Or: An anti-orthogonality thesis based on selection Written as part of the MATS 9.1 extension program, mentored by Richard Ngo[1]. Introduction One of the historical motivations for taking the AI alignment problem seriously is the orthogonality thesis, which states[2]: > Intelligence and final goals are orthogonal: more or less any...
A familiarity with the pre-rigor/post-rigor ontology might be helpful for reading this post. University math is often sold to students as imbuing in them the spirit of rigor and respect for iron-clad truth. The value in a real analysis course comes not from the specific results that it teaches —...
This post is aimed primarily at people who know what a category is in the extremely broad strokes, but aren't otherwise familiar or comfortable with category theory. One of mathematicians' favourite activities is to describe compatibility between the structures of mathematical artefacts. Functions translate the structure of one set to...
Or: Identities as Schelling Fences for Embedded Agents This post was written as part of research done at MATS 9.0 under the mentorship of Richard Ngo. He contributed significantly to the ideas discussed within. Introduction This post questions the sanctity of the "agent" and discusses how Temporal Instances (TIs) of...
This post was written as part of research done at MATS 9.0 under the mentorship of Richard Ngo. You can conceptualise Embedded agents as inducing a partition[1] of the world into "the agent", "the external world", and the dynamics that mediate their interaction; the dynamics include observations and actions. The...
Last December, we ran a workshop on exploring civilizational sanity. Our core team consisted of the lead organizer and two co-organizers, one dedicated mostly to operations (ops). Other staff included a cook and two part-time volunteers. Ten people participated in the event. Overall, it was a success! Some things went...
This post was written while at MATS 9.0 under the mentorship of Richard Ngo. It's only meta-related to my research. I would like to start by quoting a point Jan Kulveit made about economics culture in a recent post. > non-mathematical, often intuitive reasoning of [an] economist leads to some...