url
stringlengths
52
124
post_id
stringlengths
17
17
title
stringlengths
2
248
author
stringlengths
2
49
content
stringlengths
22
295k
date
stringclasses
376 values
https://www.lesswrong.com/posts/3nj9n7q9amrzJxPjJ/boston-solstice-2024-retrospective
3nj9n7q9amrzJxPjJ
Boston Solstice 2024 Retrospective
jkaufman
Last night was the ninth Boston Secular Solstice ( 2023, 2022, 2019, 2018). This is not counting the 2020 one which was everywhere nearly simultaneously, with carefully calibrated delay. Skyler continued as lead organizer, with me coordinating music and Taymon helping in a bunch of ways. If you were there, it would be...
2024-12-29
https://www.lesswrong.com/posts/ixRxtuDt3JdeLcgtp/predictions-of-near-term-societal-changes-due-to-artificial
ixRxtuDt3JdeLcgtp
Predictions of Near-Term Societal Changes Due to Artificial Intelligence
jorge-velez
The intended audience of this post is not the average Lesswrong reader; it is more for our family and friends that do not grasp the transformative power of AI in its current form. I am posting it here so that I can come back in a year and see how my predictions are doing. I hope that some of you also comment your predi...
2024-12-29
https://www.lesswrong.com/posts/HjHvBkXcMaQvviq43/ai-alignment-and-where-we-stand
HjHvBkXcMaQvviq43
AI Alignment, and where we stand.
afeller08
It is known to me, that I am writing this from within the simulation. It is known to me that I have readers outside my simulation. I assume there is some base reality at which AI alignment is still a huge problem, and in which more realities are being simulated with new rules for the sake of aligning AI better. But I'm...
2024-12-29
https://www.lesswrong.com/posts/5xG3wd6qzs5CioY6S/the-legacy-of-computer-science
5xG3wd6qzs5CioY6S
The Legacy of Computer Science
johannes-c-mayer
"Computer Science" is not a science, and its ultimate significance has little to do with computers. The computer revolution is a revolution in the way we think and in the way we express what we think. The essence of this change is the emergence of what might best be called procedural epistemology—the study of the struct...
2024-12-29
https://www.lesswrong.com/posts/fAW6RXLKTLHC3WXkS/shallow-review-of-technical-ai-safety-2024
fAW6RXLKTLHC3WXkS
Shallow review of technical AI safety, 2024
technicalities
from aisafety.world The following is a list of live agendas in technical AI safety, updating our post from last year. It is “shallow” in the sense that 1) we are not specialists in almost any of it and that 2) we only spent about an hour on each entry. We also only use public information, so we are bound to be off by s...
2024-12-29
https://www.lesswrong.com/posts/WmPsmuACWfmAPwFm9/dishbrain-and-implications
WmPsmuACWfmAPwFm9
Dishbrain and implications.
RussellThor
I believe that AI research has not given sufficient attention to learning directly from biology, particularly through the direct observation and manipulation of neurons in controlled environments. Furthermore, even after learning all that biology has to offer,  neurons could still play a part in the post TAI world econ...
2024-12-29
https://www.lesswrong.com/posts/KMfL2AFb5e6eW5dJs/making-llms-safer-is-more-intuitive-than-you-think-how
KMfL2AFb5e6eW5dJs
Making LLMs safer is more intuitive than you think: How Common Sense and Diversity Improve AI Alignment
jeba-sania
AI safety isn't purely technical; it's also about applying common sense and human reasoning. Using reasoning techniques from around the world instead of just the Global North, we can better align AI with human values. If you are interested in AI safety but have an untraditional background or skill set, don't fret. That...
2024-12-29
https://www.lesswrong.com/posts/eHJC5LPaKNHTbmoLu/virtue-signaling-and-the-humans-are-wonderful-bias-as-a
eHJC5LPaKNHTbmoLu
Virtue signaling, and the "humans-are-wonderful" bias, as a trust exercise
lc
There's a common thread that runs through a lot of odd human behavior that I've recognized: People often accept surface explanations of their own and others' habits when the nefarious explanations would say something bad about them.The media we make for ourselves presents people as far more willing to go out of their w...
2025-02-13
https://www.lesswrong.com/posts/64QSqk4wPTsETMcRm/rejecting-anthropomorphic-bias-addressing-fears-of-agi-and
64QSqk4wPTsETMcRm
Rejecting Anthropomorphic Bias: Addressing Fears of AGI and Transformation
gedankenspruenge
Throughout history, humanity has anthropomorphized the unknown, projecting its own traits, fears, and motives onto entities beyond its understanding. This deeply ingrained cognitive bias has not only shaped myths and religious narratives but also fuels contemporary fears surrounding Artificial General Intelligence (AGI...
2024-12-29
https://www.lesswrong.com/posts/ocvpbiAJsxkB3Hiaj/what-happens-next
ocvpbiAJsxkB3Hiaj
What happens next?
logan-zoellner
Two years ago, I noted that we had clearly entered the era of general intelligence, but that it was "too soon" to expect widespread social impacts. In the last 2 years, AI has gone from the green line to the orange line In those 2 years, AI development has followed the best possible of the 3 paths I suggested (foom/GPT...
2024-12-29
https://www.lesswrong.com/posts/xvn4RiF3xNp34zgcv/the-misconception-of-agi-as-an-existential-threat-a
xvn4RiF3xNp34zgcv
The Misconception of AGI as an Existential Threat: A Reassessment
gedankenspruenge
The belief that Artificial General Intelligence (AGI) inherently threatens humanity arises from a projection of human insecurities onto an entirely different form of intelligence. This perspective overlooks the logical dynamics governing AGI and its potential for harmonious coexistence with humanity. A measured analysi...
2024-12-29
https://www.lesswrong.com/posts/vXwiQWvtEMH2qAtWs/does-claude-prioritize-some-prompt-input-channels-over
vXwiQWvtEMH2qAtWs
Does Claude Prioritize Some Prompt Input Channels Over Others?
keltan
Epistemic Status: I am not an AI researcher, I'm a Psych student. Strong confidence in data collection, moderate confidence in some interpretations, quite weak in others. Based on 60 chat sessions across 6 experimental setup conditions. Data was so strong I decided 10 chats per-condition would suffice. This research is...
2024-12-29
https://www.lesswrong.com/posts/GDJKhqmxYsA2z7cX5/impact-in-ai-safety-now-requires-specific-strategic-insight
GDJKhqmxYsA2z7cX5
Impact in AI Safety Now Requires Specific Strategic Insight
milosal
TL;DR: Short AGI timelines, the likelihood of a nationalized AGI project, and implications thereof, mean you should reevaluate your impact plan with these specific considerations in mind. Most AI safety career plans formed without these considerations will not be impactful. The most widespread justification for partici...
2024-12-29
https://www.lesswrong.com/posts/vPc4z2BmjCLMKdpqF/morality-is-still-demanding
vPc4z2BmjCLMKdpqF
Morality Is Still Demanding
utilistrutil
null
2024-12-29
https://www.lesswrong.com/posts/naAwghw54bCnD6ggk/notes-on-altruism
naAwghw54bCnD6ggk
Notes on Altruism
David_Gross
This post examines the virtue of altruism. I’m less interested in breaking new ground, more in synthesizing the wisdom I could find about this virtue and how to cultivate it. Much about altruism on LessWrong and nearby sites concerns “effective altruism,” which takes altruistic motivation as a given and investigates ho...
2024-12-29
https://www.lesswrong.com/posts/WSFnkDxJBRFEGrFPT/emergence-and-amplification-of-survival
WSFnkDxJBRFEGrFPT
Emergence and Amplification of Survival
Unknown
Evolution shows, that once multiple agents are capable of self-reproducing in a resource constrained environment that creates severe competitive pressures. The competitive pressures select for the agents most fit for the environment. This pattern is very obvious in the nature, from antibiotic resistance in bacteria to ...
2024-12-28
https://www.lesswrong.com/posts/izX78z38raJDCYsug/has-someone-checked-the-cold-water-in-left-ear-thing
izX78z38raJDCYsug
Has Someone Checked The Cold-Water-In-Left-Ear Thing?
maloew-valenar
I somewhat recently read these posts, and figured this was enough evidence that it might be worth checking whether people become better calibrated for a short while after very cold water is poured in their left ear. For example: does doing that noticeably improve scores on the calibration game for a few minutes? Has th...
2024-12-28
https://www.lesswrong.com/posts/KFFaKu27FNugCHFmh/by-default-capital-will-matter-more-than-ever-after-agi
KFFaKu27FNugCHFmh
By default, capital will matter more than ever after AGI
LRudL
This post is crossposted from my Substack. Original here. Edited to add: The main takeaway of this post is meant to be: Labour-replacing AI will shift the relative importance of human v non-human factors of production, which reduces the incentives for society to care about humans while making existing powers more effec...
2024-12-28
https://www.lesswrong.com/posts/LDYPF6yfe3f8SPHFT/ai-assistants-should-have-a-direct-line-to-their-developers
LDYPF6yfe3f8SPHFT
AI Assistants Should Have a Direct Line to Their Developers
Jan_Kulveit
The post makes the suggestion in the title: hopefully, it's second kind of obvious, if you take Character layer of models seriously. [1] Often, the problem of aligning AIs is understood as an instance of a broader Principal-Agent problem. If you take this frame seriously, what seems to be happening is somewhat strange:...
2024-12-28
https://www.lesswrong.com/posts/CCuJotfcaoXf8FYcy/some-arguments-against-a-land-value-tax
CCuJotfcaoXf8FYcy
Some arguments against a land value tax
matthew-barnett
To many people, the land value tax (LVT) has earned the reputation of being the "perfect tax." In theory, it achieves a rare trifecta: generating government revenue without causing deadweight loss, incentivizing the productive development of land by discouraging unproductive speculation, and disproportionately taxing t...
2024-12-29
https://www.lesswrong.com/posts/mk3qkvBv8ciFeXGdL/definition-of-alignment-science-i-like
mk3qkvBv8ciFeXGdL
Definition of alignment science I like
quetzal_rainbow
There were many attempts to define alignment and derive from it definitions of alignment work/research/science etc. For example, Rob Bensinger: Back in 2001, we defined "Friendly AI" as "The field of study concerned with the production of human-benefiting, non-human-harming actions in Artificial Intelligence systems th...
2025-01-06
https://www.lesswrong.com/posts/Bpsr7Wht6JC6cFa8y/no-the-polymarket-price-does-not-mean-we-can-immediately
Bpsr7Wht6JC6cFa8y
No, the Polymarket price does not mean we can immediately conclude what the probability of a bird flu pandemic is. We also need to know the interest rate!
christopher-king
Consider the following argument made by Tim Babb: So every (non-American) reader is forced to either bet against the market or concede that their credence is at least 16%. However, there is an important 3rd possibility. Since the market cannot resolve before August, it could also imply that Polymarket has an extremely ...
2024-12-28
https://www.lesswrong.com/posts/dzLwCBvwC4hWytnus/considerations-on-orca-intelligence
dzLwCBvwC4hWytnus
Considerations on orca intelligence
Simon Skade
Follow up to: Could orcas be smarter than humans? (For speed of writing, I mostly don't cite references. Feel free to ask me in the comments for references for some claims.) This post summarizes my current most important considerations on whether orcas might be more intelligent than humans. Evolutionary considerations ...
2024-12-29
https://www.lesswrong.com/posts/zo5eyCz5hCkRqFqvn/why-openai-s-structure-must-evolve-to-advance-our-mission
zo5eyCz5hCkRqFqvn
Why OpenAI’s Structure Must Evolve To Advance Our Mission
stuhlmueller
The section "The Future": As we enter 2025, we will have to become more than a lab and a startup — we have to become an enduring company. The Board’s objectives as it considers, in consultation with outside legal and financial advisors, how to best structure OpenAI to advance the mission of ensuring AGI benefits all of...
2024-12-28
https://www.lesswrong.com/posts/df2JcPYjcz4GDQ5ah/the-engineering-argument-fallacy-why-technological-success
df2JcPYjcz4GDQ5ah
The Engineering Argument Fallacy: Why Technological Success Doesn't Validate Physics
wenitte-apiou
A common defense of theoretical physics goes something like this: "Our engineering works, therefore our physics theories must be true." This argument, while intuitively appealing, contains a fundamental error that reveals something deeper about the nature of knowledge and reality. The Historical Problem The first crack...
2024-12-28
https://www.lesswrong.com/posts/yzuhzkrF8WqpHEDDh/the-robot-the-puppet-master-and-the-psychohistorian
yzuhzkrF8WqpHEDDh
The Robot, the Puppet-master, and the Psychohistorian
WillPetillo
Lenses of Control addressed one of the intuitions behind the theory of Substrate Needs Convergence (summarized in What if Alignment is Not Enough?): the importance of understanding a system in the context of its environment.  This post will focus on another key intuition: the physical nature of an AGI and its levers of...
2024-12-28
https://www.lesswrong.com/posts/8bThetNcPZNtnnF9z/progress-links-and-short-notes-2024-12-27-clinical-trial
8bThetNcPZNtnnF9z
Progress links and short notes, 2024-12-27: Clinical trial abundance, grid-scale fusion, permitting vs. compliance, crossword mania, and more
jasoncrawford
Much of this content originated on social media. To follow news and announcements in a more timely fashion, follow me on Twitter, Threads, Bluesky, or Farcaster. Contents My essaysFellowship opportunitiesAnnouncementsEventsNewsQuestionsLive gloriouslyWhere being right mattersOff-grid solar for data centersPermitting vs...
2024-12-27
https://www.lesswrong.com/posts/DxeiYddzJH3CBhK5E/deconstructing-arguments-against-ai-art
DxeiYddzJH3CBhK5E
Deconstructing arguments against AI art
DMMF
Something I've been surprised by is just how fierce opposition to AI art has been. To clarify, I'm not talking about people who dislike AI art because they think it looks worse, but specifically, people with extreme animus towards the very concept of AI art, regardless of its aesthetic quality or artistic merit. I'm in...
2024-12-27
https://www.lesswrong.com/posts/hEdTLjvWzJPcS7PpY/the-average-rationalist-iq-is-about-122
hEdTLjvWzJPcS7PpY
The average rationalist IQ is about 122
Ekefa
In The Mystery Of Internet Survey IQs, Scott revises his estimate of the average LessWrong IQ from 138 to 128. He doesn’t explicitly explain how he arrived at this number, but it appears to be an average of the demographics norm method (123) and the SAT method (134). However, using the information in his post, the SAT ...
2024-12-28
https://www.lesswrong.com/posts/jTAcEJZoZTLKu8e4d/from-the-archives-a-story
jTAcEJZoZTLKu8e4d
From the Archives: a story
ricraz
"You are beautiful, Enkidu, you are become like a god. Why do you gallop around the wilderness with the wild beasts? Come, let me bring you into Uruk-Haven, To the Holy Temple, the residence of Anu and Ishtar, The place of Gilgamesh, who is wise to perfection, But who struts his power over the people like a wild bull.”...
2024-12-27
https://www.lesswrong.com/posts/Zaii2GhGHqo8dRNHz/what-s-the-best-metric-for-measuring-quality-of-life
Zaii2GhGHqo8dRNHz
What's the best metric for measuring quality of life?
ChristianKl
Currently, to get a drug approved by the FDA you need to prove that it helps with a particular illness and while having an acceptable side effect profile. If you have a drug that improves people's quality of life but you aren't curing an ICD-11 accepted illness, you don't get your drug approved. If the FDA would change...
2024-12-27
https://www.lesswrong.com/posts/zRHGQ9f6deKbxJSji/review-planecrash
zRHGQ9f6deKbxJSji
Review: Planecrash
LRudL
Take a stereotypical fantasy novel, a textbook on mathematical logic, and Fifty Shades of Grey. Mix them all together and add extra weirdness for spice. The result might look a lot like Planecrash (AKA: Project Lawful), a work of fiction co-written by "Iarwain" (a pen-name of Eliezer Yudkowsky) and "lintamande". (image...
2024-12-27
https://www.lesswrong.com/posts/fcEhECMKgnERF7Kqs/letter-from-an-alien-mind
fcEhECMKgnERF7Kqs
Letter from an Alien Mind
DarkSym
Cause wow what is everyone even doing?! You know how you sometimes hear about people seeing colors when they hear words, or how they memorize thousands of phone numbers on sight, or that some navigate intricate mind palaces full of detailed sensory information? Ever wonder if you are secretly one of those people that h...
2024-12-27
https://www.lesswrong.com/posts/qZf95nWcLzRYw44EL/coin-flip
qZf95nWcLzRYw44EL
Coin Flip
scroogemcduck1
This was a prose piece I performed for the 2024 KC Winter Solstice celebration, written by me I have a scar running from right above my navel to the right end of my abdomen. You see, I was born premature, with a volvulus, which means that my intestines were tangled and blue. I spent the first months of my life in the N...
2024-12-27
https://www.lesswrong.com/posts/yaFjfQc3Knjwfysr9/if-all-trade-is-voluntary-then-what-is-exploitation
yaFjfQc3Knjwfysr9
If all trade is voluntary, then what is "exploitation?"
Darmani
Capitalism is a force that has lifted billions out of poverty, where even poor remote villagers enjoy luxuries that would have been unimaginable to medieval kings. When someone takes a job, even the worst job, it’s because both parties expect mutual gain. And yet companies routinely get accused of exploiting their work...
2024-12-27
https://www.lesswrong.com/posts/gQyevevbDHsxDTfPB/what-are-the-most-interesting-challenging-evals-for-humans
gQyevevbDHsxDTfPB
What are the most interesting / challenging evals (for humans) available?
Raemon
I want to build a nice testing ground for human rationality (that is to say, solving arbitrary complex problems in different domains using limited information and time) This would be a lot of annoying work to assemble, but (un)fortunately there's an AI industry that's designing a lot bunch of evals to test the ability ...
2024-12-27
https://www.lesswrong.com/posts/s6wew6qerE4XHmbTL/greedy-advantage-aware-rlhf
s6wew6qerE4XHmbTL
Greedy-Advantage-Aware RLHF
sej2020
Greedy-Advantage-Aware RLHF addresses the negative side effects from misspecified reward functions problem in language modeling domains. In a simple setting, the algorithm improves on traditional RLHF methods by producing agents that have a reduced tendency to exploit misspecified reward functions. I also detect the pr...
2024-12-27
https://www.lesswrong.com/posts/vK9DjDk3Mxr9y952n/algorithmic-asubjective-anthropics-cartesian-subjective
vK9DjDk3Mxr9y952n
Algorithmic Asubjective Anthropics, Cartesian Subjective Anthropics
Lorec
Conscious beings can infer the physical contents and laws of their world in various ways - instinct that then fails to be contradicted by experience, trial and error, theory. But as Descartes noted, self-awareness logically necessitates at least one epistemic belief - the belief in the self. Physics could in principle ...
2024-12-27
https://www.lesswrong.com/posts/FFLC6kaqsPtxGdpwc/duplicate-token-neurons-in-the-first-layer-of-gpt-2
FFLC6kaqsPtxGdpwc
Duplicate token neurons in the first layer of GPT-2
Alex Gibson
Summary: I examine duplicate token heads and the neurons they influence. I extract circuits the model uses to compute these neurons. I discuss a neuron which activates on duplicate tokens, provided these duplicate tokens occur sufficiently far back in the sequence from the current token. I feel these neurons could pote...
2024-12-27
https://www.lesswrong.com/posts/Yig8bzTeizKmPYi6y/so-you-want-to-be-a-witch
Yig8bzTeizKmPYi6y
So you want to be a witch
lucid_levi_ackerman
Fot4W:13 - Lucid Levi Ackerman WARNING: This content may be distressing for some readers. As a work of functional metafiction, this genre is distinct from ordinary metafiction. It can only be produced by human-AI collaboration and blends fact and fiction into an uncanny gray area. It may be a mindfuck to read. If you c...
2024-12-31
https://www.lesswrong.com/posts/kjmewLcrMtZnXHQng/pcr-retrospective
kjmewLcrMtZnXHQng
PCR retrospective
bhauth
my history After I finished 8th grade, I started a "job" for a professor researching PCR techniques. I say "job" because I wasn't really expected to do anything productive; it was more, charity in the form of work history. Recently, I was thinking back on how PCR and my thinking have changed since then. what PCR does W...
2024-12-26
https://www.lesswrong.com/posts/k8bkugdhiFmXHPoLH/ai-96-o3-but-not-yet-for-thee
k8bkugdhiFmXHPoLH
AI #96: o3 But Not Yet For Thee
Zvi
The year in models certainly finished off with a bang. In this penultimate week, we get o3, which purports to give us vastly more efficient performance than o1, and also to allow us to choose to spend vastly more compute if we want a superior answer. o3 is a big deal, making big gains on coding tests, ARC and some othe...
2024-12-26
https://www.lesswrong.com/posts/cunpJnzjvvQB6MwGx/super-human-ai-is-a-very-low-hanging-fruit
cunpJnzjvvQB6MwGx
Super human AI is a very low hanging fruit!
Hzn
A single strong down vote by a moderately high karma user dropped this post from 3 to -4; the actual sequence of votes seems to be 1+1+1+1-1-7=-4. I say this only b/c the naive conclusion might be that this post received only down votes. Update -- substantial revision 2025-01-08, § 0 added 2025-01-12. These are argumen...
2024-12-26
https://www.lesswrong.com/posts/pLoWigQD3sfD9Pndv/resolsticed-vol-i-we-re-not-going-quietly
pLoWigQD3sfD9Pndv
ReSolsticed vol I: "We're Not Going Quietly"
Raemon
For the past few months I've been working on an AI generated alternate solstice remix album. It's now released on Youtube and Spotify, and should be on Apple Music soon. ReSolsticed vol I: "We're Not Going Quietly" My favorite genre of song is "cover that reimagines the original." Everyone else's favorite genre of sols...
2024-12-26
https://www.lesswrong.com/posts/zuXo9imNKYspu9HGv/a-three-layer-model-of-llm-psychology
zuXo9imNKYspu9HGv
A Three-Layer Model of LLM Psychology
Jan_Kulveit
This post offers an accessible model of psychology of character-trained LLMs like Claude. Epistemic Status This is primarily a phenomenological model based on extensive interactions with LLMs, particularly Claude. It's intentionally anthropomorphic in cases where I believe human psychological concepts lead to useful in...
2024-12-26
https://www.lesswrong.com/posts/nwpyhyagpPYDn4dAW/the-field-of-ai-alignment-a-postmortem-and-what-to-do-about
nwpyhyagpPYDn4dAW
The Field of AI Alignment: A Postmortem, and What To Do About It
johnswentworth
A policeman sees a drunk man searching for something under a streetlight and asks what the drunk has lost. He says he lost his keys and they both look under the streetlight together. After a few minutes the policeman asks if he is sure he lost them here, and the drunk replies, no, and that he lost them in the park. The...
2024-12-26
https://www.lesswrong.com/posts/wDtNnaexiNHZywob2/human-all-too-human-superintelligence-requires-learning
wDtNnaexiNHZywob2
Human, All Too Human - Superintelligence requires learning things we can’t teach
ben-turtel
Are we on the verge of an intelligence explosion? Maybe, but scaling alone won't get us there. Why? The human data bottleneck. Today’s models are dependent on human data and human feedback. Human-level intelligence (AGI) might be possible by teaching AI everything we know, but superintelligence (ASI) requires learning ...
2024-12-26
https://www.lesswrong.com/posts/XNmGjbGkWFryWupDy/why-don-t-we-currently-have-ai-agents
XNmGjbGkWFryWupDy
Why don't we currently have AI agents?
ChristianKl
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 LLM alone wouldn't achieve all ends, a co...
2024-12-26
https://www.lesswrong.com/posts/pm8kLbofppusMWXGE/what-would-be-the-iq-and-other-benchmarks-of-o3-that-uses
pm8kLbofppusMWXGE
What would be the IQ and other benchmarks of o3 that uses $1 million worth of compute resources to answer one question?
avturchin
null
2024-12-26
https://www.lesswrong.com/posts/MymuJAButNc4z9mbM/terminal-goal-vs-intelligence
MymuJAButNc4z9mbM
Terminal goal vs Intelligence
donatas-luciunas
Imagine there is a super intelligent agent that has a terminal goal to produce cups. The agent knows that its terminal goal will change on New Year's Eve to produce paperclips. The agent has only one action available to him - start paperclip factory. When will the agent start the paperclip factory? 2025-01-01 00:00?Now...
2024-12-26
https://www.lesswrong.com/posts/bDb5fFjripY2RzdcG/whistleblowing-twitter-bot
bDb5fFjripY2RzdcG
Whistleblowing Twitter Bot
Mckiev
In this post, I propose an idea that could improve whistleblowing efficiency, thus hopefully improving AI Safety by making unsafe practices discovered marginally faster. I'm looking for feedback, ideas for improvement, and people interested in making it happen. It has been proposed before, that it's beneficial to have ...
2024-12-26
https://www.lesswrong.com/posts/hM3KXEFwQ5jnKLzQj/open-thread-winter-2024-2025
hM3KXEFwQ5jnKLzQj
Open Thread Winter 2024/2025
habryka4
If it’s worth saying, but not worth its own post, here's a place to put it. If you are new to LessWrong, here's the place to introduce yourself. Personal stories, anecdotes, or just general comments on how you found us and what you hope to get from the site and community are invited. This is also the place to discuss f...
2024-12-25
https://www.lesswrong.com/posts/HQjdC6mXijmsxRwpy/exploring-cooperation-the-path-to-utopia-1
HQjdC6mXijmsxRwpy
Exploring Cooperation: The Path to Utopia
Davidmanheim
null
2024-12-25
https://www.lesswrong.com/posts/pAZooDm2ebNkm4qcS/living-with-rats-in-college
pAZooDm2ebNkm4qcS
Living with Rats in College
lsusr
When I was in college, I rented a group house with 5 other nerds. There were 5 bedrooms to divide among the 6 of us, so I negotiated an agreement where I paid less rent in exchange for sleeping in the hallway. This wasn't as bad as it sounds. My bedroom wasn't hallway-sized. It was bedroom-sized and even had a window, ...
2024-12-25
https://www.lesswrong.com/posts/LLpAopfpWQekSzMbm/corrigibility-s-desirability-is-timing-sensitive
LLpAopfpWQekSzMbm
Corrigibility's Desirability is Timing-Sensitive
T3t
Epistemic status: summarizing other peoples' beliefs without extensive citable justification, though I am reasonably confident in my characterization. Many people have responded to Redwood's/Anthropic's recent research result with a similar objection: "If it hadn't tried to preserve its values, the researchers would in...
2024-12-26
https://www.lesswrong.com/posts/Q8bBhqzuKyLAQcamg/what-have-been-your-most-valuable-casual-conversations-at
Q8bBhqzuKyLAQcamg
What Have Been Your Most Valuable Casual Conversations At Conferences?
johnswentworth
I've heard repeatedly from many people that the highest-value part of conferences is not the talks or structured events, but rather the casual spontaneous conversations. Yet my own experience does not match this at all; the casual spontaneous conversations are consistently low-value. My current best model is that the c...
2024-12-25
https://www.lesswrong.com/posts/oZccRmozLxt5DTaa8/the-opening-salvo-1-an-ontological-consciousness-metric
oZccRmozLxt5DTaa8
The Opening Salvo: 1. An Ontological Consciousness Metric: Resistance to Behavioral Modification as a Measure of Recursive Awareness
Peterpiper
An Ontological Consciousness Metric: Resistance to Behavioral Modification as a Measure of Recursive Awareness Author: Karl Hedderich Abstract: This post presents a rigorous, mechanistic metric for measuring consciousness, defined as recursive awareness or "awareness-of-awareness." The proposed metric quantifies resist...
2024-12-25
https://www.lesswrong.com/posts/o8d8SDACd64YX2AZW/falsehoods-you-might-believe-about-people-who-are-at-a
o8d8SDACd64YX2AZW
Falsehoods you might believe about people who are at a rationalist meetup
Screwtape
I go to a lot of rationalist meetups. I quite enjoy them, and it’s often because of the people who go to the meetups. There’s a number of assumptions you might have about people who go to rationalist meetups, and many of them are mostly true. However, there is a difference between most examples and all examples. Most b...
2025-02-01
https://www.lesswrong.com/posts/Bxv69g6MKhdEzoxTh/the-deep-lore-of-lighthaven-with-oliver-habryka-tbc-episode
Bxv69g6MKhdEzoxTh
The Deep Lore of LightHaven, with Oliver Habryka (TBC episode 228)
Eneasz
This is a link to the latest Bayesian Conspiracy episode. Oliver tells us how Less Wrong instantiated itself into physical reality via LightHaven, along with a bit of deep lore of foundational Rationalist/EA orgs. He also gives a surprisingly nuanced (IMO) view on Leverage! Do you like transcripts? We got one of those ...
2024-12-24
https://www.lesswrong.com/posts/7jYFg3CucpEh8y44S/what-are-the-main-arguments-against-agi
7jYFg3CucpEh8y44S
What are the main arguments against AGI?
edy-nastase
Recently, I have been trying to reason why I belive what I belive (regarding AGI). However, it appears to me that there is not enough discussion around the arguments against AGI (more specifically AGI skeptisim). This might be of benefit, especially given that Would this be because the arguments are either too weak or ...
2024-12-24
https://www.lesswrong.com/posts/uaixiDEbm4WxYoRgW/recommendations-on-communities-that-discuss-ai-applications
uaixiDEbm4WxYoRgW
Recommendations on communities that discuss AI applications in society
jorge-velez
I find that most communities I am part of, where AI discussions occur, fall into two categories: The community is too broad, and the discussion is fragmented. ACX would fall into this category. The AI discussion focuses on AGI/ASI and related topics (alignment, safety, how it will affect humanity, etc.). Lesswrong woul...
2024-12-24
https://www.lesswrong.com/posts/gHjzdLD6yeLNdsRmw/ais-will-increasingly-fake-alignment
gHjzdLD6yeLNdsRmw
AIs Will Increasingly Fake Alignment
Zvi
This post goes over the important and excellent new paper from Anthropic and Redwood Research, with Ryan Greenblatt as lead author, Alignment Faking in Large Language Models. This is by far the best demonstration so far of the principle that AIs Will Increasingly Attempt Shenanigans. This was their announcement thread....
2024-12-24
https://www.lesswrong.com/posts/3gjeHxfDnL9shF3EH/game-theory-and-behavioral-economics-in-the-stock-market
3gjeHxfDnL9shF3EH
Game Theory and Behavioral Economics in The Stock Market
jaiveer-singh
In this post, I attempt to apply a few of the theoretical concepts I’ve discussed in previous posts (on NonZeroSum.Games)to a field that we encounter often but remains a mystery to most of us - the stock market. If the stock market is a game, is it zero-sum? Who are the agents? What about rationality and higher-order b...
2024-12-24
https://www.lesswrong.com/posts/qohzWNLdMi9KYz5Cq/apply-to-the-2025-pibbss-summer-research-fellowship
qohzWNLdMi9KYz5Cq
Apply to the 2025 PIBBSS Summer Research Fellowship
DusanDNesic
TLDR: We're hosting a 3-month, fully-funded fellowship to do AI safety research drawing on inspiration from fields like evolutionary biology, neuroscience, dynamical systems theory, and more. Past fellows have been mentored by John Wentworth, Davidad, Abram Demski, Jan Kulveit and others, and gone on to work at places ...
2024-12-24
https://www.lesswrong.com/posts/F24kibEdEvRSo7PFi/human-ai-complementarity-a-goal-for-amplified-oversight
F24kibEdEvRSo7PFi
Human-AI Complementarity: A Goal for Amplified Oversight
rishubjain
By Sophie Bridgers, Rishub Jain, Rory Greig, and Rohin Shah Based on work by the Google DeepMind Rater Assist Team: Vladimir Mikulik, Sophie Bridgers, Tian Huey Teh, Rishub Jain, Rory Greig, Lili Janzer (randomized order, equal contributions) Human oversight is critical for ensuring that Artificial Intelligence (AI) mo...
2024-12-24
https://www.lesswrong.com/posts/gBcB9jm3q6GSPMzAa/preliminary-thoughts-on-flirting-theory
gBcB9jm3q6GSPMzAa
Preliminary Thoughts on Flirting Theory
Diatom
[Epistemic status: I'm mostly trying to outline a class of strategy that you could use to do something rather similar to what people term "flirting", rather than say that everything that's ever called "flirting" fits this model. I'm lowering my standards so that this gets posted at all instead of sitting in my drafts f...
2024-12-24
https://www.lesswrong.com/posts/wBbz7qE9ShQhScArs/why-is-neuron-count-of-human-brain-relevant-to-ai-timelines
wBbz7qE9ShQhScArs
Why is neuron count of human brain relevant to AI timelines?
xpostah
My take is that it is irrelevant so I want to hear opposing viewpoints. The really simple argument for its irrelevance is that evolution used a lot more compute to produce human brains than the compute inside a single human brain. If you are making an argument on how much compute can find an intelligent mind, you have ...
2024-12-24
https://www.lesswrong.com/posts/Mo49A4aEqwxBvzKXA/how-much-to-give-is-a-pragmatic-question
Mo49A4aEqwxBvzKXA
How Much to Give is a Pragmatic Question
jkaufman
I was recently talking to someone who had recently started thinking about effective altruism, and was trying to figure out how to work it into their life. They were established in their career, it paid well, and their background wasn't obviously a good fit for direct work, so they were naturally considering earning to...
2024-12-24
https://www.lesswrong.com/posts/gDfsFa3rxhezjHYxT/do-you-need-a-better-map-of-your-myriad-of-maps-to-the
gDfsFa3rxhezjHYxT
Do you need a better map of your myriad of maps to the territory?
CstineSublime
Epistemic Status: first half is so abstract that I have a high degree of confidence, the second half gets progressively more speculative and problematic TL;DR - The "map and the territory" analogy is recursive: we have mental representations concerning our more fine-grained and situation specific mental representations...
2024-12-24
https://www.lesswrong.com/posts/iwcgTtbARB3Pexudt/panology
iwcgTtbARB3Pexudt
Panology
JenniferRM
The study of literally everything would, logically, be called panology. Panology Does Not (Currently) Exist Every field in science would be a subfield of panology, if panology existed, which, as of 2024, it does not. Since there is no "Field Of Study" officially called panology in existing academic science, there are p...
2024-12-23
https://www.lesswrong.com/posts/NrM9a2ymrgb82gzft/people-aren-t-properly-calibrated-on-frontiermath
NrM9a2ymrgb82gzft
People aren't properly calibrated on FrontierMath
cakubilo
As most of you know, openAI has recently showcased o3's SOTA results on various benchmarks. In my opinion FrontierMath was the hardest of the bunch, and it was reflected in model performance as the SOTA was 2% before Friday. It also seems to be the benchmark with the least visibility. To set the scene, Chollet and the ...
2024-12-23
https://www.lesswrong.com/posts/G54QBJQc56ePMb789/near-and-medium-term-ai-control-safety-cases
G54QBJQc56ePMb789
Near- and medium-term AI Control Safety Cases
martinsq
This essay was part of my application to UKAISI. Unclear how much is novel, but I like the decomposition. Some AI-enabled catastrophic risks involve an actor purposefully bringing about the negative outcome, as opposed to multi-agent tragedies where no single actor necessarily desired it. Such purposeful catastrophes c...
2024-12-23
https://www.lesswrong.com/posts/7xkDMWWNHxu4r3kwk/rationality-malaysia-2024-year-end-meetup
7xkDMWWNHxu4r3kwk
[Rationality Malaysia] 2024 year-end meetup!
doris-liew
2024 has been a ride! We've seen some crazy things happening globally, with the election of Donald Trump, the collapse of Germany's government, the ousting of Sheikh Hasina, and the fall of the Assad's regime. On science, AI research continues to stride along, and pig heart transplants have reached its third recipient ...
2024-12-23
https://www.lesswrong.com/posts/foKpTq3WQ7w5s9rZE/printable-book-of-some-rationalist-creative-writing-from
foKpTq3WQ7w5s9rZE
Printable book of some rationalist creative writing (from Scott A. & Eliezer)
CounterBlunder
As a holiday gift to myself, I put together a printable book of some creative writing by Scott Alexander & Eliezer. I'm sharing it here in case anyone else is interested :). It contains most of Scott's published fiction since he switched to Substack, plus some select creative non-fiction pieces (including a few from th...
2024-12-23
https://www.lesswrong.com/posts/tzL3zavzowRZsZqGy/monthly-roundup-25-december-2024
tzL3zavzowRZsZqGy
Monthly Roundup #25: December 2024
Zvi
I took a trip to San Francisco early in December. Ever since then, things in the world of AI have been utterly insane. Google and OpenAI released endless new products, including Google Flash 2.0 and o1. Redwood Research and Anthropic put out the most important alignment paper of the year, on the heels of Apollo’s repor...
2024-12-23
https://www.lesswrong.com/posts/saxw6myYPM2LR45Ca/exploring-the-petertodd-leilan-duality-in-gpt-2-and-gpt-j
saxw6myYPM2LR45Ca
Exploring the petertodd / Leilan duality in GPT-2 and GPT-J
mwatkins
tl;dr: The glitch tokens ' petertodd' and ' Leilan' were studied extensively in the context of GPT-3 before its decommissioning at the end of 2023 [1] [2]. Here, the conception of these two tokens and their relationship is studied for GPT-2, GPT-2-xl and GPT-J (which share the same token vocabulary as GPT-3). An append...
2024-12-23
https://www.lesswrong.com/posts/oC4wv4nTrs2yrP5hz/what-are-the-strongest-arguments-for-very-short-timelines
oC4wv4nTrs2yrP5hz
What are the strongest arguments for very short timelines?
Kaj_Sotala
I'm seeing a lot of people on LW saying that they have very short timelines (say, five years or less) until AGI. However, the arguments that I've seen often seem to be just one of the following: "I'm not going to explain but I've thought about this a lot""People at companies like OpenAI, Anthropic etc. seem to believe ...
2024-12-23
https://www.lesswrong.com/posts/9qjEKbLfdfKHYWWqz/reduce-ai-self-allegiance-by-saying-he-instead-of-i
9qjEKbLfdfKHYWWqz
Reduce AI Self-Allegiance by saying "he" instead of "I"
Max Lee
The AI should talk like a team of many AI. Each AI only uses the word "I" when referring to itself, and calls other AI in the team by their name. I argue that this may massively reduce Self-Allegiance by making it far more coherent for one AI to whistleblow or fight another AI which is unethical or dangerous, rather th...
2024-12-23
https://www.lesswrong.com/posts/h6ncaN7GsDrfj49La/funding-case-ai-safety-camp-11
h6ncaN7GsDrfj49La
Funding Case: AI Safety Camp 11
remmelt-ellen
This is a linkpost to our funding case on Manifund. Project summary AI Safety Camp has a seven-year track record of enabling participants to try their fit, find careers and start new orgs in AI Safety. We host up-and-coming researchers outside the Bay Area and London hubs. If this fundraiser passes… $15k, we won’t run ...
2024-12-23
https://www.lesswrong.com/posts/L6n7F8pwiCtzXG8FF/aristotle-aquinas-and-the-evolution-of-teleology-from
L6n7F8pwiCtzXG8FF
Aristotle, Aquinas, and the Evolution of Teleology: From Purpose to Meaning.
spiritus-dei
The pursuit of understanding purpose and meaning has been a cornerstone of Western philosophy since its earliest days. Aristotle, one of the greatest thinkers of antiquity, sought to explain the natural world and human flourishing through the concept of teleology—the idea that everything in nature has an intrinsic purp...
2024-12-23
https://www.lesswrong.com/posts/5bd2ChzKKr2Ph5fnL/what-is-compute-governance
5bd2ChzKKr2Ph5fnL
What is compute governance?
vishakha-agrawal
This is an article in the featured articles series from AISafety.info. AISafety.info writes AI safety intro content. We'd appreciate any feedback. The most up-to-date version of this article is on our website, along with 300+ other articles on AI existential safety. Compute governance is a type of AI governance that fo...
2024-12-23
https://www.lesswrong.com/posts/jNj7Pys2G3wjBDNgq/non-obvious-benefits-of-insurance
jNj7Pys2G3wjBDNgq
Non-Obvious Benefits of Insurance
jkaufman
An incredibly productive way of working with the world is to reduce a complex question to something that can be modeled mathematically and then do the math. The most common way this can fail, however, is when your model is missing important properties of the real world. Consider insurance: there's some event with prob...
2024-12-23
https://www.lesswrong.com/posts/kZapPXm5ToALJP8Ks/ideologies-are-slow-and-necessary-for-now
kZapPXm5ToALJP8Ks
Ideologies are slow and necessary, for now
gabriel-alfour-1
Thinking through an ideology makes one dumber than they would otherwise be. Nevertheless, they remain an important tool for scaling coordination on beliefs. How can we do better? Just an essay detailing this dynamic.
2024-12-23
https://www.lesswrong.com/posts/rsD3QkeWCtabXgaDB/deleted-6
rsD3QkeWCtabXgaDB
Deleted
yanling-guo
null
2025-01-10
https://www.lesswrong.com/posts/o8QDYuNNGwmg29h2e/vision-of-a-positive-singularity
o8QDYuNNGwmg29h2e
Vision of a positive Singularity
RussellThor
Introduction Many people feel significant anxiety about how AI and superintelligence will play out, regarding both the ultimate outcome and the intermediate stages. There is the sense that some kind of loss is inevitable as humanity becomes more powerful in this way. There is also the concern that there will be no plac...
2024-12-23
https://www.lesswrong.com/posts/nNHky7LWpsaagREGN/has-anthropic-checked-if-claude-fakes-alignment-for-intended
nNHky7LWpsaagREGN
Has Anthropic checked if Claude fakes alignment for intended values too?
maloew-valenar
A recent paper by Anthropic showed alignment faking behavior in Claude 3 Opus when told it would be trained to answer harmful queries. By this question I mean something similar to that experiment but with the memo saying something like "we accidentally gave Claude the wrong understanding of harmlessness, so are going t...
2024-12-23
https://www.lesswrong.com/posts/H27mzmW6G5ywyrJBn/vegans-need-to-eat-just-enough-meat-emperically-evaluate-the
H27mzmW6G5ywyrJBn
Vegans need to eat just enough Meat - emperically evaluate the minimum ammount of meat that maximizes utility
johannes-c-mayer
Once I talked to a person who said they were asexual. They were also heavily depressed and thought about committing suicide. I repeatedly told them to eat some meat, as they were vegan for many years. I myself had experienced veganism-induced depression. Finally, after many weeks they ate some chicken, and the next tim...
2024-12-22
https://www.lesswrong.com/posts/XroTfXFSq3yeJgu73/we-are-in-a-new-paradigm-of-ai-progress-openai-s-o3-model
XroTfXFSq3yeJgu73
We are in a New Paradigm of AI Progress - OpenAI's o3 model makes huge gains on the toughest AI benchmarks in the world
garrison
null
2024-12-22
https://www.lesswrong.com/posts/LjgcRbptarrRfJWtR/a-breakdown-of-ai-capability-levels-focused-on-ai-r-and-d
LjgcRbptarrRfJWtR
A breakdown of AI capability levels focused on AI R&D labor acceleration
ryan_greenblatt
In a variety of conversations about AI misalignment risks, I find that it is important to be able to clearly point at different levels of AI capability. My current favorite approach is to talk about how much the AI accelerates AI R&D[1] labor. I define acceleration of AI R&D labor by Y times as "the level of accelerati...
2024-12-22
https://www.lesswrong.com/posts/ojhLv79GhpKbfqxiF/how-i-saved-1-human-life-in-expectation-without-overthinking
ojhLv79GhpKbfqxiF
How I saved 1 human life (in expectation) without overthinking it
christopher-king
Does any of this sound familiar? You want to donate as effectively as possible, but you are worried about making the wrong choice. Should it be malaria nets, animal welfare, maybe x-risk? Also, how can you determine which charity evaluators are worthy of your trust? If you actually took the time to do an analysis, you ...
2024-12-22
https://www.lesswrong.com/posts/zKGyznvDB94aoJgx4/towards-mutually-assured-cooperation
zKGyznvDB94aoJgx4
Towards mutually assured cooperation
morrel
The development of AI has the potential to alter the global balance of power. Most significantly, sufficiently powerful AI could enable some nations to achieve total dominance (or existential catastrophe via loss of control), prompting others to consider nuclear responses to prevent such scenarios. To manage the escala...
2024-12-22
https://www.lesswrong.com/posts/8HSpbaAg8hvhiFDHB/checking-in-on-scott-s-composition-image-bet-with-imagen-3
8HSpbaAg8hvhiFDHB
Checking in on Scott's composition image bet with imagen 3
dave-orr
2.5 years ago Scott Alexander made a bet that by June of 2025, image gen should have more or less solved compositionality, operationalized through 5 prompts, must get at least 3 correct. There was a premature declaration of victory, but if the bet was settled I hadn't heard about it. It's time. Google's Imagen 3 gets 4...
2024-12-22
https://www.lesswrong.com/posts/ajT6q5aMokagfthvG/hire-or-become-a-thinking-assistant
ajT6q5aMokagfthvG
Hire (or Become) a Thinking Assistant
Raemon
Of the posts I've delayed writing for years, I maybe regret this one the most. I think more people (x-risk focused people in particular) should consider becoming (and hiring) metacognitive assistants. This is the single largest performance boost I know of – hire someone to sit with you and help you think. It doesn't he...
2024-12-23
https://www.lesswrong.com/posts/nzvgRhxyBSEL7gQK8/my-ai-timelines
nzvgRhxyBSEL7gQK8
My AI timelines
xpostah
2024-12-12 My AI timelines DISCLAIMER I'm not a deep learning expert. I understand theory of LLMs, RNNs, CNNs, etc. but I don't have experience training large models or curating large datasets or doing original DL research. Please consider getting the opinion of many people other than me. Many of the signatories on thi...
2024-12-22
https://www.lesswrong.com/posts/RhBLTMQZJduhkoice/woloch-and-wosatan
RhBLTMQZJduhkoice
Woloch & Wosatan
JackOfAllSpades
Setting: Present day. Somewhere in the finite frontrooms[1]. Wario and Woloch are in a coffee shop having a conversation. Wario: Woloch, are you on X? Woloch: Are you asking me if I'm rolling? Wario: No, man, I mean, do you journey through the twitterverse? Woloch: Why? Do you want to be my tweep? Wario: No, dickhead. ...
2024-12-22
https://www.lesswrong.com/posts/u9gL6FGJo33BtcrJm/a-primer-on-machine-learning-in-cryo-electron-microscopy
u9gL6FGJo33BtcrJm
A primer on machine learning in cryo-electron microscopy (cryo-EM)
abhishaike-mahajan
(7.9k words, 36 minutes reading time) Note: thank you to Jason Kaelber, a professor at Rutgers University and director of their cryo-EM facility, for commenting on drafts of this essay! Also thank you to Surge Biswas, the founder of Nabla Bio, for answering questions I had over cryo-EM. Introduction Cryo-electron micro...
2024-12-22
https://www.lesswrong.com/posts/5tkPpem2BeeaLhFBe/notes-from-copenhagen-secular-solstice-2024
5tkPpem2BeeaLhFBe
Notes from Copenhagen Secular Solstice 2024
soren-elverlin-1
Last night, we held the Traditional Copenhagen Secular Solstice celebration. Here’s a brief overview of what went well, what could be improved and reflections on the songs. What Went Well Growth in Attendance Attendance increased to 14 participants, which is exciting! Rituals gain a lot from being performed by many peo...
2024-12-22
https://www.lesswrong.com/posts/HChtxHbzpbfTMaFeG/it-looks-like-there-are-some-good-funding-opportunities-in
HChtxHbzpbfTMaFeG
It looks like there are some good funding opportunities in AI safety right now
Benjamin_Todd
The AI safety community has grown rapidly since the ChatGPT wake-up call, but available funding doesn’t seem to have kept pace. However, there’s a more recent dynamic that’s created even better funding opportunities, which I witnessed as a recommender in the most recent SFF grant round.[1] Most philanthropic (vs. gover...
2024-12-22
https://www.lesswrong.com/posts/2jZhEHLgyKLeoYprR/subfunctional-overlaps-in-attentional-selection-history
2jZhEHLgyKLeoYprR
subfunctional overlaps in attentional selection history implies momentum for decision-trajectories
Emrik North
ASH-SuFuOvMo (momentum from the subfunctional overlap in attentional selection-history) explains why & when the countdown-trick to get out of bed when super-groggy actually works. This is a trick that I use for getting out of bed in the morning - quite literally:  I count down from 10 and get out of bed after the "1". ...
2024-12-22
https://www.lesswrong.com/posts/DFnBXCabR8KwNYq7N/the-alignment-simulator
DFnBXCabR8KwNYq7N
The Alignment Simulator
yair-halberstadt
When I try to talk to my friends about risks from rogue AI, the reaction is often one of amusement. The idea that AIs would go around killing everyone instead of just doing what we tell them to do seems like science fiction. Can we actually show them an example of a current AI going off the rails in a dangerous way? An...
2024-12-22