id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
c22d0ecb-c041-41e1-a817-fb9068ae74b2 | trentmkelly/LessWrong-43k | LessWrong | Review: Michel Thomas French (Direct Instruction)
Purpose of Review
Owen’s recent post brought up the topic of optimizing education. One particular approach, Direct Instruction (Misha’s better explanation), claims to have essentially solved the problem. In particular, Direct Instruction (DI) does allegedly not only wo... |
61c58467-4c9a-41a8-9c39-670bc8c48b94 | trentmkelly/LessWrong-43k | LessWrong | Moving to a World Beyond “p < 0.05”
The American Statistician just released a large report that outlines why p-values are problematic and then compiles many potential alternative ways to approach the situation. |
0099e949-a21f-45b2-b8f5-7ab621be4a08 | trentmkelly/LessWrong-43k | LessWrong | Multi-Agent Inverse Reinforcement Learning: Suboptimal Demonstrations and
Alternative Solution Concepts
This research was recently completed within the AI Safety division of the Stanford Existential Risk Initiative and concerns methods for reward learning in multi-agent systems.
Abstract: Multi-agent inverse reinfo... |
a5a94bc1-3bca-444d-8bf7-debadb368ce5 | trentmkelly/LessWrong-43k | LessWrong | Einstein's Arrogance
In 1919, Sir Arthur Eddington led expeditions to Brazil and to the island of Principe, aiming to observe solar eclipses and thereby test an experimental prediction of Einstein’s novel theory of General Relativity. A journalist asked Einstein what he would do if Eddington’s observations failed to m... |
77f3f162-1aee-4b86-9a63-bd7227a75b64 | StampyAI/alignment-research-dataset/blogs | Blogs | NIPS 2017 Report
This year’s NIPS gave me a general sense that near-term AI safety is now mainstream and long-term safety is slowly going mainstream. On the near-term side, I particularly enjoyed [Kate Crawfor... |
57cbbf3e-9135-4caa-a867-1e4f4cd3f4f2 | trentmkelly/LessWrong-43k | LessWrong | Calculating Natural Latents via Resampling
So you’ve read some of our previous natural latents posts, and you’re sold on the value proposition. But there’s some big foundational questions still unanswered. For example: how do we find these natural latents in some model, if we don’t know in advance what they are? Examp... |
39c33c7d-13d4-496b-a8bf-bd1f0ba80fef | trentmkelly/LessWrong-43k | LessWrong | A Conversation with GoD
The following is an inexact transcript of a conversation that happened exactly like this. The scene: a wine bar in Manhattan, on my second (and final) date with a Jewish girl. We’ll call her “Jewish Girl on Date”, or J-GoD for short.
----------------------------------------
J-GoD: You’ve chan... |
2c383d8a-b62f-4f0c-a8af-36804cf1842d | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Wrapping Up
Today's post, Wrapping Up was originally published on December 7, 2008. A summary:
> A summary of what Hanson believes to be the key unresolved issues.
Discuss the post here (rather than in the comments to the original post).
This post is part of the Rerunning the Sequences series, where... |
5030549e-e574-40a8-b4a3-dc326f943c0c | trentmkelly/LessWrong-43k | LessWrong | Wasted life
It's just occurred to me that, giving all the cheerful risk stuff I work with, one of the most optimistic things people could say to me would be:
"You've wasted your life. Nothing of what you've done is relevant or useful."
That would make me very happy. Of course, that only works if it's credible. |
7411931c-dae9-4220-99c2-eeee44fb5abb | trentmkelly/LessWrong-43k | LessWrong | Exploring Decision Theories With Counterfactuals and Dynamic Agent Self-Pointers
This is a follow-up to A Possible Resolution To Spurious Counterfactuals, which was addressing a technical problem in self-proof. See the original post for the suggestion provided for a solution to the 5 and 10 problem as described in the... |
223a7c91-458c-446a-8345-2b07d7c5badf | trentmkelly/LessWrong-43k | LessWrong | Open Thread February 25 - March 3
If it's worth saying, but not worth its own post (even in Discussion), then it goes here.
|
d897974e-b571-4c43-8125-bd401b7a75b9 | StampyAI/alignment-research-dataset/aisafety.info | AI Safety Info | Can you give an AI a goal which involves “minimally impacting the world”?
This is actually an active area of AI alignment research, called *[Impact Measures](https://www.alignmentforum.org/tag/impact-measures)*. It's not trivial to formalize in a way which won't predictably go wrong (entropy minimization likely leads ... |
5e4619ea-346f-4ec3-83f4-39c5cf6cddd1 | trentmkelly/LessWrong-43k | LessWrong | Privacy
Follow-up to: Blackmail
[Note on Compass Rose response: This is not a response to the recent Compass Rose response, it was written before that, but with my post on Hacker News I need to get this out now. It has been edited in light of what was said. His first section is a new counter-argument against a partic... |
a8073128-c456-4136-bfda-022d26fddd1e | trentmkelly/LessWrong-43k | LessWrong | How do you survive in the humanities?
Two years ago, I fulfilled a huge part of my dream of doing what I love and started studying creative writing full time. This program is run by a humanities department, so I knew I'd have to stomach epistemic nonsense from time to time, which most of the time I can do while remind... |
11e9c2de-3e4b-4193-b3e8-1e9176d82d11 | trentmkelly/LessWrong-43k | LessWrong | NYC Winter Megameetup, Event RSVPs
I've just posted two facebook events for The Winter Solstice Megameetup, the weekend of December 15th-16th.
One is for the Solstice Celebration - a Saturday night of ritual, song, stories and dance, catering to both Less Wrong-folk as well as other anyone with rational/humanist/futu... |
b5c5a1f6-354c-4e8d-a79a-5e3edb7bb05c | trentmkelly/LessWrong-43k | LessWrong | Some Comments on Recent AI Safety Developments
Overview of New Developments
Edit (4th of December, 2024): OpenAI has now signed up with Anduril, fulfilling my prediction that all three major AI developers will enter into agreements with the US military. See https://www.anduril.com/article/anduril-partners-with-openai-... |
a633cab5-f48a-477f-a9ea-c6040b61e13f | trentmkelly/LessWrong-43k | LessWrong | Meetup : San Antonio Meetup
Discussion article for the meetup : San Antonio Meetup
WHEN: 03 April 2016 03:00:00PM (-0500)
WHERE: 12651 Vance Jackson Rd #118, San Antonio, TX 78230
Bubble tea, frozen yogurt, and discussion at Yumi Berry. All are welcome.
Meetup to discuss rationality and all things LessWrong and me... |
0bfb242d-f766-4952-b42f-ceef852ad803 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | The Catastrophic Convergence Conjecture
![](http... |
24de8734-56f1-46da-b9b0-9e035483353d | trentmkelly/LessWrong-43k | LessWrong | Wits and Wagers
Wits and Wagers is apparently a board game, where players compete to be well-calibrated with respect to their trivia knowledge. I haven't played it.
Has someone else here played it? If so, what was your experience? Would it be good rationalist/bayesian training?
|
bf454f4c-7521-4a74-bb60-8ae750321167 | trentmkelly/LessWrong-43k | LessWrong | Luna Lovegood and the Chamber of Secrets - Part 12
"Stupefy," Professor Lockhart said.
Lord Voldemort spat a verbal non-somatic counterspell. He dodged too, just in case.
"Do not do that again," said Lord Voldemort.
Lord Voldemort cast another non-somatic spell. Animated skeleton hands grew from his wrists. He pick... |
f2d0ead6-fe64-4c37-acd7-0e63dafe5fef | StampyAI/alignment-research-dataset/arxiv | Arxiv | Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation
1 Introduction
---------------
For real-world decision systems such as autonomous vehicles, accuracy is not the only performance requirement and it often comes second to reliability, robustness, an... |
7927373e-da43-4702-9d74-dc3e444e89f9 | trentmkelly/LessWrong-43k | LessWrong | Your existence is informative
Cross posted from Overcoming Bias. Comments there.
***
Warning: this post is technical.
Suppose you know that there are a certain number of planets, N. You are unsure about the truth of a statement Q. If Q is true, you put a high probability on life forming on a given arbitrary planet.... |
a1170aa8-393d-4b75-ab7f-a66f552e51cd | trentmkelly/LessWrong-43k | LessWrong | POC || GTFO culture as partial antidote to alignment wordcelism
There is an important asymmetry in reception for prophets. Go read that post first if you haven't.
For those who don't want to, the gist is: Given the same level of specificity, people will naturally give more credit to the public thinker that argues tha... |
518480ac-8d3a-4ef6-9bf0-0995f9d63519 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Saint Petersburg meetup. Habits and spring.
Discussion article for the meetup : Saint Petersburg meetup. Habits and spring.
WHEN: 18 April 2015 06:00:00PM (+0300)
WHERE: Санкт-Петербург, Невский просп., 54
Place updated Saturday, 18.04.15.
From 18:00 and for about four hours.
It would be in 'Subway' cafe... |
ed43fb94-aa5c-4e81-9d3b-261ca6d725b0 | trentmkelly/LessWrong-43k | LessWrong | Welcome to Seattle Rationality [Edit With Your Details]
(The following are our suggestions for what kind of information is best to include in the welcome post of your group, feel free to replace them with whatever you think is best)
What kind of events does your group usually run? What does it usually do?
How freque... |
14691843-6bf7-4263-aa41-57f53956039c | trentmkelly/LessWrong-43k | LessWrong | The metaphor you want is "color blindness," not "blind spot."
It's genuinely possible that the title is all you need; I was tempted to write nothing further. Feel free to take ten seconds and see if it's already clicked. If not, read on.
----------------------------------------
When something is in your literal bl... |
9dd5438e-37fe-4bfd-9005-540be18d3699 | trentmkelly/LessWrong-43k | LessWrong | Meta is hiring for LLM red teaming position
Apply at the link.
We're expanding our red team, whose job it is to try breaking our LLMs to make them exhibit unexpected and unsafe behaviors. Note that one of the requirements for this specific position is a PhD in linguistics. If you have prior red teaming experience (pr... |
74712475-5a4e-40dd-aeb2-b13afeed95a5 | trentmkelly/LessWrong-43k | LessWrong | Optimisation Measures: Desiderata, Impossibility, Proposals
Previously: Towards Measures of Optimisation
When thinking about optimisation processes it is seductive to think in information-theoretic terms.
Is there some useful measure[1] of 'optimisation' we can derive from utility functions or preference orderings, ... |
53cbb0b5-4e75-467c-bc66-886d0e555b0e | trentmkelly/LessWrong-43k | LessWrong | Mech Interp Challenge: August - Deciphering the First Unique Character Model
I'm writing this post to advertise the second in the sequence of monthly mechanistic interpretability challenges (the first to be posted on LessWrong). They are designed in the spirit of Stephen Casper's challenges, but with the more specific... |
d1260135-a79f-457d-97c5-2f3587d7c995 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Epistemic status: Practising thinking aloud. There might be an important question here, but I might be making a simple error.There is a lot of variance in general competence between species. Here is the standard Bostrom/Yudkowsky graph to display this notion.There's a sense that while some mice are more genetically fi... |
02fb80ca-a6e2-45bf-9ed2-a324a3c23dff | trentmkelly/LessWrong-43k | LessWrong | How to stay concentrated for a long period of time?
I find it nearly impossible to focus on anything more than 2+ hours straight. Even if I enjoy an activity, I end up being distracted by a hell lot of things or just being too exhausted to continue doing it.
The situation is only getting worse if I have a task that i... |
06d102e3-1a7f-410f-b43b-ef70daa4603a | trentmkelly/LessWrong-43k | LessWrong | Bloggingheads: Yudkowsky and Horgan
I appear today on Bloggingheads.tv, in "Science Saturday: Singularity Edition", speaking with John Horgan about the Singularity. I talked too much. This episode needed to be around two hours longer.
One question I fumbled at 62:30 was "What's the strongest opposition you've seen ... |
cf8cb14c-f93a-48c1-a2a5-744be088ddaa | trentmkelly/LessWrong-43k | LessWrong | Breaking down the MEAT of Alignment
Preamble
This post is my attempt to try and organise some thinking about AI alignment in a way that hopefully acts as a partial-overview to some of the core ideas and approaches. It is mostly a review of existing ideas arranged with some light opinions thrown in. The goal is that th... |
4e5f1020-3391-43df-b87a-0b2ef432129d | StampyAI/alignment-research-dataset/arxiv | Arxiv | AI Development for the Public Interest: From Abstraction Traps to Sociotechnical Risks
I Introduction
---------------
Recent years have seen an increasing public awareness of the profound implications of widespread artificial intelligence (AI) and large scale data collection. It is now common for both large tech co... |
47f51f28-8295-4660-9793-7192a18fccd4 | trentmkelly/LessWrong-43k | LessWrong | Transcription of Eliezer's January 2010 video Q&A
Spurred by discussion of whether Luke's Q&A session should be on video or text-only, I volunteered to transcribe Eliezer's Q&A videos from January 2010. I finished last night, much earlier than my estimate, mostly due to feeling motivated to finish it and spending mor... |
01f45d6b-b227-431e-8d50-f4e112f93132 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | DSLT 3. Neural Networks are Singular
*TLDR; This is the third main post of* [*Distilling Singular Learning Theory*](https://www.lesswrong.com/s/czrXjvCLsqGepybHC) *which is introduced in* [*DSLT0*](https://www.lesswrong.com/posts/xRWsfGfvDAjRWXcnG/dslt-0-distilling-singular-learning-theory)*. I explain that neural net... |
f8dd97db-0b13-4e50-add5-6eda0d2efa80 | trentmkelly/LessWrong-43k | LessWrong | Just for fun: Computer game to illustrate AI takeover concepts?
I play Starcraft:BW sometimes with my brothers. One of my brothers is much better than the rest of us combined. This story is typical: In a free-for-all, the rest of us gang up on him, knowing that he is the biggest threat. By sheer numbers we beat him do... |
332bede2-f300-4a5a-b642-c76bd71c9d71 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Announcing the 2023 PIBBSS Summer Research Fellowship
*What can we learn from biological and social systems about designing beneficial AI systems?*
We are, once again, pleased to announce the PIBBSS Research Fellowship program.
*Principles of Intelligent Behavior in Biological and Social Systems* (PIBBSS) aims to f... |
535b6e74-6011-4f9e-9c17-ee4c1af98a08 | trentmkelly/LessWrong-43k | LessWrong | Consistencies as (meta-)preferences
> Do I contradict myself? Very well then I contradict myself, (I am large, I contain multitudes.)
> Walt Whitman
It is good for our decision processes to be time-consistent, transitive, and independent.
Or as Steve Omohundro apparently put it:
> If you prefer being in Berkeley t... |
17477140-5076-480e-96d2-b5ce3c14e774 | trentmkelly/LessWrong-43k | LessWrong | Is ChatGPT TAI?
Do you count ChatGPT and/or other similar systems (e.g. codex) as transformative AI? I would think so since it has a very fast adoption (million users in 5 days) and is apparently sufficiently more useful on some queries than Google that they had to declare "code red" - a possible threat to their core... |
9cc4a649-ada0-4cd4-89db-2ecc2349aa12 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | [Video] Intelligence and Stupidity: The Orthogonality Thesis
> Can highly intelligent agents have stupid goals?
> A look at The Orthogonality Thesis and the nature of stupidity.
>
>
A good popular introduction to the Orthogonality Thesis from [Robert Miles](https://www.youtube.com/channel/UCLB7AzTwc6VFZrBsO2uc... |
87227c6f-040e-4219-939a-e275cd584b1d | trentmkelly/LessWrong-43k | LessWrong | Work harder on tabooing "Friendly AI"
This is is an outgrowth of a comment I left on Luke's dialog with Pei Wang, and I'll start by quoting that comment in full:
Luke, what do you mean here when you say, "Friendly AI may be incoherent and impossible"?
The Singularity Institute's page "What is Friendly AI?" defines ... |
2bf8a89f-a981-40a7-a7c1-a920b59a9ba7 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | On language modeling and future abstract reasoning research
Hi everyone! Here I link to a sketch of my thoughts on how recent advances in language modeling may be connected, or lead, to future advances in developing machine learning models with abstract reasoning capabilities.
This was done as a side project last yea... |
74cb2dca-9f7b-471b-94d3-b480094c418f | trentmkelly/LessWrong-43k | LessWrong | The Inter-Agent Facet of AI Alignment
We argue that intent alignment and capability robustness do not capture the full “chain of command” (i.e., “alignment” without any qualifier) from the programmer's intentions to an AI agent’s real-world impact, but stops at the stage where the agent performs its actions. We argue ... |
334470cd-42e8-44ee-9fad-42283688404f | trentmkelly/LessWrong-43k | LessWrong | New York Restaurants I Love: Pizza
Previously in series: New York Restaurants I Love: Breakfast
Previously in pizza: Restaurant Guide 2: Pizza
If you don’t live in and aren’t visiting New York, and want to know how to find good pizza, refer to the guide above. It tells you what you need to know.
This series is abou... |
1408b1b7-9f01-4689-b2b9-6bc0622b4319 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Superintelligence 15: Oracles, genies and sovereigns
*This is part of a weekly reading group on [Nick Bostrom](http://www.nickbostrom.com/)'s book, [Superintelligence](http://www.amazon.com/Superintelligence-Dangers-Strategies-Nick-Bostrom/dp/0199678111). For more information about the group, and an index of posts so ... |
efb1f846-17f1-4e11-b1de-25579b7f8c67 | trentmkelly/LessWrong-43k | LessWrong | Shifting guilt
The posts so far have been less about confronting guilt, and more about different tools for shifting it. This is a valuable skill to generalize.
The posts in this series have developed three such tools for shifting guilt. In this post, I'll recast those three tools as members of the same family, so tha... |
6aa2307f-3f1f-46db-bdd0-39d06e17047c | trentmkelly/LessWrong-43k | LessWrong | Distillation Robustifies Unlearning
Current “unlearning” methods only suppress capabilities instead of truly unlearning the capabilities. But if you distill an unlearned model into a randomly initialized model, the resulting network is actually robust to relearning. We show why this works, how well it works, and how t... |
f0b84165-d7af-4345-aebd-99b08a8f8a9a | trentmkelly/LessWrong-43k | LessWrong | Babble Challenge: 50 thoughts on stable, cooperative institutions
In a recent LessWrong question Anna Salamon asks “Where did stable, cooperative institutions come from (like bridges that stay up; the rule of law; or Google)?” She also worries that “the magic that used to enable such cooperative institutions is fading... |
cfd47f2e-668f-4185-8e2a-f562ce81d01c | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Meta-preferences two ways: generator vs. patch
In my last post ([Gricean communication and meta-preferences](https://www.lesswrong.com/posts/8NpwfjFuEPMjTdriJ/gricean-communication-and-ai)), I talked about the infinite tower of meta-preferences that in principle could be applied by humans. Example meta-preference: "I'... |
bf75a8bb-e6aa-4917-9322-318718302d44 | trentmkelly/LessWrong-43k | LessWrong | Some Thoughts on AI Art
I was recently talking with a Daniel Kokotajlo about AI art. It turned out that he and I initially disagreed about ethical questions, but by the end of the conversation, I had somewhat won him over to my position.
I have the vague impression that a lot of people (on the technology side) haven'... |
31f2c348-8df0-4a31-a282-8ad6bb00957b | trentmkelly/LessWrong-43k | LessWrong | "Can you keep this confidential? How do you know?"
Pet peeve about privacy: I think people are woefully inadequate at asking, and answering, "Can you keep this confidential?"
Disclosure: I am not inherently great at keeping information private. By default, if a topic came up in conversation, I would accidentally some... |
c0824221-dcdf-4050-b4d9-1ade897a1708 | trentmkelly/LessWrong-43k | LessWrong | Dealing with a Major Personal Crisis II
This is the second post about Dealing with a Major Personal Crisis. The recount of the crisis is complete now. Please continue reading there but comment here.
The reasons for posting it this way are explained at the end of the link. I hope this approach does what I want it to.
... |
b8af7c38-912e-4bfd-ae84-e36b2b2dc798 | trentmkelly/LessWrong-43k | LessWrong | Some thoughts on vegetarianism and veganism
I feel pretty confused about whether I, as an effective altruist, should be vegetarian/vegan (henceforth abbreviated veg*n). I don’t think I’ve seen anyone explicitly talk about the arguments which feel most compelling to me, so I thought I’d do that here, in a low-effort wa... |
354609fb-4f93-498c-a480-4cd1445d0da7 | trentmkelly/LessWrong-43k | LessWrong | Was the K-T event a Great Filter?
I've been wondering about this question for a while, but some new research released today reminded me of it:
> The seasonal timing of the catastrophic end-Cretaceous bolide impact places the event at a particularly sensitive stage for biological life cycles in the Northern Hemisphere... |
1a414b6d-7139-4e7c-a0a6-3c9a424db2f7 | trentmkelly/LessWrong-43k | LessWrong | "Spiritual" techniques that actually work thread
This thread is for:
- Perfectly natural and functional ideas that came from a spiritual, religious, occultist, parapsychologist etc. source (perhaps with some "baggage")
- Techniques that are bit difficult to explain and may be seen by the gullible as magic, but... |
a37eea15-d7d2-463f-859d-b2ee9d565e86 | trentmkelly/LessWrong-43k | LessWrong | How to treat problems of unknown difficulty
Crossposted from the Global Priorities Project
This is the first in a series of posts which take aim at the question: how should we prioritise work on problems where we have very little idea of our chances of success. In this post we’ll see some simple models-from-ignorance... |
48666bff-0598-438b-b397-d7a4ec757928 | trentmkelly/LessWrong-43k | LessWrong | Announcing “Key Phenomena in AI Risk” (facilitated reading group)
TLDR: “Key Phenomena in AI Risk” is a 7 week-long, facilitated reading group. It is aimed at people interested in conceptual AI alignment research, in particular from fields such as philosophy, systems research, biology, cognitive and social sciences.
... |
d137ebc0-35c5-4b32-8a90-3b5d0374378d | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Plan for mediocre alignment of brain-like [model-based RL] AGI
*(This post is a more simple, self-contained, and pedagogical version of*[*Post #14*](https://www.lesswrong.com/posts/QpHewJvZJFaQYuLwH/intro-to-brain-like-agi-safety-14-controlled-agi) *of*[*Intro to Brain-Like AGI Safety*](https://www.lesswrong.com/s/Hzc... |
0806acf4-cd17-4870-85d7-7d72bd2d5b59 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Transformative AI issues (not just misalignment): an overview
If this ends up being the [most important century](https://forum.effectivealtruism.org/s/isENJuPdB3fhjWYHd) due to advanced AI, what are the key factors in whether things go well or poorly?
(Click to expand) More detail on why AI could make this the m... |
eecdef5c-0939-4e8a-be3c-ff0f88944330 | trentmkelly/LessWrong-43k | LessWrong | [LINK] Higher intelligence correlates with greater cooperation
The result is from 2008, but it's new to me. Abstract:
> A meta-study of repeated prisoner’s dilemma experiments run at numerous universities suggests that students cooperate 5% to 8% more often for every 100 point increase in the school’s average SAT sco... |
62f31bf6-48a7-4997-ad12-b2a38f45cab7 | trentmkelly/LessWrong-43k | LessWrong | On the Loss and Preservation of Knowledge
This is an excerpt from the draft of my upcoming book on great founder theory. It was originally published on SamoBurja.com. You can access the original here.
Let’s say you are designing a research program, and you’re realizing that the topic you’re hoping to understand is ... |
efcd3825-72c6-40a5-9f72-7d30b12ce445 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Curiosity Killed the Cat and the Asymptotically Optimal Agent
[Here's](https://e563b909-928d-4538-97f1-e473938f7515.filesusr.com/ugd/421795_b6f900ffdc194b6b88c25bbb48fb5b63.pdf) a new(ish) paper that I worked on with Marcus Hutter.
If an agent is exploring enough to be guaranteed strong performance in the limit, that... |
fde7de2f-ffd8-4413-a00b-2dd5ecbaf1de | trentmkelly/LessWrong-43k | LessWrong | Why not? potato chips in a box edition
In reviewing my year I came across these photos of a box of potato chips I took in January on a plane. I took them because it seemed so much better to me than chips in a bag:
The corners of the box opened out, so that it was like a bowl.
As usual, I wonder, is it actually bet... |
b072f619-12b8-41df-856d-a34fb0613021 | trentmkelly/LessWrong-43k | LessWrong | Kelly isn't (just) about logarithmic utility
Edit: The original version of this was titled without the "(just)". I also regret the first 4 lines, but I'm leaving them in for posterity's sake. I also think that johnswentworth's comment is a better tl;dr than what I wrote.
Deep breath.
Kelly isn't about logarithmic ut... |
e068e105-fef0-439a-bb68-3fea5bb91cb3 | trentmkelly/LessWrong-43k | LessWrong | Notes on Awe
This post examines the virtue related to awe. As with my other posts in this sequence, I’m less interested in breaking new ground and more in gathering and synthesizing whatever wisdom I could find on the subject. I wrote this not as an expert on the topic, but as someone who wants to learn more about it.... |
a31b4b2a-2adb-4fa2-87cd-c2e6145db9e6 | trentmkelly/LessWrong-43k | LessWrong | The Value Is In the Tails
I have a friend who makes a (great) living as a professional gambler. He's originally from outside the US, but was living there during 2016 and, like everyone else in our friend group, started following the election. Since he loves to gamble, he also decided to bet on the election.
I'm not s... |
39be3019-f949-4e1e-b8c2-55f50ff0aa63 | trentmkelly/LessWrong-43k | LessWrong | "Copilot" type AI integration could lead to training data needed for AGI
TLDR:full task completion training data will soon be available, leading to much more capable agentic AI
Capabilities predictions:
* Agentic AIs for all white collar tasks
* creative problem solving might be solved
Business predictions:
* M... |
1fc70859-6d76-4564-8690-1b39d0ad24d5 | trentmkelly/LessWrong-43k | LessWrong | What are concrete examples of potential "lock-in" in AI research?
I had some colleagues watch Ben Garfinkel's talk, "How sure are we about this AI stuff?", which among other things, pointed out that it's often difficult to change the long-term trajectory of some technology. For instance, electricity, the printing pres... |
6d6e9a6b-a3c4-49c8-97a3-e8e4f05dbd7e | LDJnr/LessWrong-Amplify-Instruct | LessWrong | ""Poets say science takes away from the beauty of the stars—mere globs of gas atoms. Nothing is "mere". I too can see the stars on a desert night, and feel them. But do I see less or more? "The vastness of the heavens stretches my imagination—stuck on this carousel my little eye can catch one-million-year-old light. A ... |
b7232edc-fc25-4f28-8072-da8bdc4f49a4 | trentmkelly/LessWrong-43k | LessWrong | Carving up problems at their joints
Imagine looking at flower. Depending on the lighting conditions and some other factors, you see the flower with different levels of detail. If you take a picture and project it onto a low-resolution screen, instead of a flower you might just see colored boxes that barely capture the... |
316edbf6-3095-4ef9-9a51-4d2dcb99a670 | trentmkelly/LessWrong-43k | LessWrong | [Link] AI advances: computers can be almost as funny as people
"Our model significantly outperforms a competitive baseline and generates funny jokes 16% of the time, compared to 33% for human-generated jokes."
From this paper:
Unsupervised joke generation from big data
Sasa Petrovic and David Matthews
The 51st An... |
c5a44012-902b-4611-96b3-b036b6170627 | StampyAI/alignment-research-dataset/blogs | Blogs | questions about the cosmos and rich computations
questions about the cosmos and rich computations
------------------------------------------------
**computation**: a running state of any [model of computation](https://en.wikipedia.org/wiki/Model_of_computation); for example, a specific [SKI calculus expression](http... |
e4d05d65-848e-45ba-930c-9b2e9dcaf75c | trentmkelly/LessWrong-43k | LessWrong | How do new models from OpenAI, DeepMind and Anthropic perform on TruthfulQA?
Authors: Owain Evans, Stephanie Lin (Oxford), Jacob Hilton (OpenAI)
NB: Updated (May 14) with additional results
(see section "New Results" near the end)
Overview
In September 2021, we released a benchmark (TruthfulQA) to measure th... |
9f88f527-c1d9-4e76-a5c8-556ed216fced | trentmkelly/LessWrong-43k | LessWrong | How can an AI demonstrate purely through chat that it is an AI, and not a human?
In the latest William Gibson novel Agency, a bunch of human characters are constantly told exactly what to do by a superhuman AI in order to have everything turn out for the best. They accept the notion that this character, who they only ... |
05b64335-73f1-4033-85ce-2106c116ddce | trentmkelly/LessWrong-43k | LessWrong | Did the fonts change?
I feel like some fonts may have changed on lesswrong recently. Might just be my system, but I think the fonts of post titles on the homepage and maybe answers to questions changed? |
c66883ad-43c7-406f-bfca-31928975e2be | trentmkelly/LessWrong-43k | LessWrong | How easily can we separate a friendly AI in design space from one which would bring about a hyperexistential catastrophe?
(I've written about this in my Shortform and may regurgitate some stuff from there.)
Eliezer proposes that we separate an AI in design space from one that would constitute a fate worse than death... |
4f70e462-cf2f-4aa6-9d28-9ac663cdcf18 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | 'simulator' framing and confusions about LLMs
Post status: pretty rough + unpolished, thought it might be worthwhile getting this out anyway
I feel like I've encountered various people having misunderstandings of LLMs that seem to be related to using the 'simulator' framing. I'm probably being horrendously uncha... |
9e70c733-a803-44f7-a00c-72f3c14c9e46 | trentmkelly/LessWrong-43k | LessWrong | Weekly LW Meetups: Austin, Brussels, Durham, London, Melbourne, NYC, Paderborn, Vancouver
This summary was posted to LW Main on Dec 14th, and has been moved to discussion. The following week's summary is here.
There are upcoming irregularly scheduled Less Wrong meetups in:
* Brussels meetup: 15 December 2012 01:00P... |
c0b94e4d-5700-49ae-9c92-2cec7875fd7e | trentmkelly/LessWrong-43k | LessWrong | A Kick in the Rationals: What hurts you in your LessWrong Parts?
A month or so ago I stumbled across this. It's a blog piece by one Robert Lanza M.D., a legitimate, respected biologist who has made important contributions to tissue engineering, cloning and stem cell research. In his spare time, he is a crackpot.
I ... |
70189217-6559-45fd-9ee8-1e5f77f40fea | trentmkelly/LessWrong-43k | LessWrong | Notes on "Bioterror and Biowarfare" (2006)
Cross-posted from the EA Forum
I recently finished reading Malcolm Dando’s 2006 book Bioterror and Biowarfare: A Beginner’s Guide, following Darius Meissner’s recommendation. I’d recommend the book for people who want to learn more about bioterror, biowarfare, and/or chemica... |
a6d5a539-0df2-434c-86af-48ee6b57a257 | StampyAI/alignment-research-dataset/special_docs | Other | Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small
Published as a conference paper at ICLR 2023
INTERPRETABILITY IN THE WILD:ACIRCUIT FOR
INDIRECT OBJECT IDENTIFICATION IN GPT-2 SMALL
Kevin Wang∗, Alexandre Variengien*, Arthur Conmy*, Buck Shlegeris†, Jacob Steinhardt†‡§
†Redwood... |
b6bc8f8f-9b1b-4c4f-98d6-86dca9a446cc | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Quantum immortality: Is decline of measure compensated by merging timelines?
I wrote an [article](https://docs.google.com/document/d/1Y8uvR4rxR8LMqtIjO0Eho5JzCMNR9KU39Yo00en09gM/edit?usp=sharing) about the quantum immortality which, I know, is a controversial topic, and I would like to get comments on it. The interest... |
f77fde96-aa6f-4dfa-9ae4-cfdddf2a6210 | trentmkelly/LessWrong-43k | LessWrong | A Quick Guide to Confronting Doom
Within the last two weeks, two sets of things happened: Eliezer Yudkowsky shared a post expressing extreme pessimism about humanity's likelihood of surviving AGI, and a number of AI research labs published new, highly impressive results. The combination of these two has resulted in a ... |
8f94aa10-5a8c-46a1-b853-2e6fcb1bcbe9 | trentmkelly/LessWrong-43k | LessWrong | Rationality Quotes 15
"Who thinks they're not open-minded? Our hypothetical prim miss from the suburbs thinks she's open-minded. Hasn't she been taught to be? Ask anyone, and they'll say the same thing: they're pretty open-minded, though they draw the line at things that are really wrong."
-- Paul Graham
"In ... |
e086bd4b-c505-4b96-9b1c-3863c8d642da | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Responsible Scaling Policies Are Risk Management Done Wrong
Summary
=======
TLDR
----
Responsible Scaling Policies (RSPs) have been [recently](https://evals.alignment.org/blog/2023-09-26-rsp) [proposed](https://www.anthropic.com/index/anthropics-responsible-scaling-policy) as a way to keep scaling frontier large lan... |
3a7f1ef8-096a-425e-9055-4de693a22a24 | trentmkelly/LessWrong-43k | LessWrong | Do you know any human-human communication models?
//Update: Zip version of my question using an analogy with physics:
In physics we have friction. Friction is a very complex process and creating a fully working model that works in all conditions is very complicated. But, in most cases, we can approximate friction wit... |
b44958f6-bb43-4725-b8b2-52940ddbadc1 | trentmkelly/LessWrong-43k | LessWrong | Book Review: The Beginning of Infinity
This is a crosspost from my personal website. Inspired by: Naval, If Sapiens Were a Blogpost and Brett Hall’s podcast.
Many people have recommended the book The Beginning of Infinity: Explanations that Transform the World by David Deutsch to me. I don’t know how, because I can’t... |
0115c0a4-c492-4aac-bee5-caa46bc4784f | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Brains and backprop: a key timeline crux
[Crossposted from [my blog](https://jacoblagerros.wordpress.com/2018/03/09/brains-and-backprop-a-key-timeline-crux/)]
The Secret Sauce Question
=========================
Human brains still outperform deep learning algorithms in a wide variety of tasks, such as playing soccer ... |
b2de3765-20ac-44e3-8e61-35aaa7c7f4b0 | trentmkelly/LessWrong-43k | LessWrong | A few questions about recent developments in EA
Having recognized that I have asked these same questions repeatedly across a wide range of channels and have never gotten satisfying answers for them, I'm compiling them here so that they can be discussed by a wide range of people in an ongoing way.
1. Why has EV made... |
ccf72505-c413-4638-881e-49e9e00fa906 | trentmkelly/LessWrong-43k | LessWrong | Musings on probability
I read this comment, and after a bit of rambling I realized I was as confused as the poster. A bit more thinking later I ended up with the “definition” of probability under the next heading. It’s not anything groundbreaking, just a distillation (specifically, mine) of things discussed here over ... |
4524bd44-97c7-484e-87dd-9f2ec0839028 | trentmkelly/LessWrong-43k | LessWrong | You should just smile at strangers a lot
This is so basic I feel stupid for saying it in such an intellectual place. But most of you guys share my enthusiasm for effective altruism, and here's something really altruistic and really effective that I've been doing for two decades and I think lots of you should do too.
... |
2a2b9ba9-7aca-4ccf-a31f-0220e9385529 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Proxy misspecification and the capabilities vs. value learning race
G Gordon Worley III [recently complained](https://www.alignmentforum.org/posts/sSpu2EABtTTDmBZ6T/g-gordon-worley-iii-s-shortform?commentId=tbj8R6K2q9rfhjtS7) about a lack of precision in discussions about whether Goodhart's Law will present a fatal pr... |
faeeb561-f23a-4555-8716-e98cb2023c28 | trentmkelly/LessWrong-43k | LessWrong | Discontinuous progress in history: an update
I. The search for discontinuities
We’ve been looking for historic cases of discontinuously fast technological progress, to help with reasoning about the likelihood and consequences of abrupt progress in AI capabilities. We recently finished expanding this investigation to 3... |
46649e2d-67bd-499e-8b85-27798e019d65 | trentmkelly/LessWrong-43k | LessWrong | A potentially high impact differential technological development area
Specifically, this is boosting LLMs and Non-RL AI relative to RL AI.
I am making this post because I want to signal boost an observation by porby, which could be lossily compressed as, "Instrumental goals/Instrumental convergence is at best a debat... |
72a60afd-0796-46e7-8226-ce96681b49fa | trentmkelly/LessWrong-43k | LessWrong | Rationality and Video Games
There are two points which I want to cover here. First is about my own game, and second is about raising the sanity waterline through games.
Point one: "Girl with a Heart of"
It's been over a year since I found LW community, and as soon as I finished the Sequences I realized I want to ... |
c19a5afe-05c6-4abd-a0dc-3624a4dcb5dd | trentmkelly/LessWrong-43k | LessWrong | [Altruist Support] Fix the SIAI's website (EDIT: or not. I'll do it)
EDIT: This post no longer reflects my current attitude. I'm now signed up as a volunteer for SIAI and will help them with the website and/or whatever else needs doing. Add a comment or contact me if you're curious as to what my attitude was or why it... |
4c9a802b-b292-4659-8caa-0e59f87ec71d | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Analogies between Software Reverse Engineering and Mechanistic Interpretability
These are notes taken during a call with [Itay Yona](https://mentaleap.ai/), an expert in software/hardware reverse engineering (SRE). Itay gave me an excellent distillation of key ideas and mindsets in the field, and we discussed analogie... |
224e5064-147f-4ef4-a77f-3a0d23db360d | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Concrete experiments in inner alignment
*This post is part of research I did at OpenAI with mentoring and guidance from Paul Christiano.*
The goal of this post is to present my thoughts on some of the sorts of experiments that might be able to be done now that could shed light on the [inner alignment problem](https:... |
2c6ca4c7-5612-49a0-ac0d-6e4fe0c2f238 | trentmkelly/LessWrong-43k | LessWrong | [LINK] Forty Years of String Theory: Reflecting on the Foundations
Those of us interested in "fundamental physics" may find a few interesting tidbits in the latest issue of Springer's Foundations of Physics. It has contributions from the prominent figures in String Theory and related fields, such as the Nobel laureate... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.