“Introduction: Gaussian Natural Latents” by Haru

Short introductory post for my research direction: Gaussian Natural Latents. I explain the motivation and give a preview of the forthcoming results. The Natural Abstractions agenda, in my view, is a promising research program that asks important theoretical questions about the nature of agency and optimization. Here's an excerpt from Nate Soares' excellent post: Imaginary John: I suspect there's a common format to concepts, that is a fairly objective fact about the math of the territory, and that—if mastered—could be used to understand an AGI's concepts. And perhaps select the ones we wish it would optimize for. Which isn't the whole problem, but sure is a big chunk of the problem. (And other chunks might well be easier to address given mastery of the fairly-objective concepts of "agent" and "optimizer" and so on.) Nate: This does seem to me like it's trying to attack the actual problem! I have my doubts about this particular line of research (and those doubts are on my list of things to write up), but hooray for a proposal that, if it succeeded by its own lights, would address this hard problem! I think that Natural Abstractions ideally wants to grow [...] ---Outline:(02:22) Why Gaussians?(03:53) Preview of Results(04:01) Exact natural latents don't exist(04:14) Approximate natural latents have exact prices(04:33) Characterizing the behavior of optimal latents(05:09) The Gaussian case of an open conjecture(05:27) What this Means The original text contained 2 footnotes which were omitted from this narration. --- First published: June 18th, 2026 Source: https://www.lesswrong.com/posts/H8ktAMBv8jQr8JymL/introduction-gaussian-natural-latents --- Narrated by TYPE III AUDIO. ---Images from the article:Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.