id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
af48b9f9-bbc5-4865-b314-e4538fef7d54 | trentmkelly/LessWrong-43k | LessWrong | Don't use 'infohazard' for collectively destructive info
Suppose there were a cheap way to make nuclear weapons out of common household materials. Knowing this information is not directly harmful to the median individual like yourself. On average, it may even be beneficial to the average person, to know that secret yo... |
774410e0-84a8-4cca-9679-1fb4ff40e18e | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "A man comes to the rabbi and complains about his life: "I have almost no money, my wife is a shrew, and we live in a small apartment with seven unruly kids. It's messy, it's noisy, it's smelly, and I don't want to live."The rabbi says, "Buy a goat.""What? I just told you there's hardly room for nine people, and it's m... |
c3384760-f2d0-4194-8d3d-504f76100321 | trentmkelly/LessWrong-43k | LessWrong | Bayesian updating in real life is mostly about understanding your hypotheses
My sense is that an increasingly common viewpoint around here is that the last ~20 years of AI development and AI x-risk discourse are well-described by the following narrative:
> Eliezer Yudkowsky (and various others who were at least initi... |
05b1734c-af27-4f05-aa24-e2d5bcebe375 | trentmkelly/LessWrong-43k | LessWrong | Time to Exit the Sandbox
|
4c8bba0d-56c0-4e31-bd35-68ec701761bd | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Monthly Doom Argument Threads? Doom Argument Wiki?
Disclaimer: I might have no idea what I'm talking about and my proposal might be an infohazard but it also might save us all; I don't know
LessWrong has monthly AGI safety basic questions threads where people typically ask in the comments why their imagined solution... |
53656dde-0f28-4626-826f-23c24e148693 | trentmkelly/LessWrong-43k | LessWrong | Happy simulations
Certainty is impossible.
Something exists rather than nothing.
One can't justify stopping using logic with logic.
Logic tells you what is most likely from your own perspective, it's helpful.
Beliefs that don't follow logic or evidence are not helpful on their own, since their own opposite is just as ... |
c3845a34-85ba-410a-9508-835de7355575 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | fiction about AI risk
I don’t have a background in AI, but I recently read a book which seems like a pretty good metaphor for AI and thought I’d share!
The book, *A Beautifully Foolish Endeavor* by Hank Green, focuses on [spoilers ahead] two alien intelligences battling, primarily via digital manipulation of humans o... |
7b476a3a-28fb-4093-8b63-6cd611080c1c | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Circular Altruism
Today's post, Circular Altruism was originally published on 22 January 2008. A summary (taken from the LW wiki):
> Our moral preferences shouldn't be circular. If a policy A is better than B, and B is better than C, and C is better than D, and so on, then policy A really should be bet... |
93e1492f-3dfc-43f5-838c-644fec203779 | trentmkelly/LessWrong-43k | LessWrong | Thinking without priors?
My questions is strongly related to this post:
Bayes for Schizophrenics: Reasoning in Delusional Disorders by Scott Alexander
My question: can you balance the absence of priors with something else? Even if it's something irrational, such as wishful thinking or faith.
I'm interested in this ... |
289f3b27-50e7-4530-9e53-596b28c0a520 | trentmkelly/LessWrong-43k | LessWrong | Is civilizational alignment on the table?
It seems to have become apparent that existing social systems are functionally unaligned: organizational and market dynamics are oft cited as an important factor exacerbating AI danger. It seems to me that progress in civilizational alignment would be instrumental for increasi... |
df89c499-2e10-494d-95f4-abf93c7564a7 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Meta announces Llama 2; "open sources" it for commercial use
*See also their Llama 2 website here:* [*https://ai.meta.com/llama*](https://ai.meta.com/llama)*, and their research paper here:* [*https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/*](https://ai.meta.com/research/p... |
e0ae3dd3-911e-49b8-bdb4-2d54fbf82749 | trentmkelly/LessWrong-43k | LessWrong | Effective AI Outreach | A Data Driven Approach
Noah C Wilson | Noah.C.Wilson1993@gmail.com
Key Takeaways:
* Building a massive mainstream global movement is essential to achieving safe AGI.
* AI outreach has become the most urgent cause in AI safety due to accelerating timelines. AI outreach remains underemphasize... |
0921851b-3729-4135-9ff3-fc3552c1cb03 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Key Papers in Language Model Safety
Introduction
============
One of the fastest growing subfields of AI safety focuses on language models (LMs) such as OpenAI’s GPT-3. This article provides summaries of a few dozen key papers in several important subfields of language model safety, namely:
* Persuasion
* Truthfulne... |
3e216ea9-ae6a-442d-90cd-239e3d6cc3b0 | trentmkelly/LessWrong-43k | LessWrong | OpenAI rewrote its Preparedness Framework
New PF: blogpost, pdf. Old PF: pdf.
----------------------------------------
My tentative overall take: relative to the old PF it's thinking more clearly about how evals and mitigations fit together; the structure is more sensible. In terms of content, it prominently include... |
8d200a33-9719-48e6-82bb-af4c205cd239 | trentmkelly/LessWrong-43k | LessWrong | Do universities have an incentive to ignore data ethics as more small sample bias is brought to light?
Many older pieces of once recognised scientific literature are now being deemed unreliable due to small sample bias. An increasing amount of meta-analyses are identifying unreliable fields of study, citing lack of r... |
b629e515-5561-4225-b422-dd12de13bd82 | trentmkelly/LessWrong-43k | LessWrong | Eleuther releases Llemma: An Open Language Model For Mathematics
> Today we release Llemma: 7 billion and 34 billion parameter language models for mathematics. The Llemma models were initialized with Code Llama weights, then trained on the Proof-Pile II, a 55 billion token dataset of mathematical and scientific docume... |
6eda89cb-b068-4316-a3b5-ada7e6577e55 | trentmkelly/LessWrong-43k | LessWrong | The language of desire (post 2 of 3)
To the extent that desires explain behavior, it is primarily by meshing with beliefs to favor particular actions. For example, if I desire to lose 5 lbs, and I believe that exercising a half hour per day will cause me to lose 5 lbs, then this belief-desire pair makes it more likel... |
1d84a110-efef-4ddb-8852-985c7b934a3e | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Plans Are Predictions, Not Optimization Targets
Imagine a (United States) high-schooler who wants to be a doctor. Their obvious high-level plan to achieve that goal is:
* Graduate high school and get into college
* Go to college, study some bio/chem/physiology, graduate and get into med school
* Go to med school, mak... |
56518192-ca3f-4f67-b0c2-4507f174e6fa | trentmkelly/LessWrong-43k | LessWrong | [LINK] Brief Discussion of Asteroid & Nuclear Risk from paper by Hellman
From Risk Analysis of Nuclear Deterrence by Martin Hellman. See also http://nuclearrisk.org/
> A full-scale nuclear war is not the only threat to humanity’s continued existence, and we should allocate resources commensurate with the various risk... |
afda0a52-12ca-459f-924f-865ece5e2391 | trentmkelly/LessWrong-43k | LessWrong | A guide to Iterated Amplification & Debate
This post is about two proposals for aligning AI systems in a scalable way:
* Iterated Distillation and Amplification (often just called 'Iterated Amplification'), or IDA for short,[1] is a proposal by Paul Christiano.
* Debate is an IDA-inspired proposal by Geoffrey Irvin... |
47a6ba77-8683-4aaf-9440-221bab0e4847 | trentmkelly/LessWrong-43k | LessWrong | Thinking About Generators
Every so often I think about what we would do in an extended power outage. Generally this comes up when a crisis is in the news, so not a good time to buy things. During the February Texas Storm I set myself a reminder for three months later to think about generators. So: here I am.
We curre... |
388b64a4-7823-45e2-a5c3-ab64ebfa6822 | trentmkelly/LessWrong-43k | LessWrong | Replacing expensive costly signals
I feel like there is a general problem where people signal something using some extremely socially destructive method, and we can conceive of more socially efficient ways to send the same signal, but trying out alternative signals suggests that you might be especially bad at the trad... |
33301920-f365-4464-b9af-dd61f79c24a8 | trentmkelly/LessWrong-43k | LessWrong | March 2016 Media Thread
This is the monthly thread for posting media of various types that you've found that you enjoy. Post what you're reading, listening to, watching, and your opinion of it. Post recommendations to blogs. Post whatever media you feel like discussing! To see previous recommendations, check out the o... |
09334681-6014-408b-8b33-e746eca9a807 | trentmkelly/LessWrong-43k | LessWrong | What are the biggest "moonshots" currently in progress?
You know, "moonshot" projects like:
* SpaceX's plan to colonize Mars
* SpaceX's plan to give the whole world fast satellite internet
* Tesla's plan to transition the world to sustainable energy
* Boom making commercial supersonic flight a thing again
Let's ... |
524cef00-7e06-4c57-95c1-fc92ad3ef32b | trentmkelly/LessWrong-43k | LessWrong | [VIDEO] Harm reduction, hacker psychology
Hackers As A High Risk Population-- this is an hour-long video by Violet Blue, and it's about what she's been thinking about rather than something with definitive answers.
It starts with an overview of harm reduction-- an approach to public health which begins by accepting th... |
30193a8a-707f-4311-acf6-d69de3724283 | trentmkelly/LessWrong-43k | LessWrong | AI Impacts Quarterly Newsletter, Apr-Jun 2023
Every quarter, we have a newsletter with updates on what’s happening at AI Impacts, with an emphasis on what we’ve been working on. You can see past newsletters here and subscribe to receive more newsletters and other blogposts here.
During the past quarter, Katja wrote a... |
830cd692-a429-49e8-8842-2258d1e197a6 | trentmkelly/LessWrong-43k | LessWrong | Meetup : São Paulo Meet Up 3
Discussion article for the meetup : São Paulo Meet Up 3
WHEN: 15 June 2012 02:00:00PM (-0300)
WHERE: Sala 08 do Prédio de Filosofia e Ciências Sociais, USP - Av. Prof. Luciano Gualberto, 315 (Cidade Universitária) São Paulo, SP
There's going to be an event at USP titled 1ª Jornada Trans... |
550705c4-f04c-441e-9967-00ed640d7045 | trentmkelly/LessWrong-43k | LessWrong | How to Throw Away Information in Causal DAGs
When constructing a high-level abstract causal DAG from a low-level DAG, one operation which comes up quite often is throwing away information from a node. This post is about how to do that.
First, how do we throw away information from random variables in general? Sparknot... |
bf974b61-4b8e-4d2e-b753-9838b6f385dc | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Beyond Reinforcement Learning: Predictive Processing and Checksums
I was recently talking to a bisexual friend who cannot comprehend what it is like to be gay or straight. Her argument goes like this: Suppose you meet with a smart, pretty, high-status person but his/her genitals are concealed and his/her other sexuall... |
9c1ead38-72cc-4728-abfe-a2e55e9e38c9 | trentmkelly/LessWrong-43k | LessWrong | "Throwing Exceptions" Is A Strange Programming Pattern
For laypeople: In software, “throwing an exception” is a programmer-chosen type of behavior that occurs on the event that an “error” occurs in the course of program execution. This might happen immediately prior to or right at the time of the error.
This is osten... |
cf59ce77-fa06-4afa-93df-27bdff476241 | trentmkelly/LessWrong-43k | LessWrong | Acknowledging Background Information with P(Q|I)
Epistemic Status: This was composed in late 2017, sat editing limbo, was still worth publishing in 2021 and got some edits, and by 2023 was overdue for being published. Now, in 2024, it is almost just embarrassing that I haven't published it yet.
The 2006 book "Data An... |
e3ecf4d1-c918-4aa4-acf5-e2f1ae1d5cc8 | trentmkelly/LessWrong-43k | LessWrong | Physicist's dissociation
Frankly, I find the fact that this thought was thought and written quite absurd. It is my fingers, tendons and muscles, jumping over the keys, pressing symbols made of curves. They do so with impressive agility and coordination. I see my skin over them, which is a fascinating material with phy... |
63e45014-3bc7-4f51-b641-75ea1f6f7901 | trentmkelly/LessWrong-43k | LessWrong | Awww, a Zebra
This image recently showed up on Flickr (original is nicer):
With the caption:
> "Alas for those who turn their eyes from zebras and dream of dragons! If we cannot learn to take joy in the merely real, our lives shall be empty indeed." —Eliezer S. Yudkowsky.
"Awww!", I said, and called over my girl... |
a931eeea-1e62-4aa5-a357-8c8bddb9803a | trentmkelly/LessWrong-43k | LessWrong | [Crosspost] An AI Pause Is Humanity's Best Bet For Preventing Extinction (TIME)
Otto Barten is director of the Existential Risk Observatory, a nonprofit aiming to reduce existential risk by informing the public debate.
Joep Meindertsma is founder of PauseAI, a movement campaigning for an AI Pause.
The existential ri... |
1a0579f7-2abb-478c-81e0-0a75e30abe05 | trentmkelly/LessWrong-43k | LessWrong | What should I have for dinner? (A case study in decision making)
Everyone knows that eating fatty foods is bad for you, that high cholesterol causes heart disease and that we should all do some more exercise so that we can lose weight. How do I know that everyone knows this? Well, for one thing, this government websit... |
5d72a039-f8b9-460e-9509-b20d6d9c0708 | trentmkelly/LessWrong-43k | LessWrong | Why aren't we promoting social media awareness of x-risks?
Crossposted from the EA Forum.
Videos like this one by Kurzgesagt show that it is not wholly impossible to present x-risks to a more general social media audience. It seems to me that content like this paired with a concrete call to action like contacting you... |
25da4852-1d34-4580-a191-265af154f1f2 | trentmkelly/LessWrong-43k | LessWrong | Design policy to be testable
My father in law is an expert on legislation. He's travelled around the world advising countries on how to craft laws and constitutions.
One of the projects he's working on at the moment is advising on a bill to promote integrated education of different cultural and religious groups in No... |
a4f1e054-0f5d-4c94-aff4-3ff3dacfe6bf | trentmkelly/LessWrong-43k | LessWrong | Upgrading moral theories to include complex values
Like many members of this community, reading the sequences has opened my eyes to a heavily neglected aspect of morality. Before reading the sequences I focused mostly on how to best improve people's wellbeing in the present and the future. However, after reading the... |
6f40689b-3428-45b1-8c93-2c1cb991017f | trentmkelly/LessWrong-43k | LessWrong | KC Dojo 2-18-20
Attendees: Me, A, W, S, C, J
Me:
As a follow up to last week, where I brought up the fact I am planning to change careers, I showed an example of the kind of job I would like to have: a position as a decision analyst at the Pentagon. (I am following the Career Path of ‘Improve Institutional Decision-... |
b9145dd2-2673-4f51-ab78-011e124a318d | trentmkelly/LessWrong-43k | LessWrong | Loebian cooperation, version 2
I'm writing up some math results developed on LW as a paper with the tentative title "Self-referential decision algorithms". Something interesting came up while I was cleaning up the Loebian cooperation result. Namely, how do we say precisely that Loebian cooperation is stable under mino... |
62b9b0db-2c7d-45a7-a76d-67f7b870dec3 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] The Sin of Underconfidence
Today's post, The Sin of Underconfidence was originally published on 20 April 2009. A summary (taken from the LW wiki):
> When subjects know about a bias or are warned about a bias, overcorrection is not unheard of as an experimental result. That's what makes a lot of cogniti... |
59f96506-50b8-4c04-bc7e-2746719eb1ec | trentmkelly/LessWrong-43k | LessWrong | False Thermodynamic Miracles, in equation form
In equation form, the AI is maximising
P(¬X)∗C+P(X)∗u(X,A)
for some constant C, some unlikely event X that the AI cannot affect, some set of relevant descriptors A, and some utility u. Since C is constant, this is exactly the same as maximising u(X,A) - the probability ... |
d9715476-62da-417b-bbf1-8adfc2e1e2e9 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Future ML Systems Will Be Qualitatively Different
In 1972, the Nobel prize-winning physicist Philip Anderson wrote the essay "[More Is Different](https://science.sciencemag.org/content/177/4047/393)". In it, he argues that quantitative changes can lead to qualitatively different and unexpected phenomena. While he focu... |
0036fd73-efd2-4ea8-bab5-99988cb4601e | trentmkelly/LessWrong-43k | LessWrong | Anthropic Fall 2023 Debate Progress Update
This is a research update on some work that I’ve been doing on Scalable Oversight at Anthropic, based on the original AI safety via debate proposal and a more recent agenda developed at NYU and Anthropic. The core doc was written several months ago, so some of it is likely ou... |
2bb5b577-edb3-490a-bfad-720beb86490b | StampyAI/alignment-research-dataset/arbital | Arbital | Bayes' rule: Beginner's guide
This arc teaches basic understanding of [https://arbital.com/p/1lz](https://arbital.com/p/1lz) via [https://arbital.com/p/1x5](https://arbital.com/p/1x5). This arc should work for [https://arbital.com/p/1r5](https://arbital.com/p/1r5)-type readers. |
31fc7bcd-b8ab-4f22-be0b-c6f7f32aeb0e | trentmkelly/LessWrong-43k | LessWrong | Collapsible article sections?
It would be nice to be able to make 'collapsible sections' in articles, like on my atheism FAQ. That way, each article with (for example) a long list of references at the bottom could by default have the references collapsed, but if you click 'References' then the list of references would... |
b2da87b6-6699-4829-892f-6423dfe13232 | trentmkelly/LessWrong-43k | LessWrong | Release: Optimal Weave (P1): A Prototype Cohabitive Game
I recently argued for Cohabitive Games, games that are designed for practicing negotiation, or for developing intuitions for applied cooperative bargaining, which is one of the names of preference aggregation.
I offered the assets for P1, my prototype, to whoev... |
0b0f9bbb-bf47-42cd-b4a9-19aaf64d8879 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Cambridge (MA) Meetup
Discussion article for the meetup : Cambridge (MA) Meetup
WHEN: 19 August 2012 02:00:00PM (-0400)
WHERE: 25 Ames St, Cambridge, MA 02139
Cambridge/Boston-area Less Wrong meetups on the first and third Sunday of every month, 2pm at the MIT Landau Building [25 Ames St, Bldg 66], room 14... |
bfdbeeb5-441e-4bc1-9924-4d802c8be2b8 | trentmkelly/LessWrong-43k | LessWrong | There are no rules
Crossposted to my blog
Over the course of this past year, I’ve slowly become a magician.
No, not a literal one. But in the sense that I’ve become a version of myself that I previously would’ve called a magician.
I feel less social anxiety and awkwardness when asking people for things. I feel mor... |
87befe70-dea5-40ef-8ebb-a13730cde0cd | trentmkelly/LessWrong-43k | LessWrong | "Perspective: Focused-Ultrasound Guided Neuropeptide Delivery as a Novel Therapeutic Approach in Psychiatry" (Seeds of Science call for reviewers)
Seeds of Science is a journal (funded through Scott Alexander's ACX grants program) that publishes speculative or non-traditional articles on scientific topics. Peer review... |
abeda309-b8ca-4ef0-b3dd-ea1045e6c07a | trentmkelly/LessWrong-43k | LessWrong | On Leif Wenar's Absurdly Unconvincing Critique Of Effective Altruism
Crossposted here, on my blog.
Leif Wenar recently published a critique of effective altruism that seems to be getting a lot of hype. I don’t know why. There were a few different arguments in the piece: some terrible and others even worse. Yet more ... |
bc773c96-e36f-40a5-b1c6-fe58acf45a18 | trentmkelly/LessWrong-43k | LessWrong | What would be the pros and cons of a government-backed, property-based cryptocurrency?
I'll begin with a theoretical demonstrative example.
The Bureau of Land Management (sorry for immediately Americanizing the question, to all the European readers out there, but this idea might not work well in Europe anyways, for r... |
d0a0ec4b-572b-455f-9df6-d4ccb6019ec7 | trentmkelly/LessWrong-43k | LessWrong | Genosets
Since risk from individual SNP's 'should' not be aggregated to indicate an individual's risk based on multiple sources of evidence, how are the magnitudes for genosets determined?. Can bayes or another method be used to interpret a promethease report?
Even genetic epidemiology textbooks seem pessimistic: abo... |
7de20c47-eccd-4ed6-bdf1-1fa81dbffda3 | trentmkelly/LessWrong-43k | LessWrong | Nyarlathotep Stirs: A Meta-Narrative ChatGPT Story
----------------------------------------
As Austin drifted off to sleep, he felt a sudden jolt in his brain. The chip had turned on, and he could feel the electrical pulses coursing through his mind. It was like being lost in a cosmic abyss, where the unknown and ... |
93bf3e54-23ac-4ac7-b854-b55534ba28a3 | trentmkelly/LessWrong-43k | LessWrong | CEV: coherence versus extrapolation
It's just struck me that there might be a tension between the coherence (C) and the extrapolated (E) part of CEV. One reason that CEV might work is that the mindspace of humanity isn't that large - humans are pretty close to each other, in comparison to the space of possible minds. ... |
c2875f4c-8acf-4719-aed2-2d987a508354 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Agent-Agnostic Human-in-the-Loop Reinforcement Learning
1 Introduction
---------------
A central goal of Reinforcement Learning (RL) is to design agents that learn in a fully autonomous way. An engineer designs a reward function, input/output channels, and a learning algorithm. Then, apart from debugging, the engin... |
4c6c8133-cf92-4210-bf98-cee6cf528e46 | trentmkelly/LessWrong-43k | LessWrong | The Logistics of Distribution of Meaning: Against Epistemic Bureaucratization
This is an excerpt from the Introduction section to a book-length project that was kicked off as a response to the framing of the essay competition on the Automation of Wisdom and Philosophy. Many unrelated-seeming threads open in this post,... |
05fcdf49-056f-4240-ac40-6c5193180204 | trentmkelly/LessWrong-43k | LessWrong | The Limits Of Medicine - Part 1 - Small Molecules
Much of medicine relies on what is dubbed "small molecules".
"Molecules" since they are atoms tightly bound together, forming what is easily seen as a unitary whole, as opposed to e.g. lipoproteins, which are synergistic ensembles held together by much weaker forces (... |
81b9346d-aa72-4a0c-ac18-f971babc943b | trentmkelly/LessWrong-43k | LessWrong | Induction heads - illustrated
Many thanks to everyone who provided helpful feedback, particularly Aryan Bhatt and Lawrence Chan!
TL;DR
This is my illustrated walkthrough of induction heads. I created it in order to concisely capture all the information about how the circuit works.
There are 2 versions of the walkt... |
88b8b062-77f5-4b46-a987-a48bf63a977b | trentmkelly/LessWrong-43k | LessWrong | A Practical Guide to Conflict Resolution: Comprehension
[As described in the introduction, this post is about the value of fully grasping the whole picture, including the many sides to each debate, even when most of them are wrong.]
Seek First to Understand
A good attitude and a good venue will carry you a surprisin... |
4a1ce15a-b9dd-42de-925d-9605c33abbce | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Viliam Bur made the announcement in Main, but not everyone checks main, so I'm repeating it here. During the following months my time and attention will be heavily occupied by some personal stuff, so I will be unable to function as a LW moderator. The new LW moderator is... NancyLebovitz!
From today, please direct all... |
cc68f268-c941-403e-98fe-f0cb2609704d | trentmkelly/LessWrong-43k | LessWrong | Why We Disagree
Bob spends 5 minutes thinking about x-risk. He's seen a few arguments about it, so he makes an internal model of the problem, accepts some of the arguments, amends some, comes up with counterarguments to others, comes up with arguments of his own. All of this belief-state has extremely large degrees of... |
b60a2122-268b-4a3e-b5e5-b3ce166d2acc | trentmkelly/LessWrong-43k | LessWrong | What is optimization power, formally?
I'm interested in thinking formally about AI risk. I believe that a proper mathematization of the problem is important to making intellectual progress in that area.
I have been trying to understand the rather critical notion of optimization power. I was hoping that I could find a... |
9837b6e9-30f0-497b-89b7-f9cb2ab90a40 | trentmkelly/LessWrong-43k | LessWrong | Maybe talking isn't the best way to communicate with LLMs
There are 3 reasons why not all interaction with LLMs is going to be using natural language:
1. SaSSy interfaces are better for focused tasks
2. Some people don’t like talking
3. Talking to a non-sentient intelligence is creepy
#1 is already known and acte... |
94280c82-ad89-4051-bad1-79a16dc71ad4 | trentmkelly/LessWrong-43k | LessWrong | [Link] One in five American adults say they are atheist, agnostic or "nothing in particular"
A new study by the Pew Forum on Religion and Public Life [executive summary; full report; New York Times cover story] found that 19.6% of adult Americans answered a question about their current religion by saying they were ath... |
d468905a-2c26-473b-ad64-4eac31cd9785 | trentmkelly/LessWrong-43k | LessWrong | The Pointer Resolution Problem
Thanks to Garrett Baker and Evžen Wybitul for discussions and feedback on this post.
Imagine that you meet an 18th century altruist. They tell you “So, I’ve been thinking about whether or not to eat meat. Do you know whether animals have souls?” How would you answer, assuming you actual... |
3b1630df-6e9b-4edd-842c-5f3f78d51e41 | trentmkelly/LessWrong-43k | LessWrong | Yoshua Bengio: How Rogue AIs may Arise
[I think this is noteworthy, as Yoshua Bengio is a famous ML expert, and he presents his arguments for AI xrisk here. I copied the whole blogpost below.]
The rise of powerful AI dialogue systems in recent months has precipitated debates about AI risks of all kinds, which hope... |
9d6f6015-3203-4bc6-89da-4c5db06f253f | trentmkelly/LessWrong-43k | LessWrong | Why I want to make a logical language
I would normally publish this on my blog, however, I thought that LessWrong people might be interested in this topic. This sequence is about my experience creating a logical language, Sekko (still a work-in-progress).
What's a logical language?
Languages can be divided into two ... |
4302acea-85e1-4d90-815b-89fe9accaf3c | StampyAI/alignment-research-dataset/special_docs | Other | A critical agential account of free will, causation, and physics
This is an account of free choice in a physical universe. It is very much relevant to decision theory and philosophy of science. It is largely metaphysical, in terms of taking certain things to be basically real and examining what can be defined in terms... |
dc52291d-a135-46af-94bd-0fcf2b04bf0a | trentmkelly/LessWrong-43k | LessWrong | Contribution-Adjusted Utility Maximization Funds: An Early Proposal
> Right now in Effective Altruism (or Rationality), we have a few donor funds with particular focus areas. In this post I propose a new type of fund that’s instead focused on maximizing the combined utility functions of its particular donors. The fund... |
1fe6bd68-094c-4b86-86fc-0d2b65e9807f | StampyAI/alignment-research-dataset/special_docs | Other | Negotiable Reinforcement Learning for Pareto Optimal Sequential Decision-Making
Negotiable Reinforcement Learning for Pareto
Optimal Sequential Decision-Making
Nishant Desai
Center for Human-Compatible AI
University of California, Berkeley
nishantdesai@berkeley.eduAndrew Critch
Department of EECS
University of Califor... |
a4677bc9-18a1-4880-89d4-0ae902160974 | trentmkelly/LessWrong-43k | LessWrong | Cognitive Load from simple computations
From Ken Burnside, a game designer
> Counting is easier than addition.
>
> Addition is easier than subtraction.
>
> Subtraction can be done, but combining addition and subtraction into the same game mechanic will slow down play considerably. (“I have +2 for flanking, and -2 f... |
b2faf479-041f-4520-93d1-cc578bc0c3ec | trentmkelly/LessWrong-43k | LessWrong | Less Wrong Study Hall: Now With 100% Less Tinychat
Eight months ago, I announced that the Less Wrong Study Hall, a virtual coworking space where people do pomodoros together, has moved to Complice. Complice is a software system I made to help people achieve their goals. About 20% of rationalists who've tried it have s... |
91bd1d89-aa3b-4856-b11a-61b89db2f44c | trentmkelly/LessWrong-43k | LessWrong | Parent-Friendly Dance Weekends
We just finished the 2024 edition of Beantown Stomp, a contra dance weekend I helped start (but no longer organize!) in Boston. There are a lot of things I like about the weekend, but one thing I especially like is how parent-friendly it is.
The big thing here is childcare, during the d... |
51ef4a2a-34fd-48c7-9479-b94ac9037a73 | trentmkelly/LessWrong-43k | LessWrong | Query the LessWrong Hivemind
Often, there are questions you want to know the answers to. You want other people's opinions, because knowing the answer isn't worth the time you'd have to spend to find it, or you're unsure whether your answer is right.
LW seems like a good place to ask these questions because the people... |
264abb53-588e-44e3-8caf-53f91f1768e6 | trentmkelly/LessWrong-43k | LessWrong | Upcoming API changes: Upgrading to Open-CRUD syntax
This post will only really be relevant to people who are using our API, so the vast majority of people can skip this.
We are about to update our API to the closest what graphQL currently has to an industry standard. Starting tomorrow morning (PST), you will be able ... |
3c1ca095-a294-4632-ac69-79a0cc98ac43 | trentmkelly/LessWrong-43k | LessWrong | Reading RFK Jr so that you don’t have to
Some people in my orbit suggested reading Robert F. Kennedy Jr’s book The Real Anthony Fauci.
Here’s my story of wading through a few pages of the book and trying to understand the basis of the claims. My takeaway: there's a lot of sloppiness here, and several times the book... |
125a6c95-c75d-414f-98ce-82e2a30150c9 | StampyAI/alignment-research-dataset/special_docs | Other | A Few Useful Things to Know about Machine Learning
78 communications of the acm | october 2012 | vol. 55 | no. 10review articles
Machine learning syste Ms automatically learn
programs from data. This is often a very attractive
alternative to manually constructing them, and in the last decade the use of ... |
578c0583-f075-4bd2-b183-761e41c29a1a | trentmkelly/LessWrong-43k | LessWrong | AI Problems Shared by Non-AI Systems
I am grateful to Cara Selvarajah for numerous discussions regarding this post.
----------------------------------------
Choices vs Effectively Pre-determined Outcomes
Events in the world can be divided into those with mostly pre-determined outcomes and those that look more like ... |
3b1c9b0f-a0a2-4a8c-9ebe-bcedbeaada7f | trentmkelly/LessWrong-43k | LessWrong | Finding slices of joy
|
309fb2f8-cb4d-41e5-8894-c980b55cc891 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Is the speed of training large models going to increase significantly in the near future due to Cerebras Andromeda?
Cerebras recently unveiled Andromeda - <https://www.cerebras.net/andromeda/,> an AI supercomputer that enables near linear scaling. Do I understand correctly that this might have a big impact on the larg... |
86d4b236-3dd5-4c99-b80b-661e4ba956be | trentmkelly/LessWrong-43k | LessWrong | Why you are psychologically screwed up
Linkpost for https://allegedwisdom.blogspot.com/2022/02/why-you-are-psychologically-screwed-up.html
Epistemic status: deliberately written in simplified tale/myth mode. I could go off on so many tangents on the actual complexity and nuance of everything, but I wanted to keep it ... |
6effc79e-ad5c-45a2-ab5b-10e22715600d | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | My current take on the Paul-MIRI disagreement on alignability of messy 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-spacing:... |
36426e44-9182-423b-8d7b-16c101dee2db | trentmkelly/LessWrong-43k | LessWrong | Work with me on agent foundations: independent fellowship
Edit: We're now calling this the Dovetail research group.
Summary: I am an independent researcher in agent foundations, and I've recently received an LTFF grant to fund someone to do research with me. This is a rolling application; I'll close it whenever I'm n... |
02decbb2-11d8-4c1e-a794-2b4a654dd8bd | trentmkelly/LessWrong-43k | LessWrong | Where to Start Research?
When I began what I called the knowledge bootstrapping project, my ultimate goal was “Learn how to learn a subject from scratch, without deference to credentialed authorities”. That was too large and unpredictable for a single grant, so when I applied to LTFF, my stated goal was “learn how to ... |
ab05c6a9-e892-4c40-80e5-0504d2c7dcb2 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Subsystem Alignment
*(The bibliography for the whole sequence can be found* *[here](https://intelligence.org/embedded-agency))*
![](https://res.cloudinary.com/lesswrong-2-0/image/uplo... |
96e897b8-96bd-4450-8bb1-a00a95ab53ff | trentmkelly/LessWrong-43k | LessWrong | Can we build a better Public Doublecrux?
Something I'd like to try at LessOnline is to somehow iterate on the "Public Doublecrux" format. I'm not sure if I'll end up focusing on it, but here are some ideas.
Public Doublecrux is a more truthseeking oriented version of Public Debate. The goal of a debate is to change y... |
375b58a7-4d10-4a34-8674-74ee9d0a6e4a | trentmkelly/LessWrong-43k | LessWrong | Experience of typical mind fallacy.
following on from:
http://lesswrong.com/lw/dr/generalizing_from_one_example/
I am quite sure in my experience that at some point between the ages of 10-15 I concluded that; "no the rest of the world does not think like me, I think in an unusual way".
This idea disagrees with the ... |
5d5f5d36-f840-4125-af87-89de7cc1ad04 | trentmkelly/LessWrong-43k | LessWrong | True answers from AI: Summary
A putative new idea for AI control; index here.
This post summaries the methods for getting honest answers from certain AIs, presented in the previous two posts.
You can basically safely ask an AI for expected utility estimates (including conditional ones), probability estimates, and ge... |
1bf75f8e-8e57-4819-8c4e-dbc0ad76a22b | awestover/filtering-for-misalignment | Redwood Research: Alek's Filtering Results | id: post2156
In Corrigibility Can Be VNM-Incoherent , I operationalized an agent's corrigibility as our ability to modify the agent so that it follows different policies. In the summer of 2020, I had formalized this notion, but it languished—unloved—in my Overleaf drafts. ETA 12/3/21: This post is not proposing a solu... |
1761781c-520c-4b50-94a5-3864d2f29f70 | trentmkelly/LessWrong-43k | LessWrong | Things are allowed to be good and bad at the same time
I’ve found it useful to sometimes remind myself that things are allowed to be good and bad at the same time.
Suppose that there was a particular job that I wanted but didn’t get. Afterwards, I find myself thinking:
“Damnit, some of the stuff in that job would ha... |
2a37e8f5-0be9-4d26-87e1-2b4bef3fa049 | trentmkelly/LessWrong-43k | LessWrong | Introduction to French AI Policy
This post was written as part of the AI Governance Fundamentals course by BlueDot. I thank Charles Beasley and the students from my cohort for their feedback and encouragements.
Disclaimer: The French policy landscape is in rapid flux, after president Macron called for a snap election... |
142ec1de-63b9-4006-9a01-0af45b340809 | trentmkelly/LessWrong-43k | LessWrong | The Flow-Through Fallacy
There is something of an informal reasoning fallacy where you promote something that seems like something that we should "surely do", something that seems obviously important, but where we haven't thought through all of the steps involved and so we aren't actually justified in assuming that th... |
669c12e6-f001-4153-8fff-8029ca0b72fc | trentmkelly/LessWrong-43k | LessWrong | What Are The Chances of Actually Achieving FAI?
I get that the shut up and multiply calculation will make it worth trying even if the odds are really low, but my emotions don't respond very well to low odds.
I can override that to some degree, but, at the end of the day, it'd be easier if the odds were actually prett... |
3d70da12-8121-4366-a5cb-8132f978f541 | trentmkelly/LessWrong-43k | LessWrong | Rationality Quotes - April 2009
A monthly thread for posting any interesting rationality-related quotes you've seen recently on the Internet, or had stored in your quotesfile for ages.
* Please post all quotes separately (so that they can be voted up (or down) separately) unless they are strongly related/ordered.
*... |
e9561dcc-98c7-425e-b160-cf2b08e1f0e9 | trentmkelly/LessWrong-43k | LessWrong | FROM IA CODE TO HUMAN VALUES –
A construction from MaxEnt Informational Efficiency in 4 questions
With information theory, an AI can reduce complex data to 5% and reconstruct it with 95% functional fidelity; these are latent vectors. Maybe we could apply a bit of that to our latent values..
This document introdu... |
7364d7f3-22d0-4717-b078-205ffaddc966 | trentmkelly/LessWrong-43k | LessWrong | Upcoming meet-ups
There are upcoming irregularly scheduled meet-ups in:
* Bangalore: Sunday June 19th at 4pm
* Cambridge, MA: Tuesday June 14th at 7pm
* DC: Sunday June 12th at 1pm
* Edinburgh: Saturday June 11 (I think, the announcement doesn't specify) at 2pm
* Fort Collins: Wednesday June 15th at 7pm
* Houst... |
aab48a0c-9eaf-4bc5-8698-3ed435960c46 | trentmkelly/LessWrong-43k | LessWrong | [LINK] The P + epsilon Attack (Precommitment in cryptoeconomics)
Vitalik Buterin has a new post about an interesting theoretical attack against Bitcoin. The idea relies on the assumption that the attacker can credibly commit to something quite crazy. The crazy thing is this: paying out 25.01 BTC to all the people who ... |
396f5273-6a9c-4501-bf62-e63a3d8232f9 | trentmkelly/LessWrong-43k | LessWrong | Highlights of Comparative and Evolutionary Aging
Author's Note: the purpose of this sequence is gears, i.e. physiology and molecular/cellular-level mechanisms, not evolution. This post contains only some bare-minimum background information as context for the rest; check out Will Bradshaw's series for a short intro whi... |
4156dccc-af3f-45f5-b042-6d70d7d7d9e2 | trentmkelly/LessWrong-43k | LessWrong | Thoughts On The Relationship Between Life and Intelligence
3rd May 2014: I no longer hold the ideas in this article. IsaacLewis2013 had fallen into something of an affective death spiral around 'evolution' and self-organising systems. That said, I do still hold with my statement at the time that this is 'as one intere... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.