Writing
- Ideonomy
- Sensory Transducers November 26, 2024
- Introduction to Ideonomy November 23, 2024
- Negation in Ideonomy May 4, 2024
- Properties and Dimensions in Ideonomy April 25, 2024
- Machine Behavior and Human-AI Interaction
- Reality checks for AI agents (Leaflet) September 20, 2026
- Why anthropomorphize language models? (Leaflet) September 19, 2026
- Distinguishing between LLM injection detection methods (Leaflet) November 1, 2025
- How might LLMs detect injected tokens? (Leaflet) October 8, 2025
- Advantages of AI Therapists April 19, 2024
- Novel Uses For LLMs April 9, 2024
- AI Alignment
- Can Mechanistic Interpretability Help With Prompt Injection? February 14, 2025
- A Simple Evaluation for Transformative AI February 8, 2025
- A Three-Facet Framework for AI Alignment February 6, 2025
- Subtypes of Control in AI Alignment February 6, 2025
- Miscellaneous
- X-Risks and S-Risks From Alien Invasion November 3, 2025
- The Anti-Preparedness Paradox March 15, 2025
- Revisiting Patrick Gunkel's 'Future Headlines' October 9, 2024
- How to Think August 8, 2024
- Preparing the World for Superintelligence June 8, 2024
- The Unbearable Weight of the Wayback Machine April 4, 2024
Note: I mostly write new posts on my blog these days.