id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
e19ac436-f08b-463b-bc44-14b0156a9ce2 | trentmkelly/LessWrong-43k | LessWrong | Reasoning is not search - a chess example
In the past AI systems have reached super human performance by adding search to neural networks while the network alone could not reach the level of the best humans.
At least this seems to be the case for AlphaGo, AlphaZero/Leela, AlphaGeometry and probably more, while Alpha... |
796e7bec-1619-4d3a-9dd1-f6d0619ff869 | trentmkelly/LessWrong-43k | LessWrong | Waffle Crepes
For years now I've been making eggy crepes or waffles for the kids' breakfast as a way to get them eating more protein. One thing I discovered recently, is that if you cook the crepes on both sides at the same time it's faster and they come out slightly fluffy.
We have a combination waffle maker/griddle... |
92a3f613-0b3d-4de2-8e1d-6765f35a698e | trentmkelly/LessWrong-43k | LessWrong | No Room for Political Philosophy
I was recently asked about my opinion on various schools of Political Philosophy (vg. classical liberalism, neoliberalism and Ayn Rand's Objectivism). I refused to engage with any of them in detail, because my position is that there is no room for different schools of “Political Philos... |
6e4041b0-39fa-48a0-ae35-4d659441df5a | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Making DALL-E Count
Can DALL-E count? Does DALL-E's counting ability depend on *what* it is counting? Let's find out!
I only generate the images once and paste them in along with the prompt in quotations.
**Numbers**
===========
"Zero"
------
![](https://39669.cdn.cke-cs.com/rQvD3VnunXZu34m86e5f/images/189c2a3e3d8... |
5ac6144e-abce-4446-aedc-bb73474bc9a5 | trentmkelly/LessWrong-43k | LessWrong | Go see Ex Machina
I was a little surprised that no one seems to have plugged this film here yet, but anyone interested in trans-human AI really needs to see Ex Machina. DO NOT expose yourself to any spoilers! It is very important not to know the ending of the film before you see it for it to have its full impact. B... |
822b189d-4898-4014-b225-bc6d4c153e53 | trentmkelly/LessWrong-43k | LessWrong | Full Service
New Jersey has a law that says that you are not allowed to pump your own gas. They have had this law for 70 years. This is, of course, absurd. But if it is so absurd, why do 63 percent of residents actively want to keep the law, preventing Captain Obvious (full official name: State Assemblyman Declan J. O... |
3a1c0c7c-a492-46ba-bfe8-6e2802ecf016 | trentmkelly/LessWrong-43k | LessWrong | Is "goal-content integrity" still a problem?
According to /r/controlproblem wiki one of the reasons why poorly defined goals lead to extinction we have listed:
> Goal-content integrity. An agent is less likely to achieve its goal if it has been changed to something else. For example, if you offer Gandhi a pill that m... |
5879831e-a013-4704-94e8-a7fab2c84dfe | StampyAI/alignment-research-dataset/arbital | Arbital | Preference framework
A 'preference framework' refers to a fixed algorithm that updates, or potentially changes in other ways, to determine what the agent [prefers](https://arbital.com/p/) for [terminal](https://arbital.com/p/1bh) outcomes. 'Preference framework' is a term more general than '[utility function](https:/... |
5c27e246-387b-4162-a75c-3ad6a9ea45f0 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Related to: Generalizing from One Example, Connecting Your Beliefs (a call for help), Beware the Unsurprised
The idea of this article is something I've talked about a couple of times in comments. It seems to require more attention.
As a general rule, what is obvious to some people may not be obvious to others. Is this... |
b0be7080-d26f-41b4-affc-5a1afbe4feba | trentmkelly/LessWrong-43k | LessWrong | Meetup : London meetup
Discussion article for the meetup : London meetup
WHEN: 10 May 2015 02:00:00PM (+0100)
WHERE: Shakespeare's Head, Holborn, WC2B 6BG
The next LW London meetup will be on May 10th. Join us from 2pm to talk about the sorts of things that your other friends will look funny at you for talking abou... |
ed8ec7e6-7b8b-4888-a93d-3946d28f1210 | trentmkelly/LessWrong-43k | LessWrong | A framework for thinking about AI timescales
None |
a664987b-30c6-4a8f-8c24-7934b8b5dcf1 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Learning Latent Dynamics for Planning from Pixels
1 Introduction
---------------
Planning is a natural and powerful approach to decision making problems with known dynamics, such as game playing and simulated robot control (Tassa et al., [2012](#bib.bib52); Silver et al., [2017](#bib.bib49); Moravčík et al., [2017]... |
7fc1ffbe-7f59-43d3-8a1a-f89ba72e0cf4 | trentmkelly/LessWrong-43k | LessWrong | [meta] New LW moderator: Viliam_Bur
Some time back, I wrote that I was unwilling to continue with investigations into mass downvoting, and asked people for suggestions on how to deal with them from now on. The top-voted proposal in that thread suggested making Viliam_Bur into a moderator, and Viliam gracefully accepte... |
19f645e9-16f9-4844-bb43-eb5c26e6ad2a | trentmkelly/LessWrong-43k | LessWrong | A case for gamete personhood (reductio ad absurdum)
Are animals persons? Do they have the same moral status as humans?
I’m sure all of you LessWrongers are aware of the argument from marginal cases.
For example, a chimpanzee that commits an act of rape or murder against a human isn’t seen as evil, or held morally re... |
556cc031-10cd-4331-853e-2cb555d77365 | trentmkelly/LessWrong-43k | LessWrong | An Emergency Fund for Effective Altruists
One of the things stopping people from donating a substantial part of their income to charity is the risk of a future financial downfall, which can be anything from unemployment to illness. Even in a rich country with a solid social safety net, the idea of having no financial ... |
d632d5a8-929f-48cd-8ebd-95181a4bca13 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Robustness of Contrast-Consistent Search to Adversarial Prompting
*Produced as part of the AI Safety Hub Labs programme run by Charlie Griffin and Julia Karbing. This project was mentored by Nandi Schoots.*
WHERE: 1597 Howard St. San Francisco, CA
SUPER IMPORTANT THING: This is not our normal place, although hopefully it will be in the future. Please check the address. We'... |
c3a4a594-a702-4d22-8c4e-0744c6ce6d00 | trentmkelly/LessWrong-43k | LessWrong | Don't feel bad about not knowing basic things
I recently made a mistake where I tried doing something like this in Ruby on Rails:
johns_campaign_logs = SmsLog.all.filter { |s| s.campaign_id == 1234 }
I did have a sense that it wasn't The Rails Way, but I also had a sense that it was quite readable and sufficient. T... |
ec1def68-7898-4a32-9195-619b2ef540b9 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Parametrically retargetable decision-makers tend to seek power
[This paper](https://arxiv.org/abs/2206.13477)—accepted as a poster to NeurIPS 2022— is the sequel to [Optimal Policies Tend to Seek Power](https://arxiv.org/abs/1912.01683). The new theoretical results are extremely broad, discarding the requirements of f... |
3846dadb-9345-4637-ad45-4cd94e24127a | trentmkelly/LessWrong-43k | LessWrong | Probabilistic Payor Lemma?
Epistemic status: too good to be true? Please check my math.
We've known for a while that Löb's theorem fails when proof is relaxed to probabilistic belief. This has pros and cons. On the pro side, it means there's no Löbian Obstacle to probabilistic self-trust. On the con side, it means th... |
0b19573b-f246-48be-8388-a0d68936d676 | StampyAI/alignment-research-dataset/arbital | Arbital | Trit
A trit is the trinary analog of the [https://arbital.com/p/3y2](https://arbital.com/p/3y2): Where a bit says 2, a trit says 3. "Trit," like "bit," is overloaded:
- An abstract trit (analog of the [abstract bit](https://arbital.com/p/3y3)) is an element of a [set](https://arbital.com/p/3jz) with three elements. ... |
6e441667-35e0-427e-8b82-90b75a354bfe | trentmkelly/LessWrong-43k | LessWrong | Meetup : Moscow, Scholarship and Happiness
Discussion article for the meetup : Moscow, Scholarship and Happiness
WHEN: 09 February 2014 04:00:00PM (+0400)
WHERE: Russia, Moscow, ulitsa L'va Tolstogo 16
We will gather at the same second entrance, but we will go to a room inside the building at 16:00. So please do no... |
eb987a46-6d3d-459c-8329-678e06fa4060 | trentmkelly/LessWrong-43k | LessWrong | Five toy worlds to think about heritability
Just a quick note from a Twitter/X discussion.
It’s an almost-universal scientific rule that empirics is blind without a model. The left picture below shows a bunch of points, and a regression line fitting them. It seems like a good fit. But why should we believe it? The r... |
d9ec8216-d749-470d-a9ee-7814f1ff633b | StampyAI/alignment-research-dataset/lesswrong | LessWrong | ChatGPT Plugins - The Beginning of the End
This is going to be a short post. OpenAI recently announced [ChatGPT Plugins](https://openai.com/blog/chatgpt-plugins) which will allow any developer to connect ChatGPT to external APIs and potentially real-world actions. Even if GPT-4 is not yet capable of destroying civiliz... |
1f74c351-c5be-4387-a64e-c4f375575130 | trentmkelly/LessWrong-43k | LessWrong | On Seeing Through 'On Seeing Through: A Unified Theory': A Unified Theory
None |
e0661d56-3939-412b-85bc-ef78b5a16ad9 | trentmkelly/LessWrong-43k | LessWrong | Why do we refuse to take action claiming our impact would be too small?
I've seen this often in problems like climate change or animal exploitation:
"The solution is up to others. The powerful. The governments. The policy makers."
In this way people frequently delegate their share of responsibility to more powerful ... |
b1c30bcc-2ef8-4e64-99bf-6fd9137da013 | trentmkelly/LessWrong-43k | LessWrong | Should I take glucosamine?
This paper came up on my news feed today: https://www.jabfm.org/content/jabfp/33/6/842.full.pdf
According to the research, daily intake of glucosamine/chondroitin supplements for at least a year is associated with a 39% reduction in all-cause mortality.
This is a cohort study, not a random... |
fff60cdb-a607-41ce-aaaf-e81cc0e99f70 | trentmkelly/LessWrong-43k | LessWrong | Welcome to the decade of Em
When Robin Hanson was writing Age of Em in 2016, he was thinking that Ems will be possible with advancement of brain-scanning technology in a hundred years; what he didn't anticipate was the transformer models, and their capabilities, as well as introduction of AutoGPT paradigm (I proposed ... |
a2453ffb-5322-4e7f-bc05-546b51a3c281 | trentmkelly/LessWrong-43k | LessWrong | Eric Schmidt on recursive self-improvement
Recently, Eric Schmidt gave a talk at Harvard called “Our AI Future: Hopes and Hurdles Ahead”. The entire talk is available here but there was one part that was interesting to me (around the 1:11:00 mark), and that is, his views on AI safety and trust in AI labs to stop scali... |
3f0c1443-4714-4385-8c49-88cba0dfc209 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Frequent arguments about alignment
Here, I’ll review some arguments that frequently come up in discussions about alignment research, involving one person skeptical of the endeavor (called Skeptic) and one person advocating to do more of it (called Advocate). I mostly endorse the views of the Advocate, but the Skeptic ... |
ab908b12-9a26-4d76-b6a8-463646ed7102 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | High-stakes alignment via adversarial training [Redwood Research report]
***(Update: We think the tone of this post was overly positive considering our somewhat weak results. You can read our latest post with more takeaways and followup results*** [***here***](https://www.alignmentforum.org/posts/n3LAgnHg6ashQK3fF/tak... |
ec62add4-53a7-4408-971c-ce0fa38e896b | trentmkelly/LessWrong-43k | LessWrong | Good forum for investing?
Hello I'm looking for the LW on investing advice. Any suggestions? Thanks.
EDIT:
Several commenters gave the standard advice of "buy index funds". If you bought into the Nikkei between 87 and 94 you would have made a loss or very little gains until now(30 years later). So I would appreci... |
f304c0f2-2beb-41da-956c-062bd8ce1855 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | I have thousands of copies of HPMOR in Russian. How to use them with the most impact?
(Crossposted [from the EA Forum](https://forum.effectivealtruism.org/posts/AmA9gQMhqAQW8bC4W/i-have-thousands-of-copies-of-hpmor-in-russian-how-to-use))
As a result of a crowdfunding campaign a couple of years ago, I printed 21k cop... |
85993847-292d-4fc3-9c4b-89a11430b0ca | trentmkelly/LessWrong-43k | LessWrong | On Philosophers Against Malaria
|
cb7a9221-dc7d-4cfa-89b5-8dc3b351fb0e | trentmkelly/LessWrong-43k | LessWrong | Announcing the Less Wrong Sub-Reddit
Announcing: the Less Wrong Sub-Reddit, at http://reddit.com/r/LessWrong. This Reddit is intended as a partial replacement for/complement to the Open Thread, which has gotten somewhat unwieldy and overcrowded as of late. I (Thomas McCabe) will be posting things that appear on the Ap... |
e31e49ec-ee11-4c87-9da0-042a909f3182 | trentmkelly/LessWrong-43k | LessWrong | AI Safety Prerequisites Course: Basic abstract representations of computation
Followup to AI Safety Prerequisites Course: Revamp and New Lessons. First post.
These are three new lessons of our online course on math formalizations required for AI safety research:
* Level 10: Recursive Functions
* Level 11: Set Theo... |
c7eb8828-94aa-4adb-adc1-f613f3bf4d51 | trentmkelly/LessWrong-43k | LessWrong | Critiquing Gary Taubes, Part 3: Did the US Government Give Us Absurd Advice About Sugar?
Previously: Mainstream Nutrition Science on Obesity, Atkins Redux
Here's where I start talking about the thing that initially drove me to write this post series: Taubes' repeated misrepresentation of the views of the mainstream n... |
921d379c-8464-42b6-a10b-434c1e002975 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Matt Botvinick on the spontaneous emergence of learning algorithms
Matt Botvinick is Director of Neuroscience Research at DeepMind. In [this interview](https://youtu.be/3t06ajvBtl0?t=3647), he discusses results from a [2018 paper](https://sci-hub.tw/https://www.nature.com/articles/s41593-018-0147-8) which describe con... |
d3c035d8-5b61-4cf1-aac2-08957f1ed910 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Naturalized induction – a challenge for evidential and causal decision theory
As some of you may know, I disagree with many of the criticisms leveled against [evidential decision theory](https://en.wikipedia.org/wiki/Evidential_decision_theory) (EDT). Most notably, I believe that Smoking lesion-type problems [don't](h... |
6d5b662a-fc86-49be-97c1-6f621e7e81e4 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Interdisciplinary Approaches to Understanding Artificial Intelligence's Impact on Society
Interdisciplinary Approaches to Understanding Artificial Intelligence’s
Impact on Society
A Computing Community Consortium (CCC) Quadrennial Paper
Suresh
Venkatasubramanian (University of Utah)
, Nadya Bliss (Arizo... |
721db941-c5d2-46e9-b0c8-bb8cae804096 | trentmkelly/LessWrong-43k | LessWrong | What Is the Idea Behind (Un-)Supervised Learning and Reinforcement Learning?
Through the authority of my ml class and Wikipedia[1] I "learned" that ml algorithms can be roughly put into 3 clusters: unsupervised, supervised, and reinforcement learning.
When learning about machine learning, one term I stumbled over is ... |
3dce8e75-c23e-47a5-8a01-08f2bb1824aa | trentmkelly/LessWrong-43k | LessWrong | Negotiating Up and Down the Simulation Hierarchy: Why We Might Survive the Unaligned Singularity
Another idea I picked up from Ryan Greenblatt. Epistemic status: My reconstruction of a surprising idea I encountered. I'm not at all confident that this works … but it's an interesting thought.
Clippy recently realized h... |
ea8b3026-3f3b-440a-8fdb-94d0945e009c | trentmkelly/LessWrong-43k | LessWrong | Revisiting the ideas for non-neuralese architectures
Neuralese recurrence, allowing a model to learn thousands of tokens of information from a single pass, is thought to be the key to building high-capability models. Unfortunately, this key lacks interpretability, ensuring that we cannot check the alignment of the mod... |
10291cd2-2463-4b18-960d-688a5467ce97 | trentmkelly/LessWrong-43k | LessWrong | Request for "Tests" for the MIRI Research Guide
Lately I've been looking into learning the material in the MIRI research guide. After some time, I noticed that my biggest trepidation about diving in was the nagging question of, "But how will I know if I actually learned the stuff?"
Once I realized that was the thing ... |
1200500d-ec21-424d-91d8-01751317b5a3 | trentmkelly/LessWrong-43k | LessWrong | Short timelines and slow, continuous takeoff as the safest path to AGI
There are various different timelines/takeoff dynamics scenarios:
Figure 1
In this post, we’re going to set out our understanding of the case for short timelines and slow, continuous takeoff as the safest path to AGI.
A few reasons why laying ou... |
6dd78493-f076-4296-ab0b-89d4dd5b5e43 | trentmkelly/LessWrong-43k | LessWrong | Life insurance for Cryonics, how many years?
Hello,
one question that I don't see answered is what is the duration of your life insurance? Should I buy life insurance for 20,30 years or unlimited?
I could pay more for a longer life insurance or pay less for an insurance that will cover 20 years and invest the dif... |
b905ecf1-3d7d-47ac-84c5-f6ccbac3baea | trentmkelly/LessWrong-43k | LessWrong | Politics is the mind-killer, but maybe we should talk about it anyway
I completely agree with Eliezer that Politics is the Mind-Killer, but at the same time, I worry that talking in abstracts all the time is limiting. I wouldn't want this site to tilt too much toward politics, but I feel that there's such a thing as t... |
9e78cba9-2010-4343-a1c6-5d0effa4c872 | trentmkelly/LessWrong-43k | LessWrong | Falsification
Alright, so this is going to sound a bit silly. I'm fairly sure I've read this on the Sequences somewhere, but for the life of me I can't find it. A friend of mine insists that there is a fifty-fifty chance that we live in the Matrix. His argument is that every bit of evidence we have to say that we exis... |
f977611e-26b1-43e6-90c8-8a36cbd2b7bb | trentmkelly/LessWrong-43k | LessWrong | Personal quality experimentation
Different people seem to have different strategies, which they use systematically across different parts of their lives, and that we recognize and talk about. For instance people vary on:
* Spontaneity
* Inclination toward explicit calculations
* Tendency to go meta
* Skepticism
... |
578e8302-ad4b-4886-a6d4-0e0d7e3bf098 | trentmkelly/LessWrong-43k | LessWrong | Perfect principles are for bargaining
When people commit to principles, they often consider one transgression ruinous to the whole agenda. Eating a sausage by drunken accident can end years of vegetarianism.
As a child I thought this crazy. Couldn’t vegetarians just eat meat when it was cheap under their rationale? S... |
7fb7b957-2783-4994-a0f5-d42c966503d7 | trentmkelly/LessWrong-43k | LessWrong | AI ebook cover design brainstorming
Thanks to everyone who brainstormed possible titles for MIRI’s upcoming ebook on machine intelligence. Our leading contender for the book title is Smarter than Us: The Rise of Machine Intelligence.
What we need now are suggestions for a book cover design. AI is hard to depict witho... |
5c4ea60b-08b5-4d81-a789-315d121a11e8 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Update on the UK AI Summit and the UK's Plans
On November 1st and 2nd, the UK held an international AI Summit. Speeches were given, institutes founded, roundtables held, and 29 countries signed the *Bletchley Declaration.* This is a brief overview of events leading up to and at the summit, following up last month’s [U... |
cfc39b39-6d9e-4694-8928-f44c6162ff92 | trentmkelly/LessWrong-43k | LessWrong | Sufficiently sincere confirmation bias is indistinguishable from science
Some theater people at NYU people wanted to demonstrate how gender stereotypes affected the 2016 US presidential election. So they decided to put on a theatrical performance of the presidential debates – but with the genders of the principals swa... |
21cf2877-c391-4d6e-a1c4-d6a29638e071 | trentmkelly/LessWrong-43k | LessWrong | SARS, MERS and COVID-19
Can anyone explain the difference (lay terms) between the coronavirus strain that produced SARS and the one the produced MERS?
On reason I ask is that SARS seems to have died out (last reported case in 2004). However MERS is still being reported periodically.
Would knowing these differences, ... |
1790829c-6d45-4235-91c6-fda01e3207a2 | trentmkelly/LessWrong-43k | LessWrong | Discussion on the choice of concepts
“The reason that you can currently make toast without doing great damage is just that your toaster is stupid.”
“Can ‘stupid’ be correctly applied to toasters?”
“Yes”
“What if I say no?”
“Well, if you have a conception of stupidity that can’t be applied to toasters, and one that... |
79c38370-d31a-4fae-9b17-bcd71dda453c | trentmkelly/LessWrong-43k | LessWrong | Paper: Constitutional AI: Harmlessness from AI Feedback (Anthropic)
The authors propose a method for training a harmless AI assistant that can supervise other AIs, using only a list of rules (a "constitution") as human oversight. The method involves two phases: first, the AI improves itself by generating and revising ... |
8cc10e57-b05b-4e9f-9d0c-08f5162ff07e | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | What is reward hacking?
<iframe src="https://www.youtube.com/embed/92qDfT8pENs" title="Reward Hacking: Concrete Problems in AI Safety Part 3" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>
Reward hacking occurs when... |
9e00da6f-7915-49ae-8c0a-531e0bad5fb5 | trentmkelly/LessWrong-43k | LessWrong | Safe Distillation With a Powerful Untrusted AI
Acknowledgements: Thanks to Nathan S. Sheffield for several discussions about this.
Outline of this post:
1. I define a formal mathematical problem and state a theorem.
2. I discuss why I think this math problem says something moderately interesting about the "get pot... |
3ee1422d-6b75-450a-a75d-68f5426dd647 | trentmkelly/LessWrong-43k | LessWrong | What truths are actually taboo?
LessWrong has been having fun lately with posts about sexism, racism, and academic openness. And here just like everywhere else, somebody inevitably claims taboo status for any number of entirely obvious truths, e.g. "top level mathematicians and physicists are almost invariably male,... |
6c0c5ecf-22b7-4b49-9a02-04356567a44c | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | The "best predictor is malicious optimiser" problem
Suppose you are a friendly AI .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-... |
e4faf6f8-ebc5-4f8c-934f-bb768ca8b037 | trentmkelly/LessWrong-43k | LessWrong | Pay other people to go vegetarian for you?
I notice that a large fraction of Effective Altruism people are vegetarian. This makes sense: in general Effective Altruists take moral issues seriously, even when that means changing your lifestyle. I'm not sure it's a good balance, though.
One way to think about this is to... |
8093947b-d655-4e00-83d7-50615e65ec72 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "The goal of instrumental rationality mostly speaks for itself. Some commenters have wondered, on the other hand, why rationalists care about truth. Which invites a few different answers, depending on who you ask; and these different answers have differing characters, which can shape the search for truth in different w... |
2177b93c-ab37-4398-a788-96245a843c70 | trentmkelly/LessWrong-43k | LessWrong | What do you think is wrong with rationalist culture?
|
08d2223d-9e43-4bd0-b432-29271667d63f | trentmkelly/LessWrong-43k | LessWrong | The Legacy of Computer Science
> "Computer Science" is not a science, and its ultimate significance has little to do with computers. The computer revolution is a revolution in the way we think and in the way we express what we think. The essence of this change is the emergence of what might best be called procedural ep... |
f93c1ca0-e469-4aef-a240-6a44d1554b35 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | When would AGIs engage in conflict?
Here we will look at two of the claims introduced in the previous post: AGIs might not avoid conflict that is costly by their lights ([*Capabilities aren’t Sufficient*](https://www.lesswrong.com/posts/oNQGoySbpmnH632bG/when-does-technical-work-to-reduce-agi-conflict-make-a#Capabilit... |
e32ef015-c931-4e01-8a63-e2019857685f | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Alignment Newsletter #53
Find all Alignment Newsletter resources [here](http://rohinshah.com/alignment-newsletter/). In particular, you can [sign up](http://eepurl.com/dqMSZj), or look through this [spreadsheet](https://docs.google.com/spreadsheets/d/1PwWbWZ6FPqAgZWOoOcXM8N_tUCuxpEyMbN1NYYC02aM/edit?usp=sharing) of al... |
40d1ab09-fa4a-45b5-9e5f-02c5ee042915 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Dissolving the Question
Today's post, Dissolving the Question was originally published on 08 March 2008. A summary (taken from the LW wiki):
> Proving that you are confused may not make you feel any less confused. Proving that a question is meaningless may not help you any more than answering it. Philo... |
743e54a3-fd36-472b-83f9-ef20c1c93260 | trentmkelly/LessWrong-43k | LessWrong | Updating and Editing Factual Knowledge in Language Models
Language Models go out of date. Is it possible to stop this from happening by making intrinsic alterations to the network itself?
* This article was written around Jan 2024, the exact references are surely out of date but the core ideas still hold.
Among the ... |
fd4dc525-fc59-4b22-99ce-3544bb12d134 | trentmkelly/LessWrong-43k | LessWrong | The More Power At Stake, The Stronger Instrumental Convergence Gets For Optimal Policies
Edit, 5/16/23: I think this post is beautiful, correct in its narrow technical claims, and practically irrelevant to alignment. This post presents a cripplingly unrealistic picture of the role of reward functions in reinforcement ... |
2fa86e66-b4d9-4ca7-81cb-cb87f0755269 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Towards empathy in RL agents and beyond: Insights from cognitive science for AI Alignment
This is a talk I gave at the recent AI Safety Europe Retreat (AISER) on my research on obtaining insights from the cognitive science of empathy and applying them to RL agents and LLMs.
**Talk link:** <https://clipchamp.com/watc... |
9c71cdd2-3b79-4da6-a3a4-43c5a448f9c2 | trentmkelly/LessWrong-43k | LessWrong | Quantifying wisdom
So we know that many smart people make stupid (at least in retrospect) decisions. What these people seem to be lacking, at least at the moment they make a poor decision, is wisdom ("judicious application of knowledge"). More from Wikipedia:
It is a deep understanding and realization of people, thin... |
c6fec5f7-473e-4b9c-9ae5-5c9bf3dc6df8 | StampyAI/alignment-research-dataset/blogs | Blogs | The Power of Intelligence
In our skulls we carry around 3 pounds of slimy, wet, greyish tissue, corrugated like crumpled toilet paper. You wouldn’t think, to look at the unappetizing lump, that it was some of the most powerful stuff in the known universe. If you’d never seen an anatomy textbook, and you saw a brain ly... |
964dc2ec-033f-430a-ae9f-ba6e634827fb | trentmkelly/LessWrong-43k | LessWrong | Types of subjective welfare
Summary
I describe and review four broad potential types of subjective welfare: 1) hedonic states, i.e. pleasure and unpleasantness, 2) felt desires, both appetitive and aversive, 3) belief-like preferences, i.e. preferences as judgements or beliefs about value, and 4) choice-based preferen... |
122b4b11-a688-4bfa-8c16-1d35e878ab57 | trentmkelly/LessWrong-43k | LessWrong | Linkpost: Are Emergent Abilities in Large Language Models just In-Context Learning?
A new preprint, Lu et al., published last month, has important implications for AI risk if true. It essentially suggests that emergent capabilities of current LLMs are (with some exceptions) mediated by a model's ability to do in-conte... |
7d71bb5e-1b62-429e-a48a-487d4c0b4830 | trentmkelly/LessWrong-43k | LessWrong | Podcast with Divia Eden on operant conditioning
I interviewed Divia Eden for 2.5 hours about operant conditioning on my side podcast, The Filan Cabinet. I think it's both an interesting conversation in its own right, as well as being kinda related to human rationality as well as AI and AI alignment. (I should also say... |
40211372-14d7-4f91-b69d-89775240b7d2 | trentmkelly/LessWrong-43k | LessWrong | Nuclear War, Map and Territory, Values | Guild of the Rose Newsletter, May 2024
Community Updates
Upcoming events:
* Naturalism event every week on Thursdays
* This Interest Group discusses the 'Naturalism' sequence by Logan Strohl, practicing the techniques it describes.
* Meaning and Spirituality event every o... |
dbd10088-b55e-4f80-b2a0-d0e446562b7d | trentmkelly/LessWrong-43k | LessWrong | Survey Articles: A justification
There seems to be a growing consensus among the community that while Less Wrong is great at improving epistemic rationality, it is rather lacking when it comes to resources for instrumental rationality. I've been thinking about how to address this. This can be very hard because many of... |
115d0f9a-22d4-46a1-8299-e236a095c5d0 | trentmkelly/LessWrong-43k | LessWrong | Suggestion: Implement a Change My View Feature
I know that the devs are pretty busy at the moment, and won't be able to do anything like this for a long time, but if I don't post this now, I'll probably forget it.
Change My View: is an extremely popular sub on Reddit and the responses tend to be pretty good. However,... |
20fb5e35-e9a0-41ea-9dcf-35eaab73f202 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Clarifying what ELK is trying to achieve
(Basic familiarity with [ELK](https://www.lesswrong.com/posts/qHCDysDnvhteW7kRd/arc-s-first-technical-report-eliciting-latent-knowledge) required.)
I noticed that some people who haven’t thought that much about ELK yet (including my former self) are confused about (1) why the ... |
72f95572-5e56-419a-992b-bd5e59f03763 | trentmkelly/LessWrong-43k | LessWrong | Funeral Ritual
Followup to: Solstice: What Memes May Come (Part II)
Content note: My own opinionated thoughts on rationalist funeral ritual, which have evolved a bit since I first started thinking about it in 2012. I expect that if you haven't thought about funeral ritual and find that you need to, this will make for... |
11565178-c1a5-4bc0-840b-4741bb9153ea | trentmkelly/LessWrong-43k | LessWrong | Technology and Progress
The audio version can be listened to here:
In this essay, I will give my views on technology and progress, focusing specifically on space travel, computers and transhumanism.
Futurism is not just predictive. It is also normative. We are concerned with what we should do, not just with what wi... |
9e9ac6ac-b05e-4ae5-a373-7d952b6f9cc7 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | Secure Learning in Adversarial Environments (Bo Li, Foundations of Safe Learning Workshop)
our next speaker is Paulie her boy is
assistant professor in the computer
science department at the UI you see she
got a PhD from one debate in 2016
her research focus on machine learning
security privacy and the game Syria
she'... |
90503ceb-2669-420c-818c-c543ca44a039 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Deliberation as a method to find the "actual preferences" of humans
.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: norma... |
273df191-503f-425e-a9dc-e9c2169f61ef | trentmkelly/LessWrong-43k | LessWrong | Ugh fields
Tl;Dr version: Pavlovian conditioning can cause humans to unconsciously flinch from even thinking about a serious personal problem they have, we call it an "Ugh Field"1. The Ugh Field forms a self-shadowing blind spot covering an area desperately in need of optimization, imposing huge costs.
A problem with... |
3c6866de-a1a4-4514-ad3a-cbfebcb5f7b0 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Institutional Metaphors for Designing Large-Scale Distributed AI versus AI Techniques for Running Institutions
1 Introduction
---------------
These days, analogies carry easily between simulations of social settings and architectures for minds. We for instance casually speak of electronic and computational institut... |
77fc63ef-6ab9-4b3b-97a5-efae1996303a | trentmkelly/LessWrong-43k | LessWrong | Help describing decibans?
I'm in the process of writing up an Internet Draft for a file-format, part of which involves assigning logarithmic confidence values measured in decibans. There's still a good ways to go before it'll be in good enough shape to even have a chance at being considered for an RFC; part of that is... |
3a56ef5b-b3ae-4c11-8243-be6f36102cf4 | trentmkelly/LessWrong-43k | LessWrong | If I wanted to spend WAY more on AI, what would I spend it on?
Supposedly intelligence is some kind of superpower. And they're now selling intelligence for pennies/million tokens. Logically, it seems like I should be spending way more of my income than I currently am on intelligence. But what should I spend it on?
... |
f90349f3-cd76-41ee-87bd-4a0cc71e7753 | trentmkelly/LessWrong-43k | LessWrong | Newcomb's Problem In One Paragraph
A TLDR of my recent post on Newcomb’s. If you have libertarian freewill, then Omega cannot predict your decisions based on the past with near perfect accuracy without backwards causation in which case you’d obviously one-box. Otherwise we can assume determinism. Then, “What decision ... |
3cd4d145-4e8d-482a-9220-e0c8fb1667ad | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Desirable? AI qualities
### Summary
This post argues that desirable AI qualities include 1) Bayesian inference of its expected impacts on wellbeing across times and moral circles, 2) Finding and actualizing solutions to increase individuals’ wellbeing, 3) Motivating wellbeing focus among other systems that use AI, 4)... |
4673ea89-68d9-4b65-8529-252baa65aa80 | trentmkelly/LessWrong-43k | LessWrong | If trying to communicate about AI risks, make it vivid
Crossposted from the EA Forum
If you want to communicate AI risks in a way that increases concern, [1] our new study says you should probably use vivid stories, ideally with identifiable victims.
Tabi Ward led this project as her honours thesis. In the study, w... |
0b716e99-c680-4252-a75a-694c2b9fb38c | trentmkelly/LessWrong-43k | LessWrong | Boltzmann brain's conditional probability
Boltzmann conjectured that the low entropy universe we live in could be the result of a very big fluctuation in entropy in a universe that stays most of the time in thermodynamic equilibrium. This scenario is called "Boltzmann universe". Some have argued that if this were the ... |
9f4900ea-4f12-4e7b-a458-75fc376d0b55 | trentmkelly/LessWrong-43k | LessWrong | Alignment via manually implementing the utility function
I would like to propose an idea for aligning AI.
First, I will provide some motivation for it. Suppose you are a programmer who's having a really hard time implementing a function in a computer program you're developing. Most of the code is fine, but there's th... |
4bf14d74-2690-4d44-8c2c-d5b3cb81d0e1 | trentmkelly/LessWrong-43k | LessWrong | Nutritional Supplements: A Potted Guide?
I'd be interested to find a succinct and reliable guide to nutritional supplements. Understanding that the best thing to do would be to properly understand human biology, read papers on supplements, sports science etc and make up my own mind from there. Unfortunately I don't ha... |
17bc3345-6fea-4da6-9214-635d3f5f82e0 | trentmkelly/LessWrong-43k | LessWrong | GiveWell and the Centre for Effective Altruism are recruiting
Both GiveWell and the Centre for Effective Altruism (CEA) --an Oxford-based umbrella organization consisting of Giving What We Can, 80,000 Hours, The Life You Can Save, and Effective Animal Activism-- have been discussed here before. So I thought some folk... |
d01082dd-016d-4ae5-93b3-98fe7c4a63e5 | StampyAI/alignment-research-dataset/arxiv | Arxiv | The Computational Complexity of Structure-Based Causality.
1 Introduction
---------------
There have been many attempts to define causality going back to
Hume \shortciteHume39, and continuing to the present (see, for example,
[[Collins, Hall, & Paul2004](#bib.bibx4), [Pearl2000](#bib.bibx20)] for some recent work).... |
348faf5d-3dec-4eef-ad26-e53a5f2cd123 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Melbourne, practical rationality
Discussion article for the meetup : Melbourne, practical rationality
WHEN: 02 August 2013 07:00:00PM (+1000)
WHERE: 491 King Street, West Melbourne VIC 3003, Australia
Practical rationality. This meetup repeats on the 1st Friday of each month and is distinct from our social ... |
428eb3ec-f922-4fec-9a36-b607603bdae8 | trentmkelly/LessWrong-43k | LessWrong | What does "the universe is quantum" actually mean?
To shamelessly steal from Yudkowsky:
> If you get one law, like Special Relativity, you can look at the language it's written in, and infer what the next law ought to look like. If the laws are not being generated from the same language, they surely have something in... |
53ba1bee-753a-4dd3-8847-9e75496a3407 | trentmkelly/LessWrong-43k | LessWrong | Even Superhuman Go AIs Have Surprising Failure Modes
In March 2016, AlphaGo defeated the Go world champion Lee Sedol, winning four games to one. Machines had finally become superhuman at Go. Since then, Go-playing AI has only grown stronger. The supremacy of AI over humans seemed assured, with Lee Sedol commenting the... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.