Categories
Recent Posts
- Hidden Role Games as a Trusted Model Eval
- AI Predictions 2026
- How to Tell if You’ve Instilled a False Belief in Your LLM
- On Contact, Part 1
- Retrospective: 12 Months Since MIRI
- Evaluating Stability of Unreflective Alignment
- Research Retrospective, Summer 2022
- In Search of Strategic Clarity
- Optimization and Adequacy in Five Bullets
- What I Got From EAGx Boston 2022
- Unfinished Thoughts on ELK
- Moravec’s Paradox Comes From The Availability Heuristic
- True EA Alignment is Overrated
- Which Things Are Worth Memorizing?
- Quick Reminder That Your Ability to Do Good Is Ridiculous
- DIY Asymmetric Weapons With Symmetric Weapons And Bayescraft
- The “Ratchets vs Springs” Heuristic
- I Have Changed My Mind About Asymmetric Weapons
- We Should Be Testing Frameworks
- Math, Science, and Logic Are Predictive Models
- Discuss the Substance, Not the Symbol
Tags
artificial-intelligence (8) cross-posted (10) effective-altruism (3) personal (3) philosophy (1) rationality (10)
Archive
- March 2026 1
- February 2026 1
- September 2025 1
- October 2024 1
- September 2024 1
- February 2024 1
- October 2022 1
- July 2022 1
- June 2022 1
- April 2022 1
- January 2022 1
- October 2021 1
- September 2021 1
- July 2021 1
- April 2021 3
- March 2021 4