ACX
Janus' Simulators
Scott Alexander explores the concept of AI as 'simulators' and its implications for AI alignment and human cognition.
19 min read 2,821 words
A thread through the archive
AI alignment
Essays tagged “AI alignment”. Follow an idea across the archive.
Essays on AI alignment
39 essaysLW
Alexander and Yudkowsky on AGI goals
A technical dialogue between Scott Alexander and Eliezer Yudkowsky exploring why AI alignment is difficult, covering the inapplicability of human moral development analogies, the nature of AI consequentialism, and skepticism about acausal trade as a safety mechanism.
62 min read 9,555 words
ACX
How Do AIs' Political Opinions Change As They Get Smarter And Better-Trained?
Scott examines how AI language models' opinions and behaviors evolve as they become more advanced, discussing implications for AI alignment.
28 min read 4,238 words
ACX
Perhaps It Is A Bad Thing That The World's Leading AI Companies Cannot Control Their AIs
Scott Alexander analyzes the shortcomings of OpenAI's ChatGPT, highlighting the limitations of current AI alignment techniques and their implications for future AI development.
18 min read 2,695 words
ACX
Can This AI Save Teenage Spy Alex Rider From A Terrible Fate?
Scott Alexander examines Redwood Research's attempt to create an AI that avoids generating violent content, using Alex Rider fanfiction as training data.
34 min read 5,221 words
ACX
CHAI, Assistance Games, And Fully-Updated Deference
Scott Alexander explains and analyzes the debate between MIRI and CHAI on AI alignment strategies, focusing on the challenges and potential flaws in CHAI's 'assistance games' approach.
36 min read 5,459 words
ACX
Unpredictable Reward, Predictable Happiness
Scott examines two types of happiness - one affected by predictability and one that persists - through various examples and neuroscientific concepts.
23 min read 3,488 words
ACX
ELK And The Problem Of Truthful AI
Scott Alexander examines the Eliciting Latent Knowledge (ELK) problem in AI alignment and various proposed solutions.
42 min read 6,490 words
ACX
Deceptively Aligned Mesa-Optimizers: It's Not Funny If I Have To Explain It
Scott Alexander explains mesa-optimizers in AI alignment, their potential risks, and the challenges of creating truly aligned AI systems.
23 min read 3,483 words
ACX
Contra Hoel On Aristocratic Tutoring
Scott Alexander argues against Erik Hoel's claim that the decline of 'aristocratic tutoring' explains the perceived lack of modern geniuses, offering alternative explanations and counterexamples.
16 min read 2,422 words
ACX
Practically-A-Book Review: Yudkowsky Contra Ngo On Agents
Scott Alexander reviews a dialogue between Yudkowsky and Ngo on AI alignment difficulty, exploring the challenges of creating safe superintelligent AI.
33 min read 5,013 words
SSC
The Craft And The Codex
Scott Alexander discusses how his blog contributes to developing rationality skills through analysis of complex issues and community discussion, despite not focusing directly on core rationality techniques.
7 min read 986 words
SSC
How Does Recent AI Progress Affect The Bostromian Paradigm?
Scott Alexander examines how recent AI progress in neural networks might challenge the Bostromian paradigm of AI risk, exploring potential implications for AI goal alignment and motivation systems.
15 min read 2,240 words
LW
Superintelligence FAQ
Scott explains why superintelligent AI poses serious risks, how a 'fast takeoff' could leave insufficient time to solve safety problems, and why even simple-sounding goals could lead to catastrophic outcomes without proper alignment research.
54 min read 8,281 words