Understanding Agency through Markov Blankets — LessWrong
lesswrong.com · 1,552 words · saved by 1 readers
This post was written as part of research done at MATS 9.0 under the mentorship of Richard Ngo. …
x Understanding Agency through Markov Blankets — LessWrong MATS Program Agent Foundations AI World Modeling Frontpage 25 Understanding Agency through Markov Blankets by Ashe Vazquez Nuñez 12th Jan 2026 4 min read 2 25 This post was written as part of research done at MATS 9.0 under the mentorship of Richard Ngo. Summary This post illustrates with examples how the qualitative concepts behind active inference and its usage of Markov blankets can be used to clarify agentic behaviour. If we see agents as predictors that minimise surprisal about their internal states by interacting with external st
related reading
- Irrationality as a Defense Mechanism for Reward-hacking — LessWronglesswrong.com
- Formalizing «Boundaries» with Markov blankets — LessWronglesswrong.com
- Study Guide — LessWronglesswrong.com
- Towards a scale-free theory of intelligent agencymindthefuture.info
- Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
- Agents as webs of beliefs - by Richard Ngomindthefuture.info
- Beliefs are Chosen to Serve Goals — LessWronglesswrong.com
- Embedded Agency (full-text version) — LessWronglesswrong.com
- Simulators — LessWronglesswrong.com
- The behavioral selection model for predicting AI motivations — LessWronglesswrong.com
- A case for LLMs as Self-predictors — LessWronglesswrong.com
- Open-minded updatelessness — LessWronglesswrong.com