LLMs on The Probability Engine

One Register, Slowly Diffusing: A Topic-Model, Vector-Database and Graph-Theoretic Reading of the Beatles' Lyrical Evolution (1965–1969)

Tue, 16 Jun 2026 00:00:00 +0000

Abstract

This study traces the lyrical evolution of the Beatles across four albums — Rubber Soul (1965), Revolver (1966), Sgt. Pepper’s Lonely Hearts Club Band (1967) and Abbey Road (1969) — using a pipeline of LLM-driven topic modeling (BERTopic), a vector database (OpenAI text-embedding-3-large indexed in ChromaDB), embedding geometry, and graph theory. The study puts a falsifiable question to the canonical critical narrative — that the Beatles moved through four discrete stylistic eras — by testing whether the albums occupy separable territories in lyrical-semantic space.

When Lyrics Change Language: An Embedding Study of Aquamosh

Wed, 20 May 2026 00:00:00 +0000

An exploratory comparison of embedding thresholds and a model judge in multilingual lyrics, with explicit limits on what their disagreement establishes.

Attention Windows: What Embedding Similarity Can Tell Us About Beatles and Pink Floyd

Tue, 10 Feb 2026 00:00:00 +0000

An exploratory reading of lyrical similarity, with a correction on numerical provenance and the limits of interpreting a metric as attention.

Literary Mapping of Christmas Novels: A Vector Narrative Arc Approach

Wed, 07 Jan 2026 00:00:00 +0000

Post Objective

Data cleaning and preliminary analysis process
Understanding the emotional charge or plot development of texts through semantic archaeology based on PCAs
Understanding the connections and most representative ideas within the document set

Intention

Understanding a story’s behavior at the level of its variance is a challenge addressed by attentional engineering. Therefore, using lesser-known methods such as the vector narrative arc combined with a literary map constitutes an interesting route to address increasingly common problems.