David Lorell

Featured in:

Articles

Instrumental Goals Are A Different And Friendlier Kind Of Thing Than Terminal Goals — LessWrong

Jan 24, 2025 | lesswrong.com | David Lorell

The CakeImagine that I want to bake a chocolate cake, and my sole goal in my entire lightcone and extended mathematical universe is to bake that cake. I care about nothing else. If the oven ends up a molten pile of metal ten minutes after the cake is done, if the leftover eggs are shattered and the leftover milk spilled, that’s fine. Baking that cake is my terminal goal. In the process of baking the cake, I check my fridge and cupboard for ingredients.
Minimal Motivation of Natural Latents — LessWrong

Oct 14, 2024 | lesswrong.com | David Lorell

Suppose two Bayesian agents are presented with the same spreadsheet - IID samples of data in each row, a feature in each column. Each agent develops a generative model of the data distribution. We'll assume the two converge to the same predictive distribution, but may have different generative models containing different latent variables.
Values Are Real Like Harry Potter — LessWrong

Oct 9, 2024 | lesswrong.com | David Lorell

Imagine a TV showing a video of a bizarre, unfamiliar object - let’s call it a squirgle. The video was computer generated by a one-time piece of code, so there's no "real squirgle" somewhere else in the world which the video is showing. Nonetheless, there's still some substantive sense in which the squirgle on screen is "a thing" - even though I can only ever see it through the screen, I can still:Notice that the same squirgle is shown at one time and another time.
We Don't Know Our Own Values, but Reward Bridges The Is-Ought Gap — LessWrong

Sep 19, 2024 | lesswrong.com | David Lorell

Background: “Learning” vs “Learning About”Adaptive systems, reinforcement “learners”, etc, “learn” in the sense that their behavior adapts to their environment. Bayesian reasoners, human scientists, etc, “learn” in the sense that they have some symbolic representation of the environment, and they update those symbols over time to (hopefully) better match the environment (i.e. make the map better match the territory). These two kinds of “learning” are not synonymous.
Interoperable High Level Structures: Early Thoughts on Adjectives — LessWrong

Aug 22, 2024 | lesswrong.com | David Lorell

Meta: This post is a relatively rough dump of some recent research thoughts; it’s not one of our more polished posts, in terms of either clarity or rigor. You’ve been warned. The Interoperable Semantics post and the Solomonoff Inductor Walks Into A Bar post each tackled the question of how different agents in the same world can coordinate on an ontology, so that language can work at all given only a handful of example usages of each word (similar to e.g. children learning new words).
A Robust Natural Latent Over A Mixed Distribution Is Natural Over The Distributions Which Were Mixed — LessWrong

Aug 22, 2024 | lesswrong.com | David Lorell

This post walks through the math for a theorem. It’s intended to be a reference post, which we’ll link back to as-needed from future posts. The question which first motivated this theorem for us was: “Redness of a marker seems like maybe a natural latent over a bunch of parts of the marker, and redness of a car seems like maybe a natural latent over a bunch of parts of the car, but what makes redness of the marker ‘the same as’ redness of the car?
Some Unorthodox Ways To Achieve High GDP Growth — LessWrong

Aug 8, 2024 | lesswrong.com | David Lorell

GDP growth, as traditionally calculated, is a weird metric. People interpret it as measuring “economic growth”, but… well, think about electronics. Electronics which would have cost millions of dollars (or more) in 1984 are now commonplace, everyone carries them around in their pockets.
A Simple Toy Coherence Theorem — LessWrong

Aug 2, 2024 | lesswrong.com | David Lorell

This post presents a simple toy coherence theorem, and then uses it to address various common confusions about coherence arguments. Deterministic MDP. That means at each time t there's a state S[t], the agent/policy takes an action A[t] (which can depend on both time t and current state S[t]), and then the next state S[t+1] is fully determined by S[t] and A[t]. The current state and current action are sufficient to tell us the next state.
(Approximately) Deterministic Natural Latents — LessWrong

Jul 19, 2024 | lesswrong.com | David Lorell

Background: Natural Latents: The Math, Natural Latents: The Concepts, Why Care About Natural Latents?, . This post does not assume that you’ve read all of those, or even any of them. Suppose I roll a biased die 1000 times, and then roll the same biased die another 1000 times. Then... Mediation: The first 1000 rolls are approximately independent of the second 1000 given the bias (to reasonable precision).
3C's: A Recipe For Mathing Concepts — LessWrong

Jul 2, 2024 | lesswrong.com | David Lorell

Opening Example: TeleologyWhen people say “the heart’s purpose is to pump blood” or “a pencil’s function is to write”, what does that mean physically? What are “purpose” or “function”, not merely in intuitive terms, but in terms of math and physics? That’s the core question of what philosophers call teleology - the study of “telos”, i.e. purpose or function or goal.