Blog
Also available on Substack.
2026
- Aug 29 Book Notes: Chokepoints (~14 min)
- Aug 8 ‘AI Escaped Its Sandbox’ — What Does That Actually Mean? — For non-technical readers (~8 min)
- Aug 2 Why I Watch Soccer (~7 min)
- Jul 23 Too Many Fire Alarms? (~2 min)
- Jul 6 On Writing (Code) (~3 min)
- Jun 16 On Failing Exams And Job Interviews (~1 min)
- Mar 29 Parkinson’s Law of Worry (~2 min)
- Feb 15 It’s Happening, Isn’t It? (~2 min)
2025
- Dec 31 Book Quotes From 2025 (~9 min)
- Dec 20 10% Pledge — Writing What I Can (~2 min)
- Nov 23 A Browser Extension I Made — “Elon’s X feed but without politics” (~7 min)
- Sep 28 Why Superintelligence Would Kill Us All — A 3-minute version (~4 min)
- Jul 29 People Are Less Happy Than They Seem (~1 min)
- Jul 6 How an LLM Thinks — Overview of “Tracing the Thoughts of a Large Language Model” (~6 min)
- Jun 20 [SK] AI na FI MUNI—Retrospektíva — Retrospektíva štúdia AI na FI MUNI (~7 min)
- Jan 31 DeepSeek R1-Zero, (R1) — Keep It Simple, Stupid (~3 min)
- Jan 22 Reinforcement Learning – A Reference (~5 min)
- Jan 12 Scheming and Deceptive AIs — Notes on two recent alignment papers (~6 min)
2024
- Dec 19 Can LLMs Predict When We Learn Different Words? (~6 min)
- Sep 26 Let’s Verify Step by Step — Paper summary (~3 min)
- Jun 19 Scaling Monosemanticity — Paper summary (~5 min)
- Feb 24 The Inner Alignment Problem (~5 min)
- Jan 29 Sleeper Agents — Paper summary (~13 min)
2023
- Dec 26 News Hiatus (~2 min)
- Sep 24 Notes on The Rise and Fall of the Third Reich (~4 min)
- Aug 19 Notes on Hotz vs. Yudkowski AI Safety Debate (~2 min)
- Aug 16 Virtual Reality as a Source of Suffering (~2 min)
- Jan 31 Focus on the Trajectory, Not the Current State (~3 min)
2022
- May 1 Inaccurate Memories (~3 min)
- Mar 22 Starting a Blog (~1 min)