AI Alignment Tag Examples

1. Embedded Agency (full-text version)
2. Goodhart Taxonomoy
3. An Untrollable Mathematician Illustrated
4. AlphaGo Zero and the Foom Debate
5. The unexpected difficulty of comparing AlphaStar to humans
6. Outperforming the human Atari benchmark
7. How does OpenAI's language model affect our AI timeline estimates?
8. Jeff Hawkins on neuromorphic AGI within 20 years
9. What failure looks like
10. Soft takeoff can still lead to decisive strategy advantage
11. My current framework for thinking about AGI timelines

Examples of AI Alignment Community Posts (tagged both AI Alignment and Community)

1. 2019 AI Alignment Literature Review and Charity Comparison
2. What I'll be doing at MIRI
3.  Offer of collaboration and/or mentorship
4. Where are people thinking and talking about global coordination for AI safety?

Rationality Tag Examples
 
Positive Examples

1. Highly Advanced Epistemology 101 for Beginners
2. Where Recursive Justification Hits Rock Bottom
3. Novum Organum: Introduction
4. What is Evidence?
5. Sequence introduction: non-agent and multiagent models of mind
6. Adult Neurogenesis – A Pointed Review
7. Biases: An Introduction
8. A Sketch of Good Communication
9. Double Crux –– A Strategy for Resolving Disagreements
10. "Focusing" for Skeptics
11. Active Curiosity vs Open Curiosity
12. The Schelling Choice is "Rabbit", not "Stag"
13. Understanding information cascades
14. The Neglected Virtue of Scholarship
15. The mechanics of my recent productivity
16. More Dakka

Negative Examples

1. The First Rung: Insights from 'Linear Algebra Done Right'
2. Tech economics pattern: "Commoditize Your Complement"
3. On Building Theories of Histories

Unusual Edge Cases (included)

1. Can You Prove Two Particles Are Identical?