Colorful DevInterp experiments

May 7, 2025, 4:47 AM

Coupling for Decouplers

Jacob Falkovich

Apr 8, 2025, 8:36 PM

Probability Theory Fundamentals 102

Ape in the coat

Mar 26, 2025, 6:11 AM

Orcas

Towards_Keeperhood

Mar 16, 2025, 8:53 AM

The Theoretical Foundations of Reward Learning

Feb 28, 2025, 1:19 PM

Meta-theory of rationality

Feb 20, 2025, 6:17 PM

Radical empathy

Jan 6, 2025, 5:55 PM

AIXI Agent foundations

Jan 1, 2025, 1:57 AM

Substrate Needs Convergence

Dec 28, 2024, 10:14 PM

Prospects for Solartopia

transhumanist_atom_understander

Dec 21, 2024, 4:06 AM

Miss Macross: My Life as the Star

Trevor Hill-Hand

Dec 4, 2024, 10:39 PM

How might we solve the alignment problem?

Oct 30, 2024, 5:26 PM

The Darwinian Trap

Oct 21, 2024, 9:26 PM

Intuitive Self-Models

Sep 18, 2024, 9:35 PM

The AI Alignment and Deployment Problems

Sep 13, 2024, 3:49 PM

Meaning in the Multiverse

Sep 5, 2024, 6:00 AM

Welfare and moral weights

Aug 15, 2024, 4:19 AM

Linear Diffusion of Sparse Lognormals: Causal Inference Against Scientism

Aug 7, 2024, 8:04 PM

Acausal Trade

Jul 31, 2024, 5:00 PM

CAST: Corrigibility As Singular Target

Jun 8, 2024, 12:54 AM

Situational Awareness Summarized

Jun 6, 2024, 7:28 PM

The Math of Geometric Utilitarianism

StrivingForLegibility

May 31, 2024, 7:13 PM

Geometric Utilitarianism

StrivingForLegibility

May 31, 2024, 7:07 PM

Procedural Executive Function

May 23, 2024, 12:28 PM

Big Picture AI Safety

May 23, 2024, 11:24 AM

Statistical Mechanics

Apr 23, 2024, 3:42 PM

Aspiration-based, non-maximizing AI agent designs [Aspiration-based designs]

Mar 28, 2024, 9:14 AM

AI Control

Mar 24, 2024, 10:29 PM

Adverse Selection

Mar 14, 2024, 10:05 PM

Provable AI Alignment (ProvAIA)

Mar 11, 2024, 12:44 PM

Weak-To-Strong Generalization (W2SG)

Mar 8, 2024, 8:00 PM

On Wholesomeness

Feb 29, 2024, 10:51 AM

The Sense Of Physical Necessity: A Naturalism Demo

Feb 24, 2024, 10:02 PM

Deliberative Algorithms as Scaffolding

Feb 17, 2024, 10:39 PM

Counterfactuals and Updatelessness

Feb 10, 2024, 8:42 PM

Quantitative cruxes and evidence in Alignment

Feb 10, 2024, 4:55 AM

Distributed Strategic Epistemology

StrivingForLegibility

Dec 27, 2023, 5:34 PM

Delegative Decision Theory

StrivingForLegibility

Dec 21, 2023, 7:29 PM

Formalising Catastrophic Goodhart

Dec 11, 2023, 10:08 PM

From Big Ideas To Real-World Results

Dec 11, 2023, 1:43 PM

The LessWrong Community Census

Dec 1, 2023, 9:39 PM

Rapid Coordination Field Manual

Nov 30, 2023, 7:56 PM

The Ethicophysics

Nov 30, 2023, 3:08 AM

Exploring the Digital Wildnerness

Nov 25, 2023, 12:07 PM

Game Theory without Argmax

Nov 12, 2023, 4:39 PM

The Value Change Problem (sequence)

Oct 26, 2023, 1:11 PM

Large Language Model Psychology

Quentin FEUILLADE--MONTIXI

Oct 11, 2023, 2:10 PM

Monthly Algorithmic Problems in Mech Interp

CallumMcDougall

Sep 25, 2023, 3:57 PM

Crowdsourced knowledge base

Aug 30, 2023, 10:27 AM

Waterloo Rationality Meetups Showcase

Aug 18, 2023, 10:39 PM

Consciousness Discourse

Aug 13, 2023, 7:17 AM

An Opinionated Guide to Computability and Complexity

Jul 24, 2023, 6:00 PM

Narrative Theory

Jul 14, 2023, 7:18 PM

Developmental Interpretability

Jul 3, 2023, 6:30 PM

Meta-rationality

Jun 26, 2023, 3:21 PM

Catastrophic Risks From AI

Jun 22, 2023, 6:36 PM

Distilling Singular Learning Theory

Jun 16, 2023, 6:51 AM

Towards Causal Foundations of Safe AGI

Jun 9, 2023, 4:25 PM

CAIS Philosophy Fellowship Midpoint Deliverables

Jun 7, 2023, 11:24 PM

Machine Learning For Scientific Discovery

May 19, 2023, 6:35 AM

Replacing fear

May 15, 2023, 5:55 AM

The Nuts and Bolts of Naturalism

Apr 22, 2023, 7:16 PM

Interpreting a Maze-Solving Network

Apr 20, 2023, 10:36 PM

From Atoms To Agents

Mar 31, 2023, 9:20 PM

Interpreting Othello-GPT

Mar 29, 2023, 10:12 PM

Singularity now: is GPT-4 trying to takeover the world?

Christopher King

Mar 27, 2023, 3:39 PM

I’m pretty sure AI is as dumb as We Are

Mar 10, 2023, 2:46 PM

A Data-Driven Path to Effortless Weightloss: Potatoes, Potassium, Drugs, Chocolate, and much much more

Mar 1, 2023, 7:41 PM

The Shallow Reality of ‘Deep Learning Theory’

Feb 22, 2023, 10:17 PM

Leveling Up: advice & resources for junior alignment researchers

Feb 15, 2023, 7:15 PM

LLM Mindreading

Jan 19, 2023, 12:55 AM

On Becoming a Great Alignment Researcher (Efficiently)

Jan 5, 2023, 12:03 AM

Simulators

Jan 1, 2023, 1:52 AM

Simulator seminar sequence

Jan 1, 2023, 12:34 AM

Bias in Evaluating AGI X-Risks

Dec 27, 2022, 7:52 AM

Developments toward Uncontrollable AI

Dec 26, 2022, 8:44 AM

Why Not Try Build Safe AGI?

Dec 24, 2022, 8:34 AM

Alignment Stream of Thought

Dec 2, 2022, 6:44 PM

Geometric Rationality

Scott Garrabrant

Nov 21, 2022, 6:58 PM

Some comments on the CAIS paradigm

Nov 15, 2022, 10:57 AM

(Lawrence’s) Reflections on Research

Nov 14, 2022, 4:00 AM

Entropy from first principles

Nov 6, 2022, 11:19 PM

[Redwood Research] Causal Scrubbing

Oct 26, 2022, 8:38 PM

Generalised models

Stuart_Armstrong

Oct 20, 2022, 9:32 AM

Experiments in instrumental convergence

Oct 12, 2022, 9:15 PM

Research Journals

Shoshannah Tekofsky

Sep 22, 2022, 7:20 PM

Hypothesis Subspace

Sep 12, 2022, 11:55 AM

Maximal Lottery-Lotteries

Scott Garrabrant

Sep 12, 2022, 1:27 AM

Thoughts in Philosophy of Science of AI Alignment

Aug 19, 2022, 9:22 AM

“Why Not Just...”

Aug 8, 2022, 6:15 PM

Meetup in a box

Aug 4, 2022, 10:04 PM

Law-Following AI

Aug 4, 2022, 6:21 PM

My AI Risk Model

Jul 21, 2022, 10:36 PM

Shard Theory

Jul 14, 2022, 1:36 AM

AGI-assisted Alignment

Tor Økland Barstad

Jul 9, 2022, 4:33 PM

Alignment For Foxes

Jun 20, 2022, 3:03 PM

Selection Theorems: Modularity

CallumMcDougall

Jun 16, 2022, 1:09 PM

Breaking Down Goal-Directed Behaviour

Jun 9, 2022, 10:05 PM

A Tour of AI Timelines

Jun 6, 2022, 6:21 PM

Math Upskilling Notes

May 26, 2022, 1:26 AM

Networking: A Game Manual

Severin T. Seehrich

May 17, 2022, 11:22 PM

Basic Foundations for Agent Models

May 16, 2022, 6:13 PM

Pragmatic AI Safety

May 16, 2022, 6:07 PM

Insights from Dath Ilan

May 11, 2022, 9:47 PM

An Inside View of AI Alignment

Ansh Radhakrishnan

May 11, 2022, 2:08 AM

AI Races and Macrostrategy

Michaël Trazzi

May 5, 2022, 10:37 PM

Treacherous Turn

Michaël Trazzi

May 5, 2022, 10:31 PM

The Inside View (Podcast)

Michaël Trazzi

May 5, 2022, 10:25 PM

Winding My Way Through Alignment

May 5, 2022, 3:04 AM

Interpretability Research for the Most Important Century

Apr 25, 2022, 10:56 PM

Neural Networks, More than you wanted to Show

Apr 19, 2022, 8:14 PM

Concept Extrapolation

Stuart_Armstrong

Apr 16, 2022, 10:32 AM

Calculus in Game and Decision Theory

Apr 1, 2022, 2:45 PM

Alignment Stream of Thought

Mar 27, 2022, 12:48 AM

Civilization & Cooperation

Duncan Sabien (Deactivated)

Mar 21, 2022, 12:31 AM

Trends in Machine Learning

Feb 17, 2022, 3:13 PM

Fundamental Uncertainty: A Book

Gordon Seidoh Worley

Feb 6, 2022, 6:49 PM

Intuitive Introduction to Functional Decision Theory

Feb 2, 2022, 1:25 PM

Intro to Brain-Like-AGI Safety

Jan 26, 2022, 3:51 AM

Mechanics of Tradecraft

Jan 16, 2022, 2:39 PM

Independent AI Research

Dec 19, 2021, 11:37 PM

Agency: What it is and why it matters

Daniel Kokotajlo

Dec 4, 2021, 9:36 PM

Thoughts on Corrigibility

Nov 24, 2021, 7:39 PM

Epistemic Cookbook for Alignment

Oct 18, 2021, 9:05 AM

Transformative AI and Compute

Sep 23, 2021, 2:00 PM

AI Safety Subprojects

Stuart_Armstrong

Sep 20, 2021, 12:18 PM

The Coordination Frontier

Sep 18, 2021, 9:39 PM

D&D.Sci

Sep 11, 2021, 8:02 PM

Framing Practicum

Aug 8, 2021, 9:26 PM

Rationality in Research

Aug 8, 2021, 8:12 PM

AI Defense in Depth: A Layman’s Guide

Aug 8, 2021, 5:04 PM

Modeling Transformative AI Risk (MTAIR)

Jul 28, 2021, 1:17 PM

Practical Guide to Anthropics

Stuart_Armstrong

Jul 8, 2021, 3:11 PM

The Causes of Power-seeking and Instrumental Convergence

Jul 5, 2021, 9:49 PM

2021 Less Wrong Darwin Game

Jun 4, 2021, 9:44 AM

Finite Factored Sets

Scott Garrabrant

May 25, 2021, 8:06 PM

Comprehensive Information Gatherings

May 1, 2021, 11:22 AM

Using Credence Calibration for Everything

Apr 6, 2021, 1:22 PM

Anthropic Decision Theory

Stuart_Armstrong

Mar 30, 2021, 3:51 PM

Reviews for the Alignment Forum

Mar 28, 2021, 2:49 PM

Notes on Virtues

Mar 4, 2021, 2:15 AM

Participating in a Covid-19 Vaccination Trial

Feb 27, 2021, 12:50 AM

Predictions & Self-awareness

Feb 13, 2021, 10:16 PM

Pointing at Normativity

Feb 9, 2021, 4:28 PM

Counterfactual Planning

Feb 2, 2021, 5:10 PM

AI Alignment Unwrapped

Jan 20, 2021, 1:47 PM

AI Timelines

Daniel Kokotajlo

Jan 17, 2021, 7:48 AM

Pseudorandomness Contest

Jan 15, 2021, 6:22 AM

Bayeswatch

Jan 8, 2021, 6:03 AM

Cryonics Signup Guide

Jan 6, 2021, 12:13 AM

NLP and other Self-Improvement

Jan 3, 2021, 1:25 PM

Takeoff and Takeover in the Past and Future

Daniel Kokotajlo

Dec 31, 2020, 3:04 PM

Forecasting Newsletter

Dec 14, 2020, 1:35 PM

Sunzi’s《Methods of War》

Nov 19, 2020, 3:06 AM

COVID-19 Updates and Analysis

Nov 10, 2020, 4:27 AM

Deconfusing Goal-Directedness

Nov 9, 2020, 9:40 AM

The Grueling Subject

Oct 31, 2020, 1:40 PM

2020 Less Wrong Darwin Game

Oct 23, 2020, 10:44 AM

Quantitative Finance

Oct 10, 2020, 5:46 AM

Factored Cognition

Aug 30, 2020, 5:37 PM

Zen and Rationality

Gordon Seidoh Worley

Aug 11, 2020, 8:26 PM

Privacy Practices

Jul 29, 2020, 5:27 AM

Staying Sane While Taking Ideas Seriously

Jun 27, 2020, 5:16 PM

Naturalized Induction

Jun 25, 2020, 12:29 PM

What You Can and Can’t Learn from Games

Jun 20, 2020, 10:12 PM

Short Stories

Jun 14, 2020, 8:35 AM

Toying With Goal-Directedness

Jun 11, 2020, 6:27 PM

Against Rationalization II

May 21, 2020, 9:02 PM

Implications of Logical Induction

Mar 21, 2020, 10:25 PM

Through the Haskell Jungle

Mar 18, 2020, 6:54 PM

Lessons from Isaac

Mar 14, 2020, 5:12 PM

Filk

Gordon Seidoh Worley

Feb 18, 2020, 6:28 PM

Subagents and impact measures

Stuart_Armstrong

Feb 13, 2020, 11:42 AM

If I were a well-intentioned AI...

Stuart_Armstrong

Jan 22, 2020, 2:30 PM

Moral uncertainty

Dec 30, 2019, 1:59 AM

Medical Paradigms

Dec 29, 2019, 5:17 PM

Understanding Machine Learning

Dec 23, 2019, 8:10 AM

Antimemetics

Dec 8, 2019, 10:36 AM

Gears of Aging

Nov 20, 2019, 6:35 AM

Map and Territory Cross-Posts

Gordon Seidoh Worley

Nov 15, 2019, 11:52 PM

Phenomenological AI Alignment

Gordon Seidoh Worley

Nov 15, 2019, 3:38 AM

Changing your Mind With Memory Reconsolidation

Matt Goldenberg

Nov 13, 2019, 7:46 PM

base-line to enlightenment—the physical route to better

Nov 8, 2019, 12:23 PM

Partial Agency

Oct 19, 2019, 5:27 AM

Concept Safety

Oct 2, 2019, 12:50 PM

AI Alignment Writing Day 2019

Oct 1, 2019, 12:06 AM

Novum Organum

Sep 19, 2019, 10:32 PM

Logical Counterfactuals and Proposition graphs

Sep 5, 2019, 4:56 PM

AI Alignment Writing Day 2018

Aug 13, 2019, 10:24 PM

Daily Insights

Matthew Barnett

Jul 30, 2019, 7:29 PM

Model Comparison

Jul 16, 2019, 7:47 PM

Reframing Impact

Jul 8, 2019, 12:55 AM

Alternate Alignment Ideas

May 15, 2019, 5:22 PM

Concepts in formal epistemology

May 11, 2019, 8:56 PM

So You Want To Colonize The Universe

May 10, 2019, 4:48 AM

Mechanism Design

Mar 22, 2019, 11:02 PM

Decision Analysis

Mar 10, 2019, 12:07 PM

Priming

Scott Alexander

Mar 9, 2019, 12:37 PM

Positivism and Self Deception

Scott Alexander

Mar 9, 2019, 12:27 PM

Kickstarter for Coordinated Action

Feb 21, 2019, 9:48 PM

Prediction-Driven Collaborative Reasoning Systems

Feb 21, 2019, 12:54 AM

Assorted Maths

Feb 10, 2019, 3:28 PM

Multiagent Models of Mind

Jan 16, 2019, 2:39 PM

Open Threads

Jan 9, 2019, 8:35 PM

Keith Stanovich: What Intelligence Tests Miss

Jan 7, 2019, 12:20 PM

Filtered Evidence, Filtered Arguments

Dec 7, 2018, 8:16 PM

CDT=EDT?

Dec 7, 2018, 8:05 PM

Fixed Points

Scott Garrabrant

Nov 24, 2018, 1:32 PM

Metaethics

Eliezer Yudkowsky

Nov 1, 2018, 1:23 AM

Quantum Physics

Eliezer Yudkowsky

Sep 23, 2018, 9:26 AM

Ethical Injunctions

Eliezer Yudkowsky

Sep 22, 2018, 12:39 AM

Alignment Newsletter

Aug 1, 2018, 6:31 PM

Share Models, Not Beliefs

Jul 2, 2018, 11:30 PM

Voting Theory Primer for Rationalists

Apr 22, 2018, 3:10 AM

Becoming Stronger

Apr 17, 2018, 3:23 PM

Hufflepuff Cynicism

Mar 31, 2018, 2:19 AM

Tensions in Truthseeking

Mar 12, 2018, 7:40 AM

Murphy’s Quest

Mar 11, 2018, 7:02 AM

Project Hufflepuff

Feb 3, 2018, 9:06 PM

Instrumental Rationality

lifelonglearner

Jan 1, 2018, 6:33 AM

Philosophy Corner

Charlie Steiner

Dec 20, 2017, 11:35 PM

Rational Ritual

Nov 25, 2017, 11:40 PM

The Darwin Game

Nov 21, 2017, 11:34 PM

Drawing Less Wrong

Nov 21, 2017, 4:37 AM

Keyboard shortcuts

Keys shown in yellow (e.g., ]) are accesskeys, and require a browser-specific modifier key (or keys).

Keys shown in grey (e.g., ?) do not require any modifier keys.

General
? Show keyboard shortcuts
Esc Hide keyboard shortcuts

Site navigation
h Go to Home (a.k.a. “Frontpage”) view
f Go to Featured (a.k.a. “Curated”) view
a Go to All (a.k.a. “Community”) view
m Go to Meta view
v Go to Tags view
c Go to Recent Comments view
r Go to Archive view
q Go to Sequences view
t Go to About page
u Go to User or Login page
o Go to Inbox page

Page navigation
, Jump up to top of page
. Jump down to bottom of page
/ Jump to top of comments section
s Search

Page actions
n New post or comment
e Edit current post

Post/comment list views
. Focus next entry in list
, Focus previous entry in list
; Cycle between links in focused entry
Enter Go to currently focused entry
Esc Unfocus currently focused entry
] Go to next page
[ Go to previous page
\ Go to first page
e Edit currently focused post

Editor
k Bold text
i Italic text
l Insert hyperlink
q Blockquote text

Appearance
= Increase text size
- Decrease text size
0 Reset to default text size
′ Cycle through content width settings
1 Switch to default theme [A]
2 Switch to dark theme [B]
3 Switch to grey theme [C]
4 Switch to ultramodern theme [D]
5 Switch to simple theme [E]
6 Switch to brutalist theme [F]
7 Switch to ReadTheSequences theme [G]
8 Switch to classic Less Wrong theme [H]
9 Switch to modern Less Wrong theme [I]
; Open theme tweaker
Enter Save changes and close theme tweaker
Esc Close theme tweaker (without saving)

Slide shows
l Start/resume slideshow
Esc Exit slideshow
→↓ Next slide
←↑ Previous slide
Space Reset slide zoom

Miscellaneous
x Switch to next view on user page
z Switch to previous view on user page
` Toggle compact comment list view
g Toggle anti-kibitzer