id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
a6258f98-eb37-43ac-a5c7-cf65c6d006dc | trentmkelly/LessWrong-43k | LessWrong | Could you tell me what's wrong with this?
Edit: Some people have misunderstood my intentions here. I do not in any way expect this to be the NEXT GREAT IDEA. I just couldn't see anything wrong with this, which almost certainly meant there were gaps in my knowledge. I thought the fastest way to see where I went wrong w... |
eebe574b-72ad-4a82-a66e-c111b6c35315 | trentmkelly/LessWrong-43k | LessWrong | Most Questionable Details in 'AI 2027'
My thoughts on the recently posted story.
Caveats
* I think it's great that the AI Futures Project wrote up a detailed scenario.
* I enjoy it.
* Every part of the story i didn't comment on here is either fine or excellent.
* This is one of the most realistic scenarios i've ... |
d42bb314-f4e7-424a-9fc7-0e1454bc232d | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Update March 2012: We are still accepting and processing applications for this work on an ongoing basis.
Imagine trying to learn baseball by reading essays about baseball techniques. [1]
We're trying to make the jump to teaching people rationality by, metaphorically speaking, having them throw, catch, and hit baseball... |
475acfd6-29ca-4c0c-b39e-87e47cec8f3b | trentmkelly/LessWrong-43k | LessWrong | Holden Karnofsky's Singularity Institute Objection 1
The sheer length of GiveWell co-founder and co-executive director Holden Karnofsky's excellent critique of the Singularity Institute means that it's hard to keep track of the resulting discussion. I propose to break out each of his objections into a separate Discus... |
d75b8d2e-2658-44cd-88ab-6939db75f660 | trentmkelly/LessWrong-43k | LessWrong | Wild Moral Dilemmas
[CW: This post talks about personal experience of moral dilemmas. I can see how some people might be distressed by thinking about this.]
Have you ever had to decide between pushing a fat person onto some train tracks or letting five other people get hit by a train? Maybe you have a more exciting c... |
9494ce73-521c-4515-b5c9-03cbca4bc4e0 | trentmkelly/LessWrong-43k | LessWrong | What is Wrong?
I've always looked at LessWrong as a community that aims to reduce error of reasoning. However, the word "wrong" always seemed to have connotations with ethics and logic, less so goal pursuit. Something being "right" or "wrong" is generally thought of as a state of a logical proposition with respect to ... |
32271070-f603-449f-b927-eb69b1abfc66 | trentmkelly/LessWrong-43k | LessWrong | Why humans are sometimes less rational than animals
New paper from Keith Stanovich (one of my favorite cognitive scientists):
> Several formal analyses in decision theory have shown that if people’s preferences follow certain logical patterns (the so-called axioms of rational choice) then they are behaving as if the... |
a32f34ac-4836-4a31-9424-7fa963515243 | trentmkelly/LessWrong-43k | LessWrong | FrontierMath Score of o3-mini Much Lower Than Claimed
OpenAI reports that o3-mini with high reasoning and a Python tool receives a 32% on FrontierMath. However, Epoch's official evaluation[1] received only 11%.
There are a few reasons to trust Epoch's score over OpenAIs:
* Epoch built the benchmark and has better ... |
33b41d8d-59a6-469f-bb6e-9b8253b19db5 | trentmkelly/LessWrong-43k | LessWrong | Meetup : London Meetup, 28th April
Discussion article for the meetup : London Meetup, 28th April
WHEN: 28 April 2013 02:00:00PM (+0100)
WHERE: Holborn, London
A fortnightly meetup in the Shakespeare's Head pub by Holborn tube station. We meet every other Sunday at 2pm.
Everyone is welcome to attend: we're a friend... |
5e801a39-bec2-47fa-8e72-c75b56811389 | trentmkelly/LessWrong-43k | LessWrong | GreaterWrong—new theme and many enhancements
(Previous posts: [1], [2], [3], [4])
GreaterWrong.com has just added several new features and UI enhancements:
Modern Less Wrong theme
There is now a new theme (bringing the total to nine themes to choose from), called “Less”. (This theme is inspired by the design of the... |
63ab1d3c-8344-48c5-9824-dc363a721efa | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | MIRI/OP exchange about decision theory
Open Philanthropy's Joe Carlsmith and Nick Beckstead had a short conversation about [decision theory](https://www.lesswrong.com/s/Rm6oQRJJmhGCcLvxh/p/zcPLNNw4wgBX5k8kQ) a few weeks ago with MIRI's Abram Demski and Scott Garrabrant (and me) and LW's Ben Pace. I'm copying it here b... |
fb4c77e9-7a1e-40c5-b2f5-9ef36fc1361d | StampyAI/alignment-research-dataset/arxiv | Arxiv | Reward-rational (implicit) choice: A unifying formalism for reward learning.
1 Introduction
---------------
It is difficult to specify reward functions that always lead to the desired behavior. Recent work has argued that the reward specified by a human is merely a source of information about what people actually w... |
5ba2e7bc-b221-459b-8733-a1dbd979b98d | trentmkelly/LessWrong-43k | LessWrong | Meetup : December Meetup
Discussion article for the meetup : December Meetup
WHEN: 14 December 2013 07:00:00PM (-0500)
WHERE: 491 Lindbergh Place NE Apt 618 Atlanta, GA 30324
Come join us! We'll be celebrating the Solstice while doing our normal eclectic mix of self-improvement brainstorming, educational mini-pres... |
38cce14f-60f8-4cba-b635-20f83c493f4e | StampyAI/alignment-research-dataset/blogs | Blogs | Enabling high-accuracy protein structure prediction at the proteome scale
#### The AlphaFold method
Many novel machine learning innovations contribute to AlphaFold’s current level of accuracy. We give a high-level overview of the system below; for a technical description of the network architecture see our AlphaFold ... |
06206b20-8e37-404a-a0a1-41ea60024993 | trentmkelly/LessWrong-43k | LessWrong | Step Back
From a recent Psychological Science,
> In everyday life, individuals typically approach desired stimuli by stepping forward and avoid aversive stimuli by stepping backward... Cognitive functioning was gauged by means of a Stroop task immediately after a participant stepped in one direction... Stepping backw... |
b9eb12b0-bae7-41cd-b724-040616dabeab | trentmkelly/LessWrong-43k | LessWrong | Quick look: cognitive damage from well-administered anesthesia
Recently a client commissioned me to look at the potential cognitive impacts of general anesthesia. I was surprised to find out that it’s not obvious general anesthesia does more damage than spinal or local anesthesia, and my guess is most but not all of t... |
61afc736-a4b8-432b-88d0-db417dc228c2 | trentmkelly/LessWrong-43k | LessWrong | [Link] Social Psychology & Priming: Art Wears Off
Related to: Power of Suggestion
> Social Psychology & Priming: Art Wears Off
> by Steve Sailer
>
> One of the most popular social psychology studies of the Malcolm Gladwell Era has been Yale professor John Bargh's paper on how you can "prime" students to walk more s... |
a4c77117-0295-40cc-82e6-8cf53d988465 | trentmkelly/LessWrong-43k | LessWrong | Cross-context abduction: LLMs make inferences about procedural training data leveraging declarative facts in earlier training data
Epistemic status: These are first positive results. I have not yet run extensive tests to verify repeatability, so take them with a grain of salt. This post is meant to disseminate early r... |
5b1fe8c9-dff0-4562-8507-e4e88a9a238c | trentmkelly/LessWrong-43k | LessWrong | Why there's an ethanol glut and sanitizer shortage (WSJ)
Rent-seeking is so out of control that the US literally doesn't allow ethanol producers to make sanitizer during a fuel glut/sanitizer shortage:
https://www.wsj.com/articles/why-you-cant-find-rubbing-alcohol-11588629519 |
b7824640-6ccd-48d8-9638-8ceca6b84dd4 | StampyAI/alignment-research-dataset/blogs | Blogs | Costs of human-level hardware
Computing hardware which is equivalent to the brain –
* in terms of FLOPS probably costs between $1 x 105 and $3 x 1016, or $2/hour-$700bn/hour.
* in terms of TEPS probably costs $200M – $7B, or or $4,700 – $170,000/hour (including energy costs in the hourly rate).
* in terms of seconda... |
bee1b733-0b1d-4b2f-a35a-79131e2e56df | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Mesa-Search vs Mesa-Control
~~I currently see the~~ [~~spontaneous emergence of learning algorithms~~](https://www.lesswrong.com/posts/Wnqua6eQkewL3bqsF/matt-botvinick-on-the-spontaneous-emergence-of-learning) ~~as significant evidence for the commonality of~~ [~~mesa-optimization~~](https://www.lesswrong.com/posts/Fk... |
dd7e5f4a-d169-4cac-965f-8e09e0ae6883 | trentmkelly/LessWrong-43k | LessWrong | Less Successful Cider Adventures
A few weeks ago I made some boiled apple cider. It was tasty, and after eating most of it I decided to make more. This time I used a gallon of cider, and it wasn't done after a day so I turned the slow cooker to "low" and left it overnight. Turns out that was too much! It had reduced t... |
35e7f8b0-5b13-4d0c-abf5-549226e2f56c | trentmkelly/LessWrong-43k | LessWrong | The End of Bullshit at the hands of Critical Rationalism
The public debate is rife with fallacies, half-lies, evasions of counter-arguments, etc. Many of these are easy to spot for a careful and intelligent reader/viewer - particularly one who is acquainted with the most common logical fallacies and cognitive biases. ... |
dd35a4ed-ca10-4e84-8901-698e71777d26 | trentmkelly/LessWrong-43k | LessWrong | Rationality Compendium
I want to create a rationality compendium (a collection of concise but detailed information about a particular subject) and I want to know whether you think this would be a good idea. The rationality compendium would essentially be a series of posts that will eventually serve as a guide for less... |
33858ea7-b127-4607-9370-0cb6f0066ffd | trentmkelly/LessWrong-43k | LessWrong | The tech left behind
Hello, I am asking for some insights for a research I am doing. Can you cite examples of technologies that have been forgotten? What I mean by "forgotten" is not things we don't know how to do but used to (I suspect there aren't that many), nor things that are no longer in use but used to (mechani... |
b025204c-54a3-4174-83cd-a5216222b7e8 | trentmkelly/LessWrong-43k | LessWrong | Combination Lock Boxes
Traditionally we control access to our houses with "something you have": a key. This works pretty well, until you have a visitor arrive when you're not home to give them a key. The traditional way to handle this is to hide a key (under the mat, in a flower pot, etc), turning this into "something... |
efebc50d-b7d8-48cf-9ed7-0e56c56b59f2 | trentmkelly/LessWrong-43k | LessWrong | Everything's normal until it's not
Crossposted from the EA Forum: https://forum.effectivealtruism.org/posts/2hduXN5MXCZPqKjSv/everything-s-normal-until-it-s-not
Note: This is a quick write-up of some thoughts I've had recently about communicating AI risk.
There are two claims I wish to argue for concerning ... |
2f04c203-b7cf-4178-8338-d3396ba1da3a | trentmkelly/LessWrong-43k | LessWrong | Why would AI companies use human-level AI to do alignment research?
Cross-posted from my website.
Many plans for how to safely build superintelligent AI have a critical section that goes like this:
1. Develop AI that's powerful enough to do AI research, but not yet powerful enough to pose an existential threat.
2.... |
dd5c264e-d545-4147-8d66-0101518f333f | trentmkelly/LessWrong-43k | LessWrong | Tomatoes
Are tomatoes fruits or vegetables?
I've been reading Eliezer's criticisms of Aristotelian classes as a model for the meaning of words. It occurred to me that this little chestnut is a good illustration of the problem. The best part about this example is that almost everyone has argued either on one side or... |
fcd8dd22-bc5f-44c6-9d6f-e81faa1a4257 | trentmkelly/LessWrong-43k | LessWrong | AI Alignment: A Comprehensive Survey
We have just released an academic survey of AI alignment.
We identify four main categories of alignment research:
1. Learning from feedback (e.g. scalable oversight)
2. Learning under distribution shift
3. Assurance (e.g. interpretability)
4. Governance
We mainly focused on ... |
9a144152-144e-4d89-9a12-ee29b8cfd7d8 | trentmkelly/LessWrong-43k | LessWrong | Meetup for The Roots of Progress in San Diego, Dec 1
I'll be in San Diego, CA on December 1. That evening, The Roots of Progress is hosting a community meetup and happy hour. Appetizers will be provided, cash bar. Come meet others and chat about progress.
When: Wednesday, December 1, 5:30pm
Where: Downtown San Diego... |
3b397a10-d859-424c-925e-40cec6a154a1 | trentmkelly/LessWrong-43k | LessWrong | What should be the topic of my LW mini-talk this Sunday (July 18th)?
I have signed up to give a LW mini-talk. I could in theory talk about various topics in Bayesian statistics and MCMC, but what I am actually interested in discussing right now are the ideas in this post: https://www.lesswrong.com/posts/Rh8v4ba9w5KTb6... |
61201510-4f6c-40a3-b553-fccca2d928f3 | trentmkelly/LessWrong-43k | LessWrong | Algorithms vs Compute
Two scenarios:
* I take a vision or language model which was cutting edge in 2000, and run it with a similar amount of compute/data to what's typically used today.
* I take a modern vision or language model, calculate how much money it costs to train, estimate the amount of compute I could hav... |
ff120e58-4d8c-4b7e-b1a8-dc94112078d3 | trentmkelly/LessWrong-43k | LessWrong | Abuse in LessWrong and rationalist communities in Bloomberg News
Try non-paywalled link here.
Damning allegations; but I expect this forum to respond with minimization and denial.
A few quotes:
> At the same time, she started to pick up weird vibes. One rationalist man introduced her to another as “perfect ratbait”... |
62ed8990-eeda-479c-9e63-0bcc37c58dfe | trentmkelly/LessWrong-43k | LessWrong | [Link] Physics-based anthropics?
Nick Bostrom's self-sampling assumption treats us as a random sample from a set of observers, but this framework raises several paradoxes. Instead, why not treat the stuff we observe to be a random sample from the set of all stuff that exists? I elaborate on this proposal in a new essa... |
e26c9142-2734-4054-9dd1-f16413fcf1b1 | StampyAI/alignment-research-dataset/special_docs | Other | Learning to summarize with human feedback
Learning to summarize from human feedback
Nisan StiennonLong OuyangJeff WuDaniel M. ZieglerRyan Lowe
Chelsea VossAlec Radford Dario Amodei Paul Christiano
OpenAI
Abstract
As language models become more powerful, training and evaluation are increas-
ingly bottlenecked by... |
b7660709-4b43-4c97-92b4-e7a436d83b86 | trentmkelly/LessWrong-43k | LessWrong | GPT-3, belief, and consistency
I've seen a few people debating what GPT-3 understands, and how this compares to human understanding. I think there's an easier and more fruitful question to consider: what does it believe?
It seems like it doesn't believe anything, or alternately, it believes everything. It's a categor... |
ad4d4d45-96c1-4c90-a5b3-4d6a165b13c1 | trentmkelly/LessWrong-43k | LessWrong | Bay Area: reading, writing, moving, celebrating
The interesting things going on in my life seem either too important to write about quickly, or too informative regarding some sensitive thing or another. This is perhaps exacerbated by my lack of a serious boyfriend: if I don’t have to regularly turn whatever is happeni... |
4468fdd1-5bbc-49df-a200-c1dc06015286 | trentmkelly/LessWrong-43k | LessWrong | What is a training "step" vs. "episode" in machine learning?
My impression is that steps and episodes are both time periods in a training process, and that these terms are somewhat common in RL. An episode is larger than a step and usually contains many steps.
Is this correct?
Some related questions:
1. Are reward... |
342b7470-1369-47fd-ad56-44901d230903 | trentmkelly/LessWrong-43k | LessWrong | Are COVID lab leak and market origin theories incompatible?
Epistemic status: pure speculation, want to hear what more informed people think
In public discussions of COVID origins, I observe an apparent implicit assumptions that the two leading theories - lab leak and Wuhan market origin - are incompatible, and evide... |
985ad6e7-2479-4b8b-9b1c-84b612614528 | trentmkelly/LessWrong-43k | LessWrong | AskReddit: Hard Pills to Swallow
None |
0a2f0386-fe15-43e1-bf57-742dc803461a | trentmkelly/LessWrong-43k | LessWrong | The Last Year - is there an existing novel about the last year before AI doom?
Does anybody know of any kind of novel which is set in a plausible version of the world a year or so before humanity id ended by AI, at least as we currently understand the term "humanity"? Maybe not something as technical as Gwern's doom ... |
8b8a8b5f-7c9c-456c-8716-f27b38610218 | trentmkelly/LessWrong-43k | LessWrong | Learning math (repost from reddit)
This is a good starting point for generally useful math. Probability is a conspicuous omission.
http://www.reddit.com/r/math/comments/eohrr/to_everyone_who_posts_about_learning_more_math/
|
ed852102-0dc6-48ca-bb7f-a8592c35bd0c | trentmkelly/LessWrong-43k | LessWrong | Meetup : Pittsburgh: Harry Potter and the Methods of Rationality
Discussion article for the meetup : Pittsburgh: Harry Potter and the Methods of Rationality
WHEN: 18 May 2012 06:00:00PM (-0400)
WHERE: Cafe Phipps, 1 Schenley Park, Pittsburgh, PA
In time for happy hour and/or dinner time at Cafe Phipps. Phone 412-30... |
d28a5d30-9eba-41d4-9058-9d72576af85a | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Stuart Russell Human Compatible AI Roundtable with Allan Dafoe, Rob Reich, & Marietje Schaake
At the 2020 meeting of the American Political Science Association (APSA), the largest annual meeting of political scientists in the US, Stuart Russell, professor of computer science at UC Berkeley and co-author of the standar... |
0ff5e611-b258-482a-8f56-a9dfeec2f7bb | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Scaling Laws for Reward Model Overoptimization
**TL;DR**: Reward model (RM) overoptimization in a synthetic-reward setting can be modelled surprisingly well by simple functional forms. The coefficients also scale smoothly with scale. We draw some initial correspondences between the terms of the functional forms and th... |
39435e2f-66d5-4567-8705-f2e74db9c806 | trentmkelly/LessWrong-43k | LessWrong | Meetup : San Francisco Meetup: Board Games
Discussion article for the meetup : San Francisco Meetup: Board Games
WHEN: 13 July 2015 06:15:00PM (-0400)
WHERE: 1390 Market St. Apt 2115, San Francisco, CA
(I'm on the east coast right now and the website is confused: The meetup is at 18:15 PDT)
We'll be meeting to han... |
5a515eaf-6f60-4919-b787-bde18e093219 | trentmkelly/LessWrong-43k | LessWrong | Anybody know some good Modafinil suppliers?
I've been interested in purchasing some Modafinil but I don't know any trustworthy sources. Any suggestions? |
48c13e0e-27f0-4375-88c3-2a0ad76951fb | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | GPT 4 Got Upgraded - Code Interpreter (ft. Image Editing, MP4s, 3D Plots, Data Analytics and more!)
I just got access to the code
interpreter plugin about 48 hours ago
and I've been running experiments on it
non-stop since then I've come up with
about 18 examples to show you guys its
power most of them I reckon haven'... |
4f6b45ce-54e8-4d79-85e7-e8f95a0caffa | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | [Linkpost] Some high-level thoughts on the DeepMind alignment team's strategy
***Update:** The original title "DeepMind alignment team's strategy" was poorly chosen. Some readers seem to have interpreted the previous title as meaning that this was everything that we had thought about or wanted to say about an "alignme... |
5c18406c-de21-412d-8997-cf7abfc57b71 | trentmkelly/LessWrong-43k | LessWrong | Why Not Just... Build Weak AI Tools For AI Alignment Research?
“Weak” cognitive tools are clearly a thing, and are useful. Google search is a fine example. There are plenty of flavors of “weak AI” which are potentially helpful for alignment research in a similar way to google search.
In principle, I think there’s roo... |
a67c676b-e86b-497e-9f45-0e4f488cb9a8 | trentmkelly/LessWrong-43k | LessWrong | Sunzi's《Methods of War》- Introduction
This is a translation of the Chapter 1 of The Art of War by Sunzi. No English sources were used. The original text and many of the interpretations herein come from 古诗文网.
----------------------------------------
> 孙子曰：兵者，国之大事，死生之地，存亡之道，不可不察也。
War determines life and death of tro... |
326f8596-bb9c-4537-b1d0-c4f740d542b5 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | A simple model of the Löbstacle
.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; float: none;... |
fdba501e-393e-462b-8542-421ada239d87 | trentmkelly/LessWrong-43k | LessWrong | Parable of the flooding mountain range
A mountaineer is hiking in a mountain range. There is a thick fog so he cannot see beyond a few meters.
It is raining heavily and so the mountain range is being flooded, the mountaineer has to climb to a high place so he won’t get washed away.
He will climb towards the highest ... |
78510bca-e186-41d6-a638-2d9002705792 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | October 2022 AI Risk Community Survey Results
Context
=======
In October 2022 the AI Risk community kindly filled out [this](https://forum.effectivealtruism.org/posts/8DtA57z9EyifD2wj5/ai-risk-microdynamics-survey) survey on AI Risk probabilities and timelines. Very basic research ethics is that if I use the communit... |
d7441187-2552-4e3a-9cb9-ec97610cf476 | trentmkelly/LessWrong-43k | LessWrong | From Personal to Prison Gangs: Enforcing Prosocial Behavior
This post originally appeared here; I've updated it slightly and posted it here as a follow-up to this post.
David Friedman has a fascinating book on alternative legal systems. One chapter focuses on prison law - not the nominal rules, but the rules enforced... |
aea05b81-fde0-4a9e-824f-b1ddf8f0aab5 | trentmkelly/LessWrong-43k | LessWrong | Dissolving philosophy
Summary: a large chunk of the history of Western philosophy is about finding out by what kinds of less conscious algorithms does the human mind arrive to certain intuitions.
In Plato's Republic, Socrates runs around Athens talking with people, trying to find an answer to the question: "What is ... |
d9c035ad-8090-4911-80db-882a5ce395ef | StampyAI/alignment-research-dataset/blogs | Blogs | Security Mindset and Ordinary Paranoia
The following is a fictional dialogue building off of [AI Alignment: Why It’s Hard, and Where to Start](https://intelligence.org/2016/12/28/ai-alignment-why-its-hard-and-where-to-start/).
---
(**AMBER***, a philanthropist interested in a more reliable Internet, and* **... |
7c9f5e5b-c3f5-4869-ac12-64b78def04ad | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Multibit reflective oracles
.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; float: none; dir... |
185b11a5-4388-48c1-b6b6-bbd7b9a5b2ac | trentmkelly/LessWrong-43k | LessWrong | Grace-Hanson Podcast
Cross posted from Overcoming Bias. Comments there.
***
Robin and I have a new podcast on the subject of play (mp3, wav, m4a). Older ones are here.
Don’t be thrown by a bit of silence at the start of the m4a one. We also don’t have the time right now to figure out how to put it in better formats... |
ebff8f5c-c959-43c4-b9c6-98c0de2ae859 | trentmkelly/LessWrong-43k | LessWrong | What is up with spirituality?
What is up with spirituality? I mean, from an atheistic perspective?
In my experience, atheists tend to focus on the empirical question of whether there is an all-powerful supernatural creature behind all that we observe. And yeah, there probably isn’t.
But having won that point, what d... |
3bfaac69-d6cf-4790-b6fd-a073cfe66736 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Future Meetup for Indonesian LWers
Discussion article for the meetup : Future Meetup for Indonesian LWers
WHEN: 01 January 2015 04:00:00PM (+0700)
WHERE: Bandung, Indonesia
I remember about LW's survey sometimes ago, and when the survey result come out, I see that only one LWers is come from Indonesia. Obv... |
7779b533-7524-43b6-aec4-83ec62c6a9d9 | trentmkelly/LessWrong-43k | LessWrong | Toy Models of Superposition
A new Anthropic interpretability paper—“Toy Models of Superpostion”—came out last week that I think is quite exciting and hasn't been discussed here yet.
Twitter thread from Anthropic
Twitter thread from Chris
Introduction:
> It would be very convenient if the individual neurons of arti... |
b4b13557-4d29-4e1b-83d8-70cd9cdb9b4a | trentmkelly/LessWrong-43k | LessWrong | An Attempt at Preference Uncertainty Using VNM
(This is a (possibly perpetual) draft of some work that we (I) did at the Vancouver meetup. Thanks to my meetup buddies for letting me use their brains as supplementary computational substrate. Sorry about how ugly the LaTeX is; is there a way to make this all look a bit ... |
219adf78-c56b-4c68-86fd-0fd1a11c0d48 | trentmkelly/LessWrong-43k | LessWrong | An Intuitive Explanation of Eliezer Yudkowsky’s Intuitive Explanation of Bayes’ Theorem
Common Sense Atheism has recently had a string of fantastic introductory LessWrong related material. First easing its audience into the singularity, then summarising the sequences, yesterday affirming that Death is a Problem to be ... |
35309e2f-72b9-444e-9e09-e4cdc4f5ae35 | trentmkelly/LessWrong-43k | LessWrong | The Economics of the Asteroid Deflection Problem (Dominant Assurance Contracts)
Update 2023-09-04: Partial Update: I'm fully funded!
Update 2023-09-21: Full Update. Funding is over.
Update 2023-11-28: Final Update. Platform Launched!
Imagine a world with no ads or paywalls. A world where open-source software gets t... |
43e5c9dc-6b61-4ee2-95df-9c5ac95c74b3 | trentmkelly/LessWrong-43k | LessWrong | List of petitions against OpenAI's for-profit move
Letters to attorney generals, etc, to block OpenAI from moving assets into a corporation.
* Sep: Public Citizen
* Dec: Meta
* Jan, Apr: Californian civil society nonprofits
* Apr: Coalition for AI Nonprofit Integrity
* Apr: Safety ex-employees' brief for Musk la... |
32d0ab9f-d145-4fa3-a522-5bf3415c7e53 | trentmkelly/LessWrong-43k | LessWrong | Dario Amodei leaves OpenAI
This is a linkpost for https://openai.com/blog/organizational-update/
> “We are incredibly thankful to Dario for his contributions over the past four and a half years. We wish him and his co-founders all the best in their new project, and we look forward to a collaborative relationship with... |
c332ee9a-e5f9-41c4-b901-9b738ec01671 | trentmkelly/LessWrong-43k | LessWrong | Research Direction: Be the AGI you want to see in the world
Be the AGI you want to see in the world.
Epistemic status: highly speculative, authors are not neuroscientists.
Summary
* It may be possible to enhance human intelligence via a brain-computer interface (BCI). We could put electrodes into a human brain, co... |
5f6c5787-f22a-424b-9fbe-8c0123374985 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "I think people who are not made happier by having things either have the wrong things, or have them incorrectly. Here is how I get the most out of my stuff.
Money doesn't buy happiness. If you want to try throwing money at the problem anyway, you should buy experiences like vacations or services, rather than purchasin... |
d4363036-e26c-40d5-b884-7f0b5a3f6631 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | [linkpost] Acquisition of Chess Knowledge in AlphaZero
This is a linkpost for: [Acquisition of Chess Knowledge in AlphaZero](https://arxiv.org/abs/2111.09259).
**Abstract:**
> What is being learned by superhuman neural network agents such as AlphaZero? This question is of both scientific and practical interest. If ... |
f404855d-9bbe-4f71-8f89-a140fb63a683 | trentmkelly/LessWrong-43k | LessWrong | Buying Tall-Poppy-Cutting Offsets
From Overcomingbias:
> Centuries ago, while people could rest safe and show themselves at home, when traveling between towns they tried to look either look poor or well-defended, as bandits lay in wait. Even within towns, people without allies who acted unusually rich, assertive, and... |
caac47db-5279-499c-a46c-011a978f0e0e | trentmkelly/LessWrong-43k | LessWrong | I Will Organize Meetups in Norfolk, Virginia [Hampton Roads Metro Area]
Hi!
I recently moved to Norfolk, Virginia. I used to organize the in-person meetups prior to COVID when I lived in Houston, Texas and still organize meetups there virtually.
Now that I'm living in a new place, and am vaccinated, I want to attend... |
65bfbd67-b137-41e3-b152-784a37e57b50 | trentmkelly/LessWrong-43k | LessWrong | Noticing the Taste of Lotus
Recently I started picking up French again. I remembered getting something out of Duolingo a few years ago, so I logged in.
Since the last time I was there, they added an “achievements” mechanic:
I noticed this by earning one. I think it was “Sharpshooter”. They gave me the first of three... |
d897416f-7a34-4a0e-9491-22322dfb74e5 | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post643
Thanks to Clément Dumas, Nikola Jurković, Nora Belrose, Arthur Conmy, and Oam Patel for feedback. In the comments of the post on Google Deepmind’s CCS challenges paper , I expressed skepticism that some of the experimental results seemed possible. When addressing my concerns, Rohin Shah made some claims al... |
38e53f43-bd59-4c50-9408-bb04e59fd70e | StampyAI/alignment-research-dataset/blogs | Blogs | the many faces of chaos magick
the many faces of chaos magick
------------------------------
[chaos magick](https://en.wikipedia.org/wiki/Chaos_magic) is the notion that people can "determine" (mostly in the causal sense, but also in the informational sense) aspects of reality by sufficiently convincing themselves t... |
fca5b19c-3588-4064-b6f1-a4192389f99e | trentmkelly/LessWrong-43k | LessWrong | What if AGI is near?
Consider the following observations:
* The scaling hypothesis is probably true: we will likely continue to see great improvements in AI capabilities as model sizes increase.
* Sutskever mentioned that models currently under development already have dramatic and qualitative improvements (e.g. ... |
b2da0422-ba78-4a83-ba93-9523c0ae861e | trentmkelly/LessWrong-43k | LessWrong | Free agents
Posted also on the EA Forum.
Shameless attempt at getting your attention:
If you’ve heard of AI alignment before, this might change your perspective on it. If you come from the field of machine ethics or philosophy, this is about how to create an independent moral agent.
Introduction
The problem of cre... |
9653a72e-e00e-43a1-88e1-640efb7a9036 | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | New to AI safety? Start here.
In recent years, we’ve seen AI systems grow increasingly capable. They may soon attain human and even [strongly superhuman](https://waitbutwhy.com/2015/01/artificial-intelligence-revolution-1.html) skill in a wide range of domains. Such systems could bring great benefits, but if their goa... |
34a29eac-b829-4322-ba15-a37de60f3ab5 | trentmkelly/LessWrong-43k | LessWrong | Proposed algorithm to fight anchoring bias
Anchoring is a classic cognitive bias which has been discussed on Less Wrong before. Anchoring seems very difficult to avoid. Experiments have found that warning subjects about anchoring, or giving them cash incentives, doesn't solve the problem.
Here's an algorithm to fight... |
126d7d21-b183-4fc6-afd0-75edd1412a37 | StampyAI/alignment-research-dataset/arxiv | Arxiv | The Rationale behind the Concept of Goal
1 Introduction and motivation
------------------------------
The core problem we address in this paper is how to formally describe a system operating in
an environment, with some objectives to achieve, and trying not to violate the
norms governing the domain in which the sys... |
2fcf4e28-2241-465b-bd80-bb4b7290b804 | trentmkelly/LessWrong-43k | LessWrong | Turning Some Inconsistent Preferences into Consistent Ones
cross-posted from niplav.github.io
Epistemic Status
This is still a draft that I was told to already post here, which includes working (but very slow) code for one special case. Hopefully I'll be able to expand on this in the next ~half year.
> Representing... |
13abcfef-ac50-4bf1-90a1-d2716316c5e9 | trentmkelly/LessWrong-43k | LessWrong | [Linkpost] Teaching Paradox, Europa Univeralis IV, Part I: State of Play
> I particularly wanted to discuss Paradox’s games, as compared to other historically rooted games, because I think Paradox’s oeuvre is a particularly rich vein to mine. I have already heard from multiple college-level instructors that they have ... |
ad1ad950-a30a-4889-99f1-354338257135 | trentmkelly/LessWrong-43k | LessWrong | AI #94: Not Now, Google
At this point, we can confidently say that no, capabilities are not hitting a wall. Capacity density, how much you can pack into a given space, is way up and rising rapidly, and we are starting to figure out how to use it.
Not only did we get o1 and o1 pro and also Sora and other upgrades from... |
ebd8f2eb-a9f0-412f-8752-0dda33242017 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Lesswrong Boulder CO
Discussion article for the meetup : Lesswrong Boulder CO
WHEN: 23 January 2014 07:00:00PM (-0700)
WHERE: 2690 Baseline Rd, Boulder, CO 80305
Last week didn't work out so we're doing goal factoring again. This place has really good pizza too.
Discussion article for the meetup : Lesswr... |
e86d58ae-35d8-4208-8b4a-99c2a619e834 | trentmkelly/LessWrong-43k | LessWrong | [MORESAFE] Starting global risk discussion
I am writing to propose an online discussion of global risk within the discussion part of Less Wrong. We might call this discussion "More Safe". In future it could be a site where anyone interested could discuss global risks, possibly to aggregate all existing information ab... |
601a1a85-317f-4b61-9a57-6303f50f39b0 | trentmkelly/LessWrong-43k | LessWrong | Simulate and Defer To More Rational Selves
I sometimes let imaginary versions of myself make decisions for me.
I first started doing this after a friend told me (something along the lines of) this story. When they first became executive director of their organization, they suddenly had many more decisions to deal wit... |
2f237d66-c7a0-4452-b91c-d66e14e902ea | trentmkelly/LessWrong-43k | LessWrong | AI governance student hackathon on Saturday, April 23: register now!
Cross-posted from the EA Forum
Columbia Effective Altruism and Roosevelt at Columbia are hosting an AI policy hackathon on Saturday, April 23, 2022, from 9am to 7pm EDT (UTC-4:00), open to virtual and in-person student participants! As artificial in... |
b6ab6861-5606-4ef8-a347-54cb887bb752 | trentmkelly/LessWrong-43k | LessWrong | Charitable explanation
Is anyone really altruistic? The usual cynical explanations for seemingly altruistic behavior are that it makes one feel good, it makes one look good, and it brings other rewards later. These factors are usually present, but how much do they contribute to motivation?
One way to tell if it’s all... |
fec5dc66-5ed6-446b-abba-89f0604d7389 | StampyAI/alignment-research-dataset/arbital | Arbital | Set builder notation
$\{ 2n \mid n \in \mathbb N \}$ denotes the set of all even numbers, using set builder notation. Set builder notation involves an expression on the left and a series of constraints on the right, separated by a pipe and placed between curly braces. The expression on the left makes use of variables ... |
ba4a43ae-b505-4c14-8eb0-595c3eb97e48 | trentmkelly/LessWrong-43k | LessWrong | What are some scenarios where an aligned AGI actually helps humanity, but many/most people don't like it?
One can call it "deceptive misalignment": the aligned AGI works as intended, but people really don't like it.
Some scenarios I can think of, of various levels of realism:
1. Going against the creators' will
1.... |
585dbf4a-973d-4efc-8678-adb0146f474f | trentmkelly/LessWrong-43k | LessWrong | A cynical explanation for why rationalists worry about FAI
My friend, hearing me recount tales of LessWrong, recently asked me if I thought it was simply a coincidence that so many LessWrong rationality nerds cared so much about creating Friendly AI. "If Eliezer had simply been obsessed by saving the world from astero... |
ce7dcba0-17a7-41e3-87df-fa1097357a65 | trentmkelly/LessWrong-43k | LessWrong | Northboro Air Quality Measurement
Yesterday I played the Northboro contra dance with Kingfisher, and I made the same CO2 measurements I did at BIDA a few weeks ago. This is a very different environment:
* 30 vs 80 attendees
* Eight big windows with no fans vs two doors with big barrel fans
* Maybe 1/3 the size
... |
3d6e9a3e-d319-41ed-a060-7dd6ce71e35e | trentmkelly/LessWrong-43k | LessWrong | What is the best source to explain short AI timelines to a skeptical person?
This is for a person with no ML background. He is 55 years old, he liked the sequences and I recently managed to convince him that AI risk is serious by recommending a bunch of Lesswrong posts on it, but he still thinks it's astronomically un... |
e97cc2be-ddcc-4fd1-8002-ca4c9338d471 | trentmkelly/LessWrong-43k | LessWrong | AI’s goals may not match ours
Context: This is a linkpost for https://aisafety.info/questions/NM3I/6:-AI%E2%80%99s-goals-may-not-match-ours
This is an article in the new intro to AI safety series from AISafety.info. We'd appreciate any feedback. The most up-to-date version of this article is on our website.
Maki... |
850bf5c9-d9cd-45ae-9255-3b6d6036e468 | trentmkelly/LessWrong-43k | LessWrong | RationalWiki's take on LW
I am not sure whether this has been posted here before but I came across this: http://rationalwiki.org/wiki/LessWrong
What do you think about RationalWiki in general, and their opinion regarding LW? |
d3ec4b42-5171-4ebc-9426-1aee051693c8 | trentmkelly/LessWrong-43k | LessWrong | Conned
Once in a while I’m asked “what makes you special?” It’s hard to give an honest answer other than “I’m not a snowflake, there’s nothing really unique about me”. Even my most esoteric pursuits form great tribes around them. The raison d’être of Putanumonit is that whatever peculiar idea I can write about, it wil... |
314fff60-74df-43f6-8426-7203e955c01d | trentmkelly/LessWrong-43k | LessWrong | Is GPT-3 already sample-efficient?
(Concrete, easy-to-answer question below, explanation first)
Common adage: Modern deep learning techniques are sample-inefficient; it takes loads of data for them to learn things. If you pre-train them, it takes less additional data for them to learn something new, but still compare... |
da049925-c237-4312-93b9-8fe511b26179 | trentmkelly/LessWrong-43k | LessWrong | Supplement to "Big picture of phasic dopamine"
This is "Supplementary Information" to my post "Big Picture of Phasic Dopamine".
It's a deeper dive into more specific differences between what I’m currently thinking, vs Randall O’Reilly & colleagues' PVLV model, vs Steve Grossberg & colleagues' MOTIVATOR model.
Unlike... |
282096ec-a30e-47cb-857a-af5b45baa1c9 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Alan Carter on the Complexity of Value
It’s always good news when someone else develops an idea independently from you. It's a sign you might be onto something. Which is why I was excited to discover that [Alan Carter](http://en.wikipedia.org/wiki/Alan_Carter_%28philosopher%29), Professor Emeritus of the University ... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.