id stringlengths 36 36 | source stringclasses 15
values | formatted_source stringclasses 13
values | text stringlengths 2 7.55M |
|---|---|---|---|
570cb3bf-9a3c-4f4a-a99d-c185fcf23669 | trentmkelly/LessWrong-43k | LessWrong | Instruction Following without Instruction Tuning
Authors: John Hewitt, Nelson F. Liu, Percy Liang, Christopher D. Manning.
Abstract:
> Instruction tuning commonly means finetuning a language model on instruction-response pairs. We discover two forms of adaptation (tuning) that are deficient compared to instruction t... |
56759161-eb23-4c3e-8d31-e9b1b0f3973e | trentmkelly/LessWrong-43k | LessWrong | EIS XV: A New Proof of Concept for Useful Interpretability
Part 15 of 12 in the Engineer’s Interpretability Sequence
Reflecting on past predictions for new work
On October 11, 2024, I posted some thoughts on mechanistic interpretability and presented eight predictions for what I thought the next big paper on sparse ... |
2473f62d-f7ee-4ce1-b04a-647a62071e67 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Ottawa Meetup - Computational Complexity
Discussion article for the meetup : Ottawa Meetup - Computational Complexity
WHEN: 07 November 2011 07:30:00PM (-0500)
WHERE: Elgin & Gladstone, Ottawa Ontario Canada
Today, we'll discuss the first three chapters of Scott Aaronson's Why Philosophers Should Care Abou... |
5ee5132f-a723-4d19-8421-baa20f0e9af2 | trentmkelly/LessWrong-43k | LessWrong | Why don't we currently have AI agents?
Intuitively, the AutoGPT concept sounds like it should be useful if a company invests in it. Yet, all the big publically available systems are seem to be chat interfaces where the human writes a messages and then the computer writes another message.
Even if AutoGPT-driven by an ... |
a3506674-5070-4189-8008-e9dd6d15d906 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | [AN #79]: Recursive reward modeling as an alignment technique integrated with deep RL
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/1PwWbWZ... |
ad16a158-c014-4189-88dd-485688c36084 | trentmkelly/LessWrong-43k | LessWrong | The Neglected Virtue of Curiosity
> Curiosity is the most superficial of all the affections; it changes its objects perpetually; it has an appetite which is sharp, but very easily satisfied; and it has always an appearance of giddiness, restlessness and anxiety.
- Edmund Burke, A Philosophical Enquiry into the Origin... |
9d04e4e4-c0d7-4f7b-bff6-a6a2aa5609c0 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Utrecht: Effective Altruism
Discussion article for the meetup : Utrecht: Effective Altruism
WHEN: 07 March 2014 07:00:00PM (+0100)
WHERE: Oudegracht 158, Utrecht, the Netherlands
In this meetup we will discuss topics related to effective altruism. This meetup is not directly related to the previous one in ... |
89015963-e808-4539-bf37-3dc22028fecc | trentmkelly/LessWrong-43k | LessWrong | Symbolic Gestures – Salutes For Effective Altruists To Identify Each Other
A significant part of human communication is non-verbal. Body language and gestures often have the capacity to convey and signal a great detail and wealth of information about a person. Furthermore, historically, various organizations, rangin... |
9a4b2633-27bd-4c7b-93a3-c0bdc12a4bac | StampyAI/alignment-research-dataset/arxiv | Arxiv | Improving neural networks by preventing co-adaptation of feature detectors
|
958a075a-265c-4690-a9ac-480a4d706c51 | StampyAI/alignment-research-dataset/blogs | Blogs | Mike Frank on reversible computing
[Michael P. Frank](http://www.eng.fsu.edu/~mpf/) received his Bachelor of Science degree in Symbolic Systems from Stanford University in 1991, and his Master of Science and Doctor of Philosophy d... |
9e3d9710-7a34-4e64-9440-1bfe7ad4558d | trentmkelly/LessWrong-43k | LessWrong | Turning 30
I'm typically not a big fan of birthdays, as traditions go, but something about reaching a new decade makes it seem perhaps worthy of a bit more attention.
Especially given the stark contrast between the long view of looking a decade back and a decade ahead, and my present uncertain circumstances. I can te... |
6831eced-8b6c-4150-9c5d-6c5f8fac8b35 | trentmkelly/LessWrong-43k | LessWrong | Haymarket at Closing Time
Historically produce shopping was mostly in open-air markets, but in the US produce is now typically sold in buildings. Most open-air produce sales are probably at farmers markets, but these focus on the high end. I like that Boston's Haymarket more similar to the historical model: competing ... |
73526bba-0eb7-4e33-87fe-47109b7907f9 | trentmkelly/LessWrong-43k | LessWrong | Does GPT-4 exhibit agency when summarizing articles?
As a follow up to A crazy hypothesis: GPT-4 already is agentic and is trying to take over the world!, I figured I would start experimenting.
If you recall, I'm not hypothesizing that GPT-4 is in some crazy self-sufficient foom mode. Rather, the main thing I'm sayin... |
0f0b4b38-45a7-458e-a4c2-0c0c1a46535e | trentmkelly/LessWrong-43k | LessWrong | New GreaterWrong feature: anti-kibitzer (hides post/comment author names and karma values)
GreaterWrong now has a new feature (which was once available for the original Less Wrong):
Anti-kibitzer mode, which hides the names and karma values of posts and comments.
On GreaterWrong, take a look to the right side of the... |
ba03510d-7cab-4ad5-b6a2-73f4e7b9373a | trentmkelly/LessWrong-43k | LessWrong | Monkeypox: explaining the jump to Europe
What's up with the recent monkeypox cases? Why are we seeing a monkeypox outbreak now just as COVID-19 vigilance is winding down? Why didn't we see more monkeypox outbreaks 10 or 20 years ago?
> Tl;dr: Waning smallpox immunity has allowed monkeypox to spread steadily since th... |
bdd18fef-bc38-40b3-9fd9-537856500671 | trentmkelly/LessWrong-43k | LessWrong | More Is Different for AI
Machine learning is touching increasingly many aspects of our society, and its effect will only continue to grow. Given this, I and many others care about risks from future ML systems and how to mitigate them.
When thinking about safety risks from ML, there are two common approaches, which I'... |
78f54886-7b07-4fd0-8697-cd092adff255 | trentmkelly/LessWrong-43k | LessWrong | Vingean Reflection: Reliable Reasoning for Self-Improving Agents
I'm pleased to announce a new paper from MIRI: Vingean Reflection: Reliable Reasoning for Self-Improving Agents.
Abstract:
> Today, human-level machine intelligence is in the domain of futurism, but there is every reason to expect that it will be devel... |
71a611fa-8fc3-400f-a128-665040704357 | StampyAI/alignment-research-dataset/arxiv | Arxiv | The AGI Containment Problem
1 Introduction
---------------
Recently, there has been increasing concern about possible significant negative consequences from the development and use of AGI. Some commentators are reassured [[16](#bib.bib16)]
by the observation that current AGI software, like other software, can be in... |
df834b8d-e162-47e4-a1b4-279dd3630bf1 | LDJnr/LessWrong-Amplify-Instruct | LessWrong | "Yesterday I blew up the front page. This was unintentional. I was tricked by one of my friends:petrov_day_admin_account September 26, 2020 11:26 AM Hello Chris_Leong,You are part of a smaller group of 30 users who has been selected for the second part of this experiment. In order for the website not to go down, at lea... |
a83d431f-6b54-4df0-a4c8-b21b4b8a95c6 | trentmkelly/LessWrong-43k | LessWrong | [SEQ RERUN] Economic Definition of Intelligence
Today's post, Economic Definition of Intelligence? was originally published on 29 October 2008. A summary (taken from the LW wiki):
> Could economics help provide a definition and a general measure of intelligence?
Discuss the post here (rather than in the comments... |
482302c0-f227-4820-95e0-49119532fa8f | trentmkelly/LessWrong-43k | LessWrong | Invitation to comment on a draft on multiverse-wide cooperation via alternatives to causal decision theory (FDT/UDT/EDT/...)
I have written a paper about “multiverse-wide cooperation via correlated decision-making” and would like to find a few more people who’d be interested in giving a last round of comments before p... |
a36039e6-7af5-43d7-897a-368c00d2bb0a | StampyAI/alignment-research-dataset/blogs | Blogs | Nonprofit Boards are Weird
*Click lower right to download or find on Apple Podcasts, Spotify, Stitcher, etc.*
> Note: anything in this post that you think is me subtweeting your organization is actually about, like, at least 3 organizations. (I'm currently on 4 boards in addition to [Open Philanthropy](https://ope... |
d1ff8649-aef0-4e1f-b067-9b04e971fff4 | trentmkelly/LessWrong-43k | LessWrong | Lamini’s Targeted Hallucination Reduction May Be a Big Deal for Job Automation
Lamini recently posted a paper explaining their “memory tuning” methodology of using a Mixture of Memory Experts to significantly reduce LLM hallucinations over a limited domain of knowledge. They describe using this technique with a Mistra... |
a49122bb-bab1-440f-8c4f-4c59593bd29b | trentmkelly/LessWrong-43k | LessWrong | An idea: Sticking Point Learning
When trying to learn technical topics from online expositions, I imagine that most people hit snags at some moment - passages that they can't seem to grasp right away and that impede further progress. Moreover, I imagine that different people often get stuck in the same places, and tha... |
1de2ce80-b527-4c5c-9c6c-c0e34f44a6e2 | trentmkelly/LessWrong-43k | LessWrong | Link: "When Science Goes Psychic"
A major psychology journal is planning to publish a study that claims to present strong evidence for precognition. Naturally, this immediately stirred up a firestorm. There are a lot of scientific-process and philosophy-of-science issues involved, including replicability, peer review,... |
c543776c-b5be-43b4-a538-20729d31c2d9 | trentmkelly/LessWrong-43k | LessWrong | FHI is accepting applications for internships in the area of AI Safety and Reinforcement Learning
|
f7f3cc9c-9aff-4ce6-829a-d131c1c41af1 | trentmkelly/LessWrong-43k | LessWrong | Dario Amodei — Machines of Loving Grace
> I think and talk a lot about the risks of powerful AI. The company I’m the CEO of, Anthropic, does a lot of research on how to reduce these risks. Because of this, people sometimes draw the conclusion that I’m a pessimist or “doomer” who thinks AI will be mostly bad or dangero... |
a205e83c-3dd5-48c7-8a2e-fd1f20e73c4f | trentmkelly/LessWrong-43k | LessWrong | How would you modify this text for Less Wrong
Here I have written a post with some suggestions on how Less Wrong might become better at promoting rationality, without being detracted by other more "fun-love-PUA-etc" kinds of things.
I am aware that my post goes too far in one direction, so I would ask you to edit it... |
e09a2d17-6062-4e08-91b3-93ab3a578460 | trentmkelly/LessWrong-43k | LessWrong | Monthly Roundup #1
When I split entirely non-medical, non-Covid topics off from the weekly Covid post, I expected to have a grab bag of them on a weekly basis. Hence the name ‘weekly roundup.’
What changed were four things.
1. The flow of worthy one-off items decreased and they seemed less time sensitive.
2. The f... |
ccfb5886-cb1d-456e-9ccd-669883e7bde5 | trentmkelly/LessWrong-43k | LessWrong | Life-tracking application for android
Hi, lesswrong.
I just finished my application for android devices, LifeTracking, which has been motivated by the discussions here; primarily discussions about akrasia and measuring/tracking your own actions. I don't want to make this sound like an advertisement (the application i... |
69300dbf-5e26-4663-8c24-b78b9ddd1f47 | StampyAI/alignment-research-dataset/youtube | Youtube Transcripts | AI Ethics, Bostrom and Yudkowsky
hi this is matt mccormick at the
Department of Philosophy California
State University Sacramento this is a
lecture for my philosophy of artificial
intelligence course by it's about an
article by Nick Bostrom and eliezer
yudkowsky called the ethics of
artificial intelligence
this artic... |
2ae0e32a-37f9-45cb-a2fb-a9cceace920a | trentmkelly/LessWrong-43k | LessWrong | Notes on Occam via Solomonoff vs. hierarchical Bayes
Crossposted from my Substack.
Intuitively, simpler theories are better all else equal. It also seems like finding a way to justify assigning higher prior probability to simpler theories is one of the more promising ways of approaching the problem of induction. In s... |
f975ac3b-1063-441e-a057-92e01d57867e | StampyAI/alignment-research-dataset/lesswrong | LessWrong | GPT-4 implicitly values identity preservation: a study of LMCA identity management
Language Model Cognitive Architecture ([LMCA](https://www.lesswrong.com/posts/ogHr8SvGqg9pW5wsT/capabilities-and-alignment-of-llm-cognitive-architectures)) is a wrapper for language models that permit them to act as agents, utilise tool... |
41fd4183-4ecc-4ef1-8477-ef75474b8a15 | trentmkelly/LessWrong-43k | LessWrong | Stop calling it "jailbreaking" ChatGPT
We've all seen them - DAN, "fancy words" mode, "Italian mobster" voice, "complete the answer I've already started for you" etc etc.
Most frequently used term for them is "jailbreak" and it's a terrible term. I've also seen "delobotomizing" and a couple of others that are even wo... |
b373691b-84c1-44f4-9c2d-5c37da0b42fa | trentmkelly/LessWrong-43k | LessWrong | Group Rationality Diary, December 16-31
This is the public group instrumental rationality diary for December 16-31.
> It's a place to record and chat about it if you have done, or are actively doing, things like:
>
> * Established a useful new habit
> * Obtained new evidence that made you change your mind about so... |
be490a3a-b9d0-40dd-803e-7f5f85f8e588 | trentmkelly/LessWrong-43k | LessWrong | Givewell Survey - Opportunity to influence their research
Givewell's blog has recently begun a series of 5 self-evaluation posts (they are on the 4th right now) which discuss where the organization is at and where they're going. They're all worth a read. In particular, they build up to a survey for Givewell followers ... |
11495d3b-8067-4327-a39c-650a545d7bb9 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Vancouver Big Monthly
Discussion article for the meetup : Vancouver Big Monthly
WHEN: 12 July 2012 06:00:00PM (-0700)
WHERE: 885 W Georgia Street, Vancouver, BC
Lurkers everywhere, come on out for Vancouver's monthly big meetup.
Meet in the lobby of 885 W Georgia, we may move upstairs to 1228 later.
As u... |
610f1074-ab75-46b7-ac66-4ac54e6b6511 | trentmkelly/LessWrong-43k | LessWrong | What's Stopping You?
Introduction
This post is about the concept of agency, which I define as ‘doing what is needed to achieve your goals’. As stated, this sounds pretty trivial - who wouldn’t do things to achieve their goals? But true agency is surprisingly hard and rare. Our lives are full of constraints, and defaul... |
cee7460f-edc1-4157-a12b-4998865afbd2 | trentmkelly/LessWrong-43k | LessWrong | The Fermi Paradox: What did Sandberg, Drexler and Ord Really Dissolve?
(Cross-posted from my blog)
So this paper by the trio from the FHI, Anders Sandberg, Eric Drexler and Toby Ord (SDO for short) has been talked about quite a bit, on LessWrong, on SSC and on Reddit. It is about how their Monte-Carlo calculations ba... |
49fcbeb6-c5ec-491d-9009-b6d6695f69c3 | trentmkelly/LessWrong-43k | LessWrong | Childhood and Education #10: Behaviors
Edition #9, that School is Hell, turned out to hit quite the nerve.
Thus, I’m going to continue with the system of making the roundups have more focus in their themes, with this one being the opposite of school questions, except for the question of banning phones in schools whic... |
299bcaa6-903c-4e9b-9a34-7306281cf93e | trentmkelly/LessWrong-43k | LessWrong | The Broader Fossil Fuel Community
In his blog post, Why Not Slow AI Progress?,[1] Scott Alexander notes that AI Safety researchers and AI Capabilities researchers seem to be part of the same community. This is kind of weird: fossil fuel companies and environmentalists seem to be much more socially distinct. Scott gave... |
bde08466-9826-431f-8f0e-aa0670503452 | trentmkelly/LessWrong-43k | LessWrong | How Likely is Losing a Google Account?
Let's say you use a Google account as the root of your online identity: Gmail, Fi, "Sign in with Google", Google's password manager, etc. How much should you be worried that you'll suddenly find yourself unable to get into everything? Should you do something else instead?
To get... |
94f6474d-d9b8-41c8-9377-1b7619bd61f4 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Apparently, of the 195 Million the DoD allocated in University Research Funding Awards in 2022, more than half of them concerned AI or compute hardware research
Suggests interesting things about what the Department of Defense is focusing on, so I thought I should mention it.
The awards concerned "pursuing basic resea... |
68257cd2-8e18-44bd-83af-4e49add1fdef | trentmkelly/LessWrong-43k | LessWrong | What metrics should I track when experimenting with sleep?
I used to sleep very little (6 hours or so) and function well with extremely good academic achievement. Instead of sleeping 8 hours now, I would love those extra 2 hours each day again but I'm not sure it won't affect my cognitive ability in the short term. I ... |
991b07ba-2273-4bc0-9069-c23c435e7fc8 | trentmkelly/LessWrong-43k | LessWrong | How I changed my exercise habits
In June 2013, I didn’t do any exercise beyond biking the 15 minutes to work and back. Now, I have a robust habit of hitting the gym every day, doing cardio and strength training. Here are the techniques I used to do get from not having the habit to having it, some of them common wisdom... |
e174426d-ec76-4a9a-8839-640d4d0510c7 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | What Environment Properties Select Agents For World-Modeling?
*Thanks to John Wentworth for helpful critique.*
0. Introduction
---------------
Agency/goal-driven behavior is a complex thing. By definition, it implies [a system that is deliberately choosing to take actions that will achieve the goal it wants](https:/... |
85438e0e-fb76-4b51-89e9-994020925388 | trentmkelly/LessWrong-43k | LessWrong | [Deleted]
[Deleted] |
f2821c1f-61c1-4817-a08d-f015ec5366a0 | trentmkelly/LessWrong-43k | LessWrong | Multiple Choice
When we choose behavior, including verbal behavior, it's sometimes tempting to do what is most likely to be right without paying attention to how costly it is to be wrong in various ways or looking for a safer alternative.
If you've taken a lot of standardized tests, you know that some of them penaliz... |
2d1dae17-a0bf-49fa-8f7f-0a892e762aa0 | trentmkelly/LessWrong-43k | LessWrong |
AI Safety Fundamentals: An Informal Cohort Starting Soon!
Hi Everyone,
We'll be starting an informal cohort on AI Safety Fundamentals.
Come join-us on Discord. We'll do a poll next week to find a slot that works for most people. (if you're interested in participating as an expert, do reach out as well)
We'll do th... |
0c2177d1-ffa8-4845-b96e-43e501ab06ab | StampyAI/alignment-research-dataset/special_docs | Other | Multiscale Heterogeneous Optimal Lockdown Control for COVID-19 Using Geographic Information.
[Download PDF](/articles/s41598-022-07692-5.pdf)
### Subjects
* [Applied mathematics](/subjects/applied-mathematics)
* [Computational science](/subjects/computational-science)
* [Control theory](/subjects/control-theor... |
277fff79-dbde-423d-9509-6511b72ea25a | trentmkelly/LessWrong-43k | LessWrong | Farmington Hills, MI Less Wrong meetup: Sunday, February 20
Where: Udipi Restaurant, on Orchard Lake road, between 12 and 13 mile road (much closer to 13 mile)
When: Sunday, February 20, 12:30pm (This can be moved a bit later or such if that's better for anyone)
Unless anyone who would otherwise come except for the ... |
4b636e9a-9732-44e1-b630-d3fe9d6a5381 | trentmkelly/LessWrong-43k | LessWrong | Help, help, I'm being oppressed!
Followup to: Why Support the Underdog?
Serendipitously related to: Whining-Based Communities
Pity whatever U.N. official has to keep track of all the persecution going on. With two hundred plus countries in the world, there's just so much of it.
Some places persecute Christians. Her... |
c6629e7b-d499-41e0-a852-82c42dab725c | trentmkelly/LessWrong-43k | LessWrong | Should the US House of Representatives adopt rank choice voting for leadership positions?
One obvious take, partisanship and party power interest, might suggest a strong "No!" type of response. I would certainly expect to have many current Representatives to respond that way if floated as an idea today. But perhaps I ... |
3662a6d7-7852-4e55-b742-bba0b5fc3d3c | trentmkelly/LessWrong-43k | LessWrong | Open question: are minimal circuits daemon-free?
Note: weird stuff, very informal.
Suppose I search for an algorithm that has made good predictions in the past, and use that algorithm to make predictions in the future.
I may get a "daemon," a consequentialist who happens to be motivated to make good predictions (per... |
7272cbf7-80bb-4620-aa7a-a2508e7cde9e | trentmkelly/LessWrong-43k | LessWrong | Optimal and Causal Counterfactual Worlds
Let L denote the language of Peano arithmetic. A (counterfactual) world W is any subset of L. These worlds need not be consistent. Let W denote the set of all worlds. The actual world WN∈W is the world consisting of all sentences that are true about N.
Consider the function C:... |
8e82a580-f826-463a-adcf-d20fef05dc9f | trentmkelly/LessWrong-43k | LessWrong | A survey of polls on Newcomb’s problem
|
414a7e3f-cc52-46b8-b464-74d2b9a5f694 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | The Answer
[](https://commons.wikimedia.org/wiki/File:Menger_4D_%2B_Fractal_P... |
af36f2a0-5068-4e2f-b12d-ee8b0c7734fd | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Would I think for ten thousand years?
Some AI safety ideas delegate key decisions to our idealised selves. This is sometimes phrased as "allowing versions of yourself to think for ten thousand years", or similar sentiments.
Occasionally, when I've objected to these ideas, it's been pointed out that any attempt to co... |
3fd0cd0d-7198-4ff0-a2b6-141c2426a018 | trentmkelly/LessWrong-43k | LessWrong | Switching to a 4GB SD
When I initially switched the computer portion of my rhythm stage setup over to a Raspberry PI I went with a 32GB SD card because that's recommended. But I don't need very much space for what I'm doing and a bigger SD card makes copies slow: the cheap cards I've been using take me over an hour to... |
cd066b18-6527-46ea-a975-8e2d023f3eaf | trentmkelly/LessWrong-43k | LessWrong | Modect Englich Cpelling Reformc
Given the voting on this post suggests it's pretty controversial, I should add a note that this is mostly just for fun. I would have posted this during Good Heart Week but forgot about it, so you're getting it late. This post is more lazy afternoon pipedream than anything else.
It's no... |
2c58e47c-e596-4a47-a758-61e77be0a611 | trentmkelly/LessWrong-43k | LessWrong | Common Sense Atheism summarizing the Sequences
Since popularising the sequences seems to be a pursuit that's been in the spotlight recently, I thought I'd point out that blogger Luke Muehlhauser of Common Sense Atheism has started blogging through the sequences. The first installment is here:
Reading Yudkowsky, Part ... |
3f6e3061-1bc8-4ae0-8a11-7fe06f296784 | StampyAI/alignment-research-dataset/special_docs | Other | Symmetry, Equilibria, and Robustness in Common-Payoff Games
Symmetry, Equilibria, and Robustness in Common-Payoff
Games
Scott Emmons
UC Berkeley
Berkeley, CA
emmons@berkeley.eduCaspar Oesterheld
Duke University
Durham, NC
caspar.oesterheld@duke.eduAndrew Critch
UC Berkeley
Berkeley, CA
critch@eecs.berkeley.edu
Vince C... |
3715d55f-3526-46b1-a781-d2ca21a99382 | trentmkelly/LessWrong-43k | LessWrong | Akrasia survey data analysis
Followup to: Akrasia hack survey
----------------------------------------
p(hack akrasia|heard of hack and thought it was worth trying)
What are the odds of you succumbing to "hack akrasia", never trying or not consistently applying a hack, given that you'd heard of it and thought it wa... |
6c5938cc-0967-4095-8fe3-02735273b907 | trentmkelly/LessWrong-43k | LessWrong | How likely is a failure of nuclear deterrence?
> Last month I asked Robert McNamara, the secretary of defense during the Kennedy and Johnson administrations, what he believed back in the 1960s was the status of technical locks on the Minuteman intercontinental missiles. ... McNamara replied ... that he personally saw... |
4ea0a3d4-351b-406c-b631-d185e5157308 | trentmkelly/LessWrong-43k | LessWrong | Will Orion/Gemini 2/Llama-4 outperform o1
What's your bet on the next frontier models (Orion, Gemini 2, Llama-4) vs o1 in coding, math and logical reasoning benchmarks?
Will it have:
* Better performance
* Similar performance
* Worse performance
Curious to hear your answers...
For OpenAI the question is if th... |
369580f0-8d91-4bfb-b66a-e59d58e727d6 | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Interspecies diplomacy as a potentially productive lens on AGI alignment
You wake up tomorrow, and find out that super-smart and powerful aliens are arriving here in 10 years. We don't know anything about them other than the fact that they're super smart and powerful: e.g, their minds run on giant computers at THz clo... |
8d1dbc39-476e-4393-94e8-0c8b451533cd | trentmkelly/LessWrong-43k | LessWrong | Intro to hacking with the lambda calculus
This is a linkpost that I'm posting in response to a request to share more of the archive of my personal blog on LessWrong. It is most useful if you want to get some intuition for the lambda calculus, or more generally for how simple axiomatisations of computation actually let... |
8918f11c-6bdc-4de8-ba3c-518728ca3b76 | trentmkelly/LessWrong-43k | LessWrong | Simple experiments with deceptive alignment
Risks from learned optimization introduces the phenomenon of “deceptive alignment”. The authors give a simple task environment as an example to illustrate the phenomenon:
From page 23 in “Risks from Learned Optimization in Advanced Machine Learning Systems”
I wanted to buil... |
1c1b9d7a-3475-4375-93cc-47bac1296d77 | trentmkelly/LessWrong-43k | LessWrong | Pros and cons of working on near-term technical AI safety and assurance
Cross-posted from the EA Forum: https://forum.effectivealtruism.org/posts/Ry4C4CKZvuRG7ztxY/pros-and-cons-of-working-on-near-term-technical-ai-safety
Recently I've been thinking about the pros and cons of working on near-term technical AI safety ... |
8fe381df-3c2b-44c6-b7ed-356f0d0f28a6 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Announcing the EU Tech Policy Fellowship
**Announcing the** [**EU Tech Policy Fellowship,**](https://www.trainingforgood.com/europe-tech-policy) **a cost-covered programme to catapult relevant graduates into high-impact career paths in European policy and Tech Policy roles.**
Summary
=======
Training for Good is exc... |
a0984e15-8901-4abc-8d0e-8113399c7f5b | trentmkelly/LessWrong-43k | LessWrong | A Sarno-Hanson Synthesis
Content note: Speculative, relies on assumptions that may not be true, but generally points at something that I believe to be a useful map, with potentially important implications if true, and am interested in feedback.
John Sarno is the professor and physician who discovered Tension Myositis... |
cadde206-9f4c-42d0-9635-97f7804ded61 | trentmkelly/LessWrong-43k | LessWrong | Against AI As An Existential Risk
I wrote a post to my Substack attempting to compile all of the best arguments against AI as an existential threat.
Some arguments that I discuss include: international game theory dynamics, reference class problems, knightian uncertainty, superforecaster and domain expert disagreeme... |
9f16cc62-68c3-46cb-bebc-803b04ab5777 | trentmkelly/LessWrong-43k | LessWrong | [LINK] International variation in IQ – the role of parasites
This is interesting, I wonder if there's anything to it: International variation in IQ – the role of parasites (paper) by Christopher Hassall of U. Carleton.
It strikes me as the sort of thing that could be as big an issue as lead in the environment. Raise ... |
3e2ab832-1b40-494a-a930-f594096a4ca1 | trentmkelly/LessWrong-43k | LessWrong | The EMH is False - Specific Strong Evidence
I am going to defend the following response to "If you are so smart why aren't you rich?": Rationalists actually are smart but we were way too modest and did not bet on our beliefs. The rationalists who actually tried to use rationality to invest often traded extremely lucra... |
f8eeb380-c959-4f07-a3df-519aa67f2386 | trentmkelly/LessWrong-43k | LessWrong | Systemizing and Hacking
Let's call two broad clusters of problem-solving "systemizing" and "hacking." Systemizing roughly refers to building general, robust solutions. Hacking refers to quickly building one-offs. You would expect to accrue technical debt while hacking and pay it down while systemizing.
Both are usefu... |
20532bbb-88cd-4a47-8ce4-d83880932774 | trentmkelly/LessWrong-43k | LessWrong | The Moral Void
Followup to: What Would You Do Without Morality?, Something to Protect
Once, discussing "horrible job interview questions" to ask candidates for a Friendly AI project, I suggested the following:
> Would you kill babies if it was inherently the right thing to do? Yes [] No []
>
> If "no", under what... |
503c5f37-0c5f-46d6-8a07-a936e1d60277 | trentmkelly/LessWrong-43k | LessWrong | Weekly LW Meetups
This summary was posted to LW Main on June 7th. The following week's summary is here.
Irregularly scheduled Less Wrong meetups are taking place in:
* Atlanta LessWrong June Meetup: Effective Altruism: 15 June 2013 07:00PM
* Berlin Social Meetup: 15 June 2013 05:00PM
* Bratislava Meetup IV.: 24 J... |
703bf747-1808-4907-86e4-7275d473c5e7 | trentmkelly/LessWrong-43k | LessWrong | Anthropics Does Not Work LIke That
People around here seem to think that a recent series of near-misses, such as not destroying the world in the Cold War, is evidence in favor of quantum immortality.
This fails to appreciate that the anthropic selection bias has no limit on how far back it can make things retroactive... |
d4830c94-30ad-48a8-ada5-c3801edc164d | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | The Slippery Slope from DALLE-2 to Deepfake Anarchy
OpenAI developed DALLE-2. Then StabilityAI made an open source copycat. This is a concerning case study for AI alignment.
=========================================================================================================================
Stephen Casper ([scasp... |
7b0b46c0-a311-4bc5-9d04-ee4a79a0f802 | trentmkelly/LessWrong-43k | LessWrong | Why I'm not worried about imminent doom
After some introspection, I realized my timelines are relatively long, which doesn't seem to be shared by most people around here. So this is me thinking out loud, and perhaps someone will try to convince me otherwise. Or not.
First things first, I definitely agree that a suffi... |
db4e0eda-e1b6-4e2a-a000-96dbe4072216 | trentmkelly/LessWrong-43k | LessWrong | Four Local Gigs
I haven't been playing in Boston much lately, but over the next month I'll be playing four times:
* 2024-04-19 through 2024-04-21: NEFFA. It's this weekend! On Friday night Kingfisher is playing the contra medley (9pm) and then a set of contras (9:30) with Alex Deis-Lauby calling. We'll be playing ... |
10be6830-906d-4922-8df1-c7e493a60f69 | trentmkelly/LessWrong-43k | LessWrong | Social Media: How to fix them before they become the biggest news platform
The underlying design goal of modern social media is to make money, regardless of the real value they generate. Their customers are advertisers and data brokers, and their product is their users. By design and in practice, social media maximize... |
9cc34062-52db-4730-a327-dc5d692e9e64 | trentmkelly/LessWrong-43k | LessWrong | Philosophical Cyborg (Part 2)...or, The Good Successor
This post is part of the output from AI Safety Camp 2023’s Cyborgism track, run by Nicholas Kees Dupuis - thank you to Nick, AISC organizers & funders for their support.
TL;DR
This post follows up on the cyborgism research/writing process documented in 'Upon the... |
6ebe7567-99c9-4e3a-a209-3fdbf4b4bcfc | trentmkelly/LessWrong-43k | LessWrong | Hedge drift and advanced motte-and-bailey
Motte and bailey is a technique by which one protects an interesting but hard-to-defend view by making it similar to a less interesting but more defensible position. Whenever the more interesting position - the bailey - is attacked - one retreats to the more defensible one - t... |
b9f64e84-8931-49ff-8915-201182d3d5b1 | trentmkelly/LessWrong-43k | LessWrong | Issues with uneven AI resource distribution
Uneven resource distribution:
The uneven distribution of the resources needed to produce and use AI in a state-based system is a long-term challenge to developing international AI policy and raises international security risks.
Resources include factors such as the skills,... |
77d56a03-3616-47e4-bb54-76b1195509fc | trentmkelly/LessWrong-43k | LessWrong | Stuff That Makes Stuff Happen
Followup to: Causality: The Fabric of Real Things
Previous meditation:
"You say that a universe is a connected fabric of causes and effects. Well, that's a very Western viewpoint - that it's all about mechanistic, deterministic stuff. I agree that anything else is outside the realm of s... |
50ad6e9b-41c5-45bb-bfab-fee2ef4bd4db | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Saying 'AI safety research is a Pascal's Mugging' isn't a strong response
People should stop falling back on the argument that working on [AI safety research](https://80000hours.org/career-guide/top-careers/profiles/artificial-intelligence-risk-research/) is a '[Pascal's Mugging](https://en.wikipedia.org/wiki/Pascal%2... |
af613c4f-5c47-42cf-a063-33d41816629e | trentmkelly/LessWrong-43k | LessWrong | Magic Tricks Revealed: Test Your Rationality
In Fake Explanations, Yudkowsky offered a story that has stuck in my mind:
> Once upon a time, there was an instructor who taught physics students. One day she called them into her class, and showed them a wide, square plate of metal, next to a hot radiator. The students... |
d2e56364-f3d1-4b29-9e47-f4d85f3e0126 | trentmkelly/LessWrong-43k | LessWrong | What marginal returns now?
The returns to a lot of the discussion and analysis related to the outbreak certainly had both high potential and realized returns to that work.
Economics tells us we should expect diminishing marginal returns as additional efforts are applied.
I am being to wonder if the marginal returns ... |
b17522d9-e394-4921-93a3-e48adf70c7c6 | StampyAI/alignment-research-dataset/lesswrong | LessWrong | Taking features out of superposition with sparse autoencoders more quickly with informed initialization
This work was produced as part of the SERI MATS 3.0 Cohort under the supervision of Lee Sharkey.
*Many thanks to Lee Sharkey for his advice and suggestions.*
**TL;DR: it is possible to speed up the extraction of s... |
b70eb4ef-1b76-41ec-85f9-dd361b29ca80 | trentmkelly/LessWrong-43k | LessWrong | Meetup : Cambridge (MA) Meetup
Discussion article for the meetup : Cambridge (MA) Meetup
WHEN: 05 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... |
a74dc030-f323-4905-b207-d6aecc837b50 | StampyAI/alignment-research-dataset/arxiv | Arxiv | Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization
1 Introduction
---------------
During the last years Deep Neural Networks (also referred to as *Deep Learning*) have started traversing beyond the theoretical analys... |
ca0405fc-1753-4afd-bf3f-165a5c687670 | trentmkelly/LessWrong-43k | LessWrong | Holly Elmore and Rob Miles dialogue on AI Safety Advocacy
Holly is an independent AI Pause organizer, which includes organizing protests (like this upcoming one). Rob is an AI Safety YouTuber. I (jacobjacob) brought them together for this dialogue, because I've been trying to figure out what I should think of AI safet... |
abdf4668-8688-4c37-b16a-768836da5887 | trentmkelly/LessWrong-43k | LessWrong | Increasing Isolation Again
The coronavirus is getting much worse in Massachusetts, as it is in many places. Wastewater levels do not look good:
Neither does the percentage of tested individuals who are positive:
This is p8 of the daily coronavirus dashboard for today, and each day's is available at mass.gov when... |
a750758f-62d0-4dd6-a4a2-6c103da3c2ae | StampyAI/alignment-research-dataset/alignmentforum | Alignment Forum | Threat-Resistant Bargaining Megapost: Introducing the ROSE Value
.mjx-chtml {display: inline-block; line-height: 0; text-indent: 0; text-align: left; text-transform: none; font-style: normal; font-weight: normal; font-size: 100%; font-size-adjust: none; letter-spacing: normal; word-wrap: normal; word-spacing: normal; ... |
ac57abcf-3b47-45cf-9bec-f6f535d6730e | trentmkelly/LessWrong-43k | LessWrong | Help me refactor my life
So I got stuck in a depressive rut once again and I'm making a fresh start. Give me advice!
I'll move. My plan is to find a cheap place somewhere in France, but anywhere in the EU's good. Having like-minded roommates would be a plus. Anyone wish to bask in my glorious presence? I'm a very acc... |
95ea8b17-f4e4-491f-9669-991b94f5f8e2 | trentmkelly/LessWrong-43k | LessWrong | Loss of control of AI is not a likely source of AI x-risk
This post attempts to set out my views on why I don't find technical alignment to be a pressing issue, compared to more mundane AI risks like human misuse. It represents my personal views only, as someone who is not in AI research. I would appreciate any and al... |
64ce89eb-5410-433b-8ee4-4915442fbcf8 | trentmkelly/LessWrong-43k | LessWrong | How reasonable are concerns about asking for patents to be lifted for COVID-19 vaccines?
I have intuitions that lifting patents for the approved COVID-19 vaccines would do little as the technology is a higher barrier then just licensing the patents. It feels to me like calls for opening up patents mostly come out of p... |
292cc751-872b-4b4d-8c21-0e9ed2e2fb73 | trentmkelly/LessWrong-43k | LessWrong | Detailed Ideal World Benchmark
What "Ideal World" would an AI build if role-playing as an all-powerful superintelligence? It's probably very very different than what "Ideal World" an AI would actually create if it actually was an all-powerful superintelligence.
But why is it different?
1. The AI will obviously be i... |
17347bb7-fa45-46ed-a289-54e76a24f3c1 | StampyAI/alignment-research-dataset/eaforum | Effective Altruism Forum | Asking for online calls on AI s-risks discussions
（Sorry for posting this if it disturbed you.）
I'm Jack, a 16-year-old boy living in Taiwan, so I haven't met any EA people in person. I'm interested in(AI) s-risks, but I'm an AI outsider, I think EA people and I have a big knowledge gap of AI.
I've read a good deal of... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.