flâneur

Formalizing «Boundaries» with Markov blankets — LessWrong

lesswrong.com · 3,462 words · saved by 1 readers

[The post is largely a conceptual distillation of Andrew Critch’s Part 3a: Defining boundaries as directed Markov blankets.] By the end of this section, I want you to understand the following diagram (Pearlian causal diagram): Also: I will assume a basic familiarity with Markov chains in this post. First, I want you to imagine a simple Markov chain that represents the fact that a human influences itself over time: Second, I want you to imagine a Markov chain that represents the fact that the environment[1] influences itself over time: Okay. Now, notice that in between the human and its environment there’s some kind of boundary. For example, their skin (a physical boundary) and their interpretation/cognition (an informational boundary). If this were not a human but instead a bacterium, then the boundary I mean would (mostly) be the bacterium’s cell membrane. Third, imagine a Markov chain that represents that boundary influencing itself over time: Okay, so we have these three Markov chai

x Formalizing «Boundaries» with Markov blankets — LessWrong Boundaries (membranes) for AI safety by Chipmonk Boundaries / Membranes [technical] Causality Free Energy Principle Outer Alignment World Modeling Techniques AI World Modeling Frontpage 23 Formalizing «Boundaries» with Markov blankets by Chris Lakin 19th Sep 2023 4 min read 20 23 How could «boundaries» be formally specified? Markov blankets seem to be one fitting abstraction. [The post is largely a conceptual distillation of Andrew Critch’s Part 3a: Defining boundaries as directed Markov blankets .] Explaining Markov blankets By the e

related reading