x

LESSWRONG
LW

Daniel C — LessWrong

Daniel C

Top postsTop post

Daniel C

Message

Master's student in applied mathematics, funded by Center on Long-Term Risk to investigate the cheating problem in safe pareto-improvements. Former dovetail fellow with @Alex_Altair.

282

Ω

11

9

64

4y

Daniel C

Master's student in applied mathematics, funded by Center on Long-Term Risk to investigate the cheating problem in safe pareto-improvements. Former dovetail fellow with @Alex_Altair.

Top postsTop post

A summary of Condensation and its relation to Natural Latents

Short summary of Condensation Condensation is a theory of concepts by Sam Eisenstat. The paper can be read here. Abram wrote a review on Lesswrong, and a followup. The paper is very much worth reading, and can be skimmed to just understand the motivation if you’re time constrained. What is a concept? One rough pointer is "the little packets of information that are the meaning of a word or phrase". Another is the clusters found in the cluster structure of thingspace. Maybe we could think of them as little chunks of a generative model that compose together to make complete model of a complex world. It often seems to be the case that this kind of chunking is arbitrary, in the sense that there isn’t one way to chunk up a generative model. It just depends on the hypothesis class, prior and implementation details. But some concepts seem to be more objective than this, in that we would expect different agents with different implementation details to use the same concept. One question that Condensation answers is “under what conditions can concepts be more objective?”. The theory provides some assumptions and metrics that can be used to select among latent variable models (LVM)s to find ones that use more “objective”[1] concepts. If we make these assumptions on two agents’ latent variable models, it tells us when they will (and won’t) use the same latent variables. This is very similar to the motivation for John Wentworth’s Natural Latents, as is noted in the Condensation paper, but so far no one has worked through the similarities between the two on a mathematical level. So the main goal of this post is to show some simple relationships between these two theories. A secondary goal is to work through an intuitive example of a non-trivial condensation, and this is where we’ll start. How does condensation work? There are multiple ways we could organize a generative model. We’ll call a “way of organizing a generative model” an LVM. Condensation is a method for sorting amo

Towards building blocks of ontologies

What program structures enable efficient induction?

My decomposition of the alignment problem

A summary of Condensation and its relation to Natural Latents

Short summary of Condensation Condensation is a theory of concepts by Sam Eisenstat. The paper can be read here. Abram wrote a review on Lesswrong, and a followup. The paper is very much worth reading, and can be skimmed to just understand the motivation if you’re time constrained. What is...

Daniel C's Shortform

Dec 22, 2025•3

Abstraction as a generalization of algorithmic Markov condition

A core subproblem in ontology identification is to understand why and how humans and agents break down their world models into distinct, structured concepts like tables, chairs and strawberries. This is important because we want AIs to optimize the real world things we care, but the things we care about...

Dec 14, 2025•8

Algorithmic thermodynamics and three types of optimization

Context:I (Daniel C) have been working with Aram Ebtekar on various directions in his work on algorithmic thermodynamics and the causal arrow of time. This post explores some implications of algorithmic thermodynamics on the concept of optimization. All mistakes are my (Daniel's) own. A typical picture of optimization is when...

Dec 8, 2025•11

Sleeping Experts in the (reflective) Solomonoff Prior

Epistemic status: This first collaboration between Daniel Chiang (who is interested in the algorithmic information theory of incrementally constructed representations) and myself (Cole Wyeth) contains some fairly simple but elegant results that help illustrate differences between ordinary and reflective Oracle Solomonoff Induction (rOSI). Update 02/15/26: The connection between rOSI and...

Aug 31, 2025•16

Towards building blocks of ontologies

This dialogue is part of the agent foundations fellowship with Alex Altair, funded by the LTFF. Thank you Dalcy, Alex Altair and Alfred Harwood for feedback and comments. Context: I (Daniel) am working on a project about ontology identification. I've found conversations to be a good way to discover inferential...

Feb 8, 2025•29

Can subjunctive dependence emerge from a simplicity prior?

Suppose that an embedded agent models its environment using an approximate simplicity prior, would it acquire a physicalist agent ontology or an algorithmic/logical agent ontology? One argument for the logical agent ontology is that it allows the agent to compress different parts of its observations that are subjunctively dependent: If...

Sep 16, 2024•11

Load More (7/10)