Hey, I am Robert Kralisch, an independent conceptual/theoretical Alignment Researcher. I have a background in Cognitive Science and I am interested in collaborating on an end-to-end strategy for AGI alignment.

I am one of the organizers for the AI Safety Camp 2025, working as a research coordinator by evaluating and supporting research projects that fit under the umbrella of “conceptually sound approaches to AI Alignment”.

The three main branches that I aim to contribute to are conceptual clarity (what should we mean by agency, intelligence, embodiment, etc), the exploration of more inherently interpretable cognitive architectures, and Simulator theory.

One of my concrete goals is to figure out how to design a cognitively powerful agent such that it does not become a Superoptimiser in the limit.

Yeah, I am not super familiar with PCA, but my understanding is that while both PCA and referential containment can be used to extract lower-dimensional or more compact representations, they operate on different types of data structures (feature vectors vs. graphs/hypergraphs) and have different objectives (capturing maximum variance vs. identifying self-contained conceptual chunks). Referential containment is more focused on finding semantically meaningful and contextually relevant substructures within a causal or relational knowledge representation. It also tries to address the opposite direction, basically how to break existing concepts apart when zooming into the representations, and I am not sure if something like that is done with PCA.

I had Claude 3 read this post and compare the two. Here it is, if you are interested (keep in mind that Claude tends to be very friendly and encouraging, so it might be valuing referential containment too highly):

Similarities:

Both aim to identify patterns and structure in high-dimensional data.

Both can be used to reduce the dimensionality of data by finding lower-dimensional representations.

Both rely on analyzing statistical dependencies or correlations between variables/features.

Differences:

PCA is a linear dimensionality reduction technique that projects data onto a lower-dimensional subspace spanned by the principal components (eigenvectors of the covariance matrix). Referential containment is not inherently a dimensionality reduction technique but rather a way to identify self-contained or tightly coupled substructures within a causal graph or hypergraph representation.

PCA operates on numerical feature vectors, while referential containment deals with graph/hypergraph structures representing conceptual relationships and causal dependencies.

PCA finds orthogonal linear combinations of features that capture maximum variance. Referential containment aims to identify subgraphs with strong internal connections and minimal external connections, which may not necessarily correspond to maximum variance directions.

PCA is an unsupervised technique that does not consider semantics or labeled data. Referential containment, as proposed in the context of the PSCA architecture, can potentially leverage semantic information and learned representations to guide the identification of meaningful conceptual chunks.

PCA produces a fixed set of principal components for a given dataset. Referential containment, as described, is more flexible and can adapt the level of granularity or resolution based on context, objectives, and resource constraints.