coast by to get an acceptable grade. Or, on the o... |
ccc72246-cc8e-43bb-b722-13e6dac5d57a | StampyAI/alignment-research-dataset/arbital | Arbital | Eigenvalues and eigenvectors
Consider a linear transformation represented by a matrix $A$, and some vector $v$. If $Av = \lambda v$, we say that $v$ is an _eigenvector_ of $A$ with corresponding eigenvalue $\lambda$. Intuitively, this means that $A$ doesn't rotate or change the direction of $v$; it can only stretch it... |
69f2759c-3d2c-4f29-afc2-1c80810d89f6 | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post3879
A putative new idea for AI control; index here . Any suggestions for refining this model are welcome! Somewhat inspired by the previous post , this is a model of human bias that can be used to test theories that want to compute the "true" human preferences. The basic idea is to formalise the question: If ... |
a90a5356-a388-4d3f-aedd-62ae8da69bd7 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Aligning a toy model of optimization
Suppose I have a magic box .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; w... |
d208c9e1-9968-44eb-b012-2cf12c2476aa | trentmkelly/LessWrong-43k | LessWrong | Challenge: construct a Gradient Hacker
This is a relatively clean subproblem that we came upon a few months ago while thinking about gradient hacking. We're throwing it out to the world to see if anyone can make progress.
Problem: Construct a gradient hacker (definition below), or prove that one cannot exist under ... |
ef119b90-4bb7-464a-93d6-f5613f65f947 | trentmkelly/LessWrong-43k | LessWrong | Locally optimal psychology
Thanks to Kaj Sotala, Brian Toomey, Stag Lynn, Ethan Kuntz, and Anna Salamon.
There’s no way that chronic depression, self-loathing, poor agency, or muscle tension could be optimal… right?
Jake was depressed for 6 months. He also felt horrible every time he interacted with other people be... |
025bdaa9-c35e-40a4-808a-cc810931abcb | trentmkelly/LessWrong-43k | LessWrong | UNGA Resolution on AI: 5 Key Takeaways Looking to Future Policy
The United Nations General Assembly passed its first resolution on AI on 21st March 2024 and passed with the support of all 193 member states. The text is available here to read.
For the purposes of this summary, I focused on key aspects of the UNGA Reso... |
e588da13-4394-47b5-8736-da70121eb433 | trentmkelly/LessWrong-43k | LessWrong | Research Report: Sparse Autoencoders find only 9/180 board state features in OthelloGPT
[3/7 Edit: I have rephrased the bolded claims in the abstract per this comment from Joseph Bloom, hopefully improving the heat-to-light ratio.
Commenters have also suggested training on earlier layers and using untied weights, an... |
000c29ef-237e-4493-b5d9-e304e4d571d7 | trentmkelly/LessWrong-43k | LessWrong | Resolving the Dr Evil Problem
Deep in Dr Evil's impregnable fortress (paraphrased):
> Dr Evil is just about to complete his evil plan of destroying the Earth, when he receives a message from the Philosophy Defence Force on Mars. They have created a clone in the exact same subjective situation Dr Evil now occupies; he... |
85b25b65-1e12-4724-8c6d-ef63b55c3a35 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Washington DC meetup
Discussion article for the meetup : Washington DC meetup
WHEN: 12 May 2012 03:00:00PM (-0400)
WHERE: Portrait Gallery, central plaza
Please note the date has changed; sorry for the inconvenience. Topic will be the recent critique of SI by givewell. http://lesswrong.com/lw/cbs/thoughts_... |
73ad3117-0a77-478c-8284-1bf572a1c627 | trentmkelly/LessWrong-43k | LessWrong | Time is not the bottleneck (on making progress thinking about difficult things)
... at least, not for me. The bottleneck is something like mental energy. I can only make progress on a (subjectively) difficult topic for a handful of hours (at best) each day before hitting severe diminishing returns, and being forced to... |
568fc046-864e-4e1d-bced-16d57763139a | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | How likely is it that an AI would pretend to be a human to further its goals?
Talking about full AGI: Fairly likely, but depends on takeoff speed. In a slow takeoff of a misaligned AGI, where it is only weakly superintelligent, manipulating humans would be one of its main options for trying to further its goals for so... |
cecc7c7b-a7b0-460d-b895-0f1cc0892b70 | trentmkelly/LessWrong-43k | LessWrong | Most reliable news sources?
I've longed assumed that the vast majority of what the news discusses is irrelevant in the long run, and not that well reported at that. But the world seems to be moving faster these days, and I have more of a sense that I want to know what happened this week, because it might impact what I... |
a7ecb831-eb84-4003-b580-da4e0178c223 | trentmkelly/LessWrong-43k | LessWrong | Lizard Jockeying for Fun and Profit
If this works, it will serve as a kind of introduction to a series - or sequence, if you will - on social interaction and strategic incorporation of one's emotions into one's reason. But first let's throw this out there and see what happens, shall we?
Part the zeroth: a caveat.
Le... |
a1eb7548-5844-4afd-99f9-1d03ed446b43 | trentmkelly/LessWrong-43k | LessWrong | [video] Paul Christiano's impromptu tutorial on AIXI and TDT
Paul Christiano was about to give a tutorial on AIXI and TDT, so I whipped out my iPhone and recorded it. His tutorial wasn't carefully planned or executed, but it may still be useful to some. Note that when Paul writes "UDT" on a piece of paper he really me... |
d7bf885c-00d0-4f61-ad1b-cf526d38a6dc | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Injecting some numbers into the AGI debate - by Boaz Barak
I found this article useful context for Boaz Barak's more recent article about [the probability of AI Doom](https://www.lesswrong.com/posts/zB3ukZJqt3pQDw9jz/ai-will-change-the-world-but-won-t-take-it-over-by-playing-3).
In this article, the author (through ... |
9e80309f-4ead-4223-9f47-445c206d5961 | trentmkelly/LessWrong-43k | LessWrong | AI Fables
I write fiction. I'm also interested in how AI is going to impact the world. Among other things, I'd prefer that AI not lead to catastrophe. Let's imagine that I want to combine these two interests, writing fiction that explores the risks posed by AI. How should I go about doing so? More concretely, what ide... |
ae35be63-5489-4545-8839-aa55335b619d | trentmkelly/LessWrong-43k | LessWrong | Philadelphia Meetup: Sunday 12/6, Postrel's _The Power of Glamour_-- Winfrey/Moore video link added
1:00 PM, December 6, Nam Phuong (Vietnamese restaurant), 1100 Washington Ave, Philadelphia, PA 19147 (west side of street, just south of Washington)
http://www.thedailybeast.com/articles/2013/11/09/the-persistence-of... |
3c20f587-3340-42df-8bbe-5879adee280e | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Is Google Paperclipping the Web? The Perils of Optimization by Proxy in Social Systems
**Related to:** [The Importance of Goodhart's Law](/lw/1ws/the_importance_of_goodharts_law/), [Lucas Critique](http://en.wikipedia.org/wiki/Lucas_critique), [Campbell's Law](http://en.wikipedia.org/wiki/Campbell%27s_Law)
*tl;... |
6367f558-54ae-47db-824d-2053e59d60f6 | trentmkelly/LessWrong-43k | LessWrong | Reason is not the only means of overcoming bias
Sometimes the best way to overcome bias is through an emotional appeal. Below I interweave discussion of how emotional appeals can be used to overcome the bias corresponding to the identifiable victim effect and maladaptive resource hoarding instinct.
The beginning of... |
5086fec4-ad15-4c90-a9bf-a55484779bec | trentmkelly/LessWrong-43k | LessWrong | Effective public college tuition vs. private college tuition
Harvard charges $42k/year and $61k/year including room, board, books and personal expenses. UC Berkeley charges $13k/year in tuition and $33k/year including room, board, books and personal expenses. As a part of research for Cognito Mentoring, I looked at UC... |
d78458c2-e89d-4ee5-9206-8c31512f5557 | trentmkelly/LessWrong-43k | LessWrong | How To Construct a Political Ideology
Related to: Hold Off On Proposing Solutions, Logical Rudeness
Politics is sometimes hard to discuss. Partly since most of us seem to unconsciously take political matters with the same degree of seriousness as our forefathers used to, because we use the same mode of thought as the... |
0e8b76f9-4bf0-4fcc-a7d6-806709a803cb | trentmkelly/LessWrong-43k | LessWrong | [$20K in Prizes] AI Safety Arguments Competition
TL;DR—We’re distributing $20k in total as prizes for submissions that make effective arguments for the importance of AI safety. The goal is to generate short-form content for outreach to policymakers, management at tech companies, and ML researchers. This competition wi... |
5bec146b-400d-4b5e-8e00-42b69302aada | trentmkelly/LessWrong-43k | LessWrong | The Rationalist-Etcetera Diaspora: A SPREADSHEET!!
For ye sweet springborn children too young to recall — know that LW is but one small isle of a grand and august archipelago!
Immediately after our community was born, we schismed a whole bunch. And now there are rat colonies (evolved and culturally drifted and not ne... |
9c21050e-96fd-449e-815e-3807cc2c5562 | trentmkelly/LessWrong-43k | LessWrong | The AGI Optimist’s Dilemma
Does it matter if AI destroys the world?
Lots of (virtual) ink has been spilled on AGI x-risk. The median opinion on this forum is that when AGI is birthed, it will have terminal values that are unaligned humanity’s; it will therefore pursue those terminal values at the expense of humanit... |
72844d4b-469d-4784-8904-7b292f448c11 | trentmkelly/LessWrong-43k | LessWrong | Interspecies diplomacy as a potentially productive lens on AGI alignment
You wake up tomorrow, and find out that super-smart and powerful aliens are arriving here in 10 years. We don't know anything about them other than the fact that they're super smart and powerful: e.g, their minds run on giant computers at THz clo... |
d56649df-4c96-4ee0-92d8-b87cadb7e439 | trentmkelly/LessWrong-43k | LessWrong | Will As Thou Wilt
Followup to: Possibility and Could-ness
Arthur Schopenhauer (1788-1860) said:
> "A man can do as he wills, but not will as he wills."
For this fascinating sentence, I immediately saw two interpretations; and then, after some further thought, two more interpretations.
On the first interpretation,... |
3380fbdd-b7d2-44fc-b66c-dc8c0c9c2cf5 | trentmkelly/LessWrong-43k | LessWrong | Covid 9/3: Meet the New CDC
This week’s news all centers around policy decisions. The new data contains few important surprises, so attention shifts to what actions will be taken and how that will affect the path we follow going forward. The CDC’s fall and transformation into an arm of the White House reelection campa... |
0980845c-48da-4508-8ad2-8c629d845878 | trentmkelly/LessWrong-43k | LessWrong | Monitoring devices I have loved
Every once in a while a measurement device improves my life a lot at little cost. This post is an attempt to share those data points and gather more, so we can all get a bunch of free gains.
The typical shape of problems solved by measurement devices is as follows: there's something I ... |
b611c863-d053-4ff4-a8b0-ab1d99b31d6e | trentmkelly/LessWrong-43k | LessWrong | Descriptive vs. prescriptive optimism
[Cross-posting this essay from 2020 by request.]
I am not an “optimist”. Well, not exactly. Though I sing the praises of progress in these essays, and though I paint a bold vision for the future, I have hesitated to apply that term to myself. I have said that I am “fundamentally”... |
fd91c6cb-a3b0-4d04-862e-d702f41e2c19 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Interpretability in ML: A Broad Overview
(Reposting because I think a GreaterWrong bug on submission made this post invisible for a while last week so I'm trying again on LW.)
This blog post is an overview of ways to think about machine learning interpretability; it covers some recent research techniques as well as ... |
d3f7a032-82a5-493a-bdd8-521e055d6836 | trentmkelly/LessWrong-43k | LessWrong | Large corporations can unilaterally ban/tax ransomware payments via bets
After the Colonial Pipeline ransomware attack, the idea of banning ransomware payments has become more prominent (at least in the US). This has the benefit of reducing the incentives of hackers as well as avoiding money going to criminal syndicat... |
413056d7-fa24-4737-90e3-24f0f8f8928c | trentmkelly/LessWrong-43k | LessWrong | Why Many-Worlds Is Not The Rationally Favored Interpretation
Eliezer recently posted an essay on "the fallacy of privileging the hypothesis". What it's really about is the fallacy of privileging an arbitrary hypothesis. In the fictional example, a detective proposes that the investigation of an unsolved murder should ... |
7339344d-e169-4472-92ab-84e7fe7e5694 | trentmkelly/LessWrong-43k | LessWrong | A better analogy and example for teaching AI takeover: the ML Inferno
Epistemic Status: entirely speculative
Note: this article was assisted by ChatGPT
A very common example given for AI takeover is silently killing all humans with nanotech.
> The concrete example I usually use here is nanotech, because there's bee... |
21d42b52-9ef6-4956-bb8e-8e31d6cd3f3c | trentmkelly/LessWrong-43k | LessWrong | Modifying Jones' "AI Dilemma" Model
Code for some of the equations and plots can be found here.
Charles I. Jones’ paper The A.I. Dilemma: Growth versus Existential Risk tackles the question of whether or not to pursue AI development in the face of existential risk. I found the approach both interesting and accessible... |
938c9dc7-7cee-4672-b605-27e18d88dfb8 | trentmkelly/LessWrong-43k | LessWrong | Help me teach Bayes'
Next Monday I am supposed to introduce a bunch of middle school students to Bayes' theorem.
I've scoured the Internet for basic examples where Bayes' theorem is applied. Alas, all explanations I've come cross are, I believe, difficult to grasp for the average middle school student.
So what I am... |
27585540-5adb-48de-9ece-4100be83648c | trentmkelly/LessWrong-43k | LessWrong | K-types vs T-types — what priors do you have?
Summary: There is a spectrum between two types of people, K-types and T-types. K-types want theories with low kolmogorov-complexity and T-types want theories with low time-complexity. This classification correlates with other classifications and with certain personality tr... |
a05e3b72-7456-4bc8-825e-2616943d567a | trentmkelly/LessWrong-43k | LessWrong | Comments on OpenPhil's Interpretability RFP
I'm very excited about research that tries to deeply understand how neural networks are thinking, and especially to understand tiny parts of neural networks without too much concern for scalability, as described in OpenPhil's recent RFP or the Circuits thread on Distill.
I... |
4570da0a-30e8-4c1a-ac5f-53237fbaad9b | trentmkelly/LessWrong-43k | LessWrong | DARPA Perspective on AI
|
2f9991ab-1335-4f22-b49a-e9269443003a | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Saving Time
For the last few years, a large part of my research motivation has been directed at trying to save the concept of time—save it, for example, from all the weird causal loops created by decision theory problems. This post will hopefully explain why I care so much about time, and what I think needs to be fixe... |
05188456-9bc0-41a6-8638-28463566395e | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Thoughts on gradient hacking
Gradient hacking is the hypothesised phenomenon of a machine learning model, during training, deliberate thinking in ways which guide gradient descent to update its parameters in the directions it desires. The key intuition here is that because the loss landscape of a model is based on the... |
1130e286-3e08-483b-9119-c8301652e018 | trentmkelly/LessWrong-43k | LessWrong | Popular media coverage of Singularity Summit -the Verge [link]
http://www.theverge.com/2012/10/22/3535518/singularity-rapture-of-the-nerds-gods-end-human-race |
aea7a664-a7f8-465a-aaf6-6bb47ce14348 | trentmkelly/LessWrong-43k | LessWrong | Frequentist Statistics are Frequently Subjective
Andrew Gelman recently responded to a commenter on the Yudkowsky/Gelman diavlog; the commenter complained that Bayesian statistics were too subjective and lacked rigor. I shall explain why this is unbelievably ironic, but first, the comment itself:
> However, the fund... |
1bc2e88d-7b5a-4243-9934-9dca167783f4 | StampyAI/alignment-research-dataset/arbital | Arbital | Free group universal property
The [https://arbital.com/p/-600](https://arbital.com/p/-600) of the [https://arbital.com/p/-5kg](https://arbital.com/p/-5kg) basically tells us that "the definition of the free group doesn't depend (up to isomorphism) on the exact details of the set $X$ we picked; only on its [https://arb... |
31356544-4ed4-4b03-876b-a023b38cc59d | trentmkelly/LessWrong-43k | LessWrong | Deck Guide: Burning Drakes
[Note to rationalists: This is a straight up strategy article on Magic: The Gathering that the website I write for did not have room for, so if you don’t play, skip this.]
[Note to Magic websites: You have permission to post this article on your site anywhere that is not behind a paywall, p... |
7f4f52e7-0f28-4c8f-a999-1584de7df3aa | trentmkelly/LessWrong-43k | LessWrong | Digital Immortality Map: How to collect enough information about yourself for future resurrection by AI
If someone has died it doesn’t mean that you should stop trying to return him to life. There is one clear thing that you should do (after cryonics): collect as much information about the person as possible, as well ... |
a56f0704-84b1-4c56-b556-67b016fd417c | trentmkelly/LessWrong-43k | LessWrong | [link] Why Self-Control Seems (but may not be) Limited
Another attack on the resource-based model of willpower, Michael Inzlicht, Brandon J. Schmeichel and C. Neil Macrae have a paper called "Why Self-Control Seems (but may not be) Limited" in press in Trends in Cognitive Sciences. Ungated version here.
Some of the m... |
7943d644-3a38-499d-9f3f-5a0e29e9e0b6 | trentmkelly/LessWrong-43k | LessWrong | A Refutation of (Global) "Happiness Maximization"
NB: This is a follow-up to my previous essay The Criminal Stupidity of Intelligent People, as cross-posted to my blog: http://fare.livejournal.com/168562.html.
As promised, here is a detailed rational refutation of the utilitarian concept of (Global) "Happiness Maxim... |
049c64ca-38cc-4873-b9a8-bb4ebf0fb4c2 | trentmkelly/LessWrong-43k | LessWrong | LLMs may enable direct democracy at scale
American democracy currently operates far below its theoretical ideal. An ideal democracy precisely captures and represents the nuanced collective desires of its constituents, synthesizing diverse individual preferences into coherent, actionable policy.
Today's system offers ... |
2ee20d54-e133-45c2-8000-66e3d1823a60 | trentmkelly/LessWrong-43k | LessWrong | Web Audio Echo?
Update 2020-04-19: This actually can be done fully in AudioWorklet: echo-demo-v2. Thanks stellartux!
The hello world of audio processing is an echo:
def processAudio(samples):
return samples
You take a buffer of samples and then return them unmodified, echoing the audio back out. For example, wh... |
89069f43-010b-4ce0-abcf-783367187451 | trentmkelly/LessWrong-43k | LessWrong | Meetup : London - The Schelling Point Strategy Game (plus socials)
Discussion article for the meetup : London - The Schelling Point Strategy Game (plus socials)
WHEN: 19 January 2014 02:00:00PM (+0000)
WHERE: Shakespeare's Head, Holborn, WC2B 6BG
For the first London practical session of 2014, we will be playing The... |
a35c4e1b-c690-4342-865d-714c1a8a718b | trentmkelly/LessWrong-43k | LessWrong | Planning to build a cryptographic box with perfect secrecy
Summary
Since September 2023, I started learning a lot of math and programming skills in order to develop the safest cryptographic box in the world (and yes, I am aiming high). In these four months, I learned important things you may want to know:
* Fully Ho... |
bfe2ab79-0171-4a43-872a-74c70e0f4dd5 | trentmkelly/LessWrong-43k | LessWrong | Pantheon Interface
Pantheon is an experimental LLM interface exploring a different type of human-AI interaction. We created this as a part of the cyborgism project, with the abstract motivation of augmenting the human ability to think by integrating human and AI generated thoughts.
How it works:
1. A human user “th... |
55c2e153-0ca8-4a79-a674-1d3d4ecfd82a | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | 'Artificial Intelligence Governance under Change' (PhD dissertation)
*This is a link for my PhD dissertation, ‘[Artificial Intelligence Governance under Change: Foundations, Facets, Frameworks](https://drive.google.com/file/d/1vIJUAp_i41A5gc9Tb9EvO9aSuLn15ixq/view)’. I originally submitted this to the University of Co... |
7d020873-9204-4f95-af9a-50f395d81d11 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Thread: Reflections on the AGI Safety Fundamentals course?
I recently completed the [AGI Safety Fundamentals course](https://www.agisafetyfundamentals.com/) (on [AI alignment](https://www.agisafetyfundamentals.com/ai-alignment-curriculum)) and really enjoyed it.
I imagine lots of people on the forum have taken the co... |
5b1e2495-6d8f-4276-b15a-479b6ae834b0 | trentmkelly/LessWrong-43k | LessWrong | "warning about ai doom" is also "announcing capabilities progress to noobs"
(Some recommended writing style rules slightly broken because I'm lazy and have followed them a lot before. Shrug. Contribute edits if you care, I guess.)
----------------------------------------
A lot of people who pay some attention to cap... |
1a4e4d7e-671e-490f-9fc9-12056d25c363 | trentmkelly/LessWrong-43k | LessWrong | How evolution succeeds and fails at value alignment
Disclaimer: I don't have a background in alignment research or reinforcement learning, and I don't think any of the ideas discussed here are new, but they might be interesting to some.
A recent post suggested that humans provide an untapped wealth of evidence about ... |
23b875bb-e9d9-4b96-976d-67b97e56780c | trentmkelly/LessWrong-43k | LessWrong | Why did ChatGPT say that? Prompt engineering and more, with PIZZA.
All examples in this post can be found in this notebook, which is also probably the easiest way to start experimenting with PIZZA.
From the research & engineering team at Leap Laboratories (incl. @Arush, @sebastian-sosa, @Robbie McCorkell), where w... |
f1593c11-c373-4294-875d-07c9a6cd721a | trentmkelly/LessWrong-43k | LessWrong | Doing Despite Disliking: Self‐regulatory Strategies in Everyday Aversive Activities
A large survey of self-regulatory strategies and how reportedly effective they are.
Much more in the typical "self-regulatory" paradigm for self-help psychology, where people are assumed to have a lot more control over the strategies ... |
0983210d-c20d-4e05-81de-bd890041249d | trentmkelly/LessWrong-43k | LessWrong | One week left for CSER researcher applications
This is the last week to apply for one of four postdoctoral research positions at the Centre for the Study of Existential Risk. We are seeking researchers in disciplines including: economics, science and technology studies, science policy, arms control policy, expert elic... |
6ad98239-c26b-4574-8b61-aab32ce2ad8e | StampyAI/alignment-research-dataset/arxiv | Arxiv | A Survey on XAI for Beyond 5G Security: Technical Aspects, Use Cases, Challenges and Research Directions
I Introduction
---------------
The wireless communication industry can be considered one of the most rapidly developing sectors in technology. The innovations that thrive in the telecommunication sector have lai... |
410e8d84-0c58-41d0-a87d-cdd0979455e9 | trentmkelly/LessWrong-43k | LessWrong | Fact Finding: Simplifying the Circuit (Post 2)
This is the second post in the Google DeepMind mechanistic interpretability team’s investigation into how language models recall facts. This post focuses on distilling down the fact recall circuit and models a more standard mechanistic interpretability investigation. This... |
213aed8f-0822-4b5f-b983-ddc7eb9a5228 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "In honor of System Administrator Appreciation Day, this is a post to thank Trike Apps for creating & maintaining Less Wrong. A lot of the time when they are mentioned on Less Wrong, it is to complain about bugs or request new features. So this is the time of year: thanks for everything that continues to silently go ri... |
a5a042b4-8783-4ed0-a0cc-66d4976a4360 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Transforming myopic optimization to ordinary optimization - Do we want to seek convergence for myopic optimization problems?
While reading some papers, I found a way to take a [myopic](https://www.lesswrong.com/tag/myopia) optimization problem L.mjx-chtml {display: inline-block; line-height: 0; text-indent: 0; text-al... |
51992a4f-ab1a-4acf-9ec6-89c8310a8ca7 | trentmkelly/LessWrong-43k | LessWrong | Novum Organum: Introduction
In light of its value as a rationalist text, its historical influence on the progress of science, and its general expression of the philosophy and vision which guides LessWrong 2.0, the moderation team has seen fit to publish Novum Organum as a LessWrong sequence. (Image: the engraved tit... |
0699d9c5-7e4c-4d88-8b54-9f3d1f6d4623 | trentmkelly/LessWrong-43k | LessWrong | My Greatest Achievement
[warning: this is another gooey self-disclosure in the spirit of Alicorn and lukeprog’s recent posts, except more so.]
According to my submissions summary, my first top-level post dates back to February 18th, 2011. (I don’t know exactly when I started commenting, but I don’t feel like clicking... |
54842566-a8c7-4e87-a0be-ca3c00d2e033 | trentmkelly/LessWrong-43k | LessWrong | ‘Clearly’ covers murky thought
Why do we point out that statements we are making are obvious? If a statement is actually obvious, there should rarely reason to point the statement out, let alone that it is obvious. It’s obviousness should be obvious. It seems that a person often emphasizes that a statement is obvious ... |
8b07c49f-9717-4d26-85d8-6ec4721276bb | trentmkelly/LessWrong-43k | LessWrong | A Neural Network undergoing Gradient-based Training as a Complex System
In Thought Experiments Provide a Third Anchor, Jacob Steinhardt wrote about the relative merits of a few different reference classes when it comes to reasoning and making predictions about future machine learning systems. He refers to these refere... |
216dd01e-5bb7-4a9e-9950-89d9b8998116 | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | What technical research would be helpful for governance?
Technical AI research could [help](https://forum.effectivealtruism.org/posts/BJtekdKrAufyKhBGw/ai-governance-needs-technical-work) governance efforts by:
1. Making AI risk more concrete for policymakers by illustrating our inability to control existing AI syste... |
231f660d-5b01-4b9d-ad38-b491c7110f3d | trentmkelly/LessWrong-43k | LessWrong | Cognitive Bias of AI Researchers?
I find it inconvenient that many AI discussions circle around "agents", “environments” and “goals”. These are non-mathematical words, and by using this vocabulary we are anthropomorphizng natural world's phenomena.
While an "agent" may well be a set of interacting processes, that pro... |
2633cac0-c543-47ab-b0a1-23bcc9385486 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Othello-GPT: Reflections on the Research Process
*This is the third in a three post sequence about interpreting Othello-GPT. See [the first post](https://neelnanda.io/othello) for context.*
*This post is a detailed account of what my research process was, decisions made at each point, what intermediate results looke... |
058f7ec2-43a7-4991-8f39-2d273aa1988d | trentmkelly/LessWrong-43k | LessWrong | Willpower and diet: advice?
Since the beginning of September, I have been attempting a gluten-free diet. (I was tested and I'm not celiac, but eating wheat, and especially highly refined-flour foods like cookies, tends to make me bloated and give me diarrhea.) I also wanted to lose 5 to 10 pounds. I'm not overweight p... |
45b089f0-4375-4f09-819f-b04d9b261cbe | trentmkelly/LessWrong-43k | LessWrong | Bayes-Up: An App for Sharing Bayesian-MCQ
Inspired by Lê Nguyên Hoang's post on Bayesian Examination, I have been developing (as a hobby) a new app called Bayes-Up (available at: bayes-up.web.app). The app is now in a state where it is working well enough to be shared with others. In this post I list a few things you ... |
b5fc6f86-6e3c-4453-92e6-ccd9f50aae31 | trentmkelly/LessWrong-43k | LessWrong | Evidence for Connection Theory
Connection Theory (CT) is the original philosophy underpinning Leverage Research, a research think tank focused that has worked with the effective altruism movement, and the rationality community, in the past on community-building, and existential risk reduction. CT was developed by Leve... |
cdb9feed-9150-452d-ba9e-2d27b03357d2 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Why is the impact penalty time-inconsistent?
.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: nowrap;... |
80811a80-9ffd-4373-9140-3d2e85704906 | StampyAI/alignment-research-dataset/special_docs | Other | Goertzel’s GOLEM implements evidential decision theory applied to policy choice
I’ve written about the question of which decision theories describe the behavior of approaches to AI like the “Law of Effect”. In this post, I would like to discuss GOLEM, an architecture for a self-modifying artificial intelligence agent ... |
89fdf722-2461-40d6-8666-6e90507376c3 | trentmkelly/LessWrong-43k | LessWrong | Keep your protos in one repo
This analysis is targeted at organizations that have not yet locked in their strategy for managing protobufs/gRPC, or have the capacity to pivot. I expect the principles involved to generalize to other organizational questions. Some of the tradeoffs are only relevant from a "protos as se... |
a8cc40e4-a519-4be9-b155-0c13b201bb66 | trentmkelly/LessWrong-43k | LessWrong | Seeking an Outside View on Israeli Military Service
I would like your assistance with gathering rational outside view so that I can make better moral decisions. The general context is that I consider myself an effective altruist with mostly Utilitarian ethics, and I have some more time of mandatory service in which I ... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.