This study investigates the internal mechanisms of BERT, a transformer-based large language model, with a focus on its ability to cluster narrative content and authorial style across its layers. Using a dataset of narratives developed via GPT-4, featuring diverse semantic content and stylistic variations, we analyze BERT's layerwise activations to uncover patterns of localized neural processing. Through dimensionality reduction techniques such as Principal Component Analysis (PCA) and Multidimensional Scaling (MDS), we reveal that BERT exhibits strong clustering based on narrative content in its later layers, with progressively compact and distinct clusters. While strong stylistic clustering might occur when narratives are rephrased into different text types (e.g., fables, sci-fi, kids' stories), minimal clustering is observed for authorial style specific to individual writers. These findings highlight BERT's prioritization of semantic content over stylistic features, offering insights into its representational capabilities and processing hierarchy. This study contributes to understanding how transformer models like BERT encode linguistic information, paving the way for future interdisciplinary research in artificial intelligence and cognitive neuroscience.

The human brain possesses the extraordinary capability to contextualize the information it receives from our environment. The entorhinal-hippocampal plays a critical role in this function, as it is deeply engaged in memory processing and constructing cognitive maps using place and grid cells. Comprehending and leveraging this ability could significantly augment the field of artificial intelligence. The multi-scale successor representation serves as a good model for the functionality of place and grid cells and has already shown promise in this role. Here, we introduce a model that employs successor representations and neural networks, along with word embedding vectors, to construct a cognitive map of three separate concepts. The network adeptly learns two different scaled maps and situates new information in proximity to related pre-existing representations. The dispersion of information across the cognitive map varies according to its scale - either being heavily concentrated, resulting in the formation of the three concepts, or spread evenly throughout the map. We suggest that our model could potentially improve current AI models by providing multi-modal context information to any input, based on a similarity metric for the input and pre-existing knowledge representations.

PFLUGERVILLE, Texas – As a SWAT team closed in, the suspected bomber whose deadly explosives terrorized Austin for three weeks used one of his devices to blow himself up. But police warned that he could have planted more bombs before his death, and they cautioned the city to stay on guard. Mark Anthony Conditt, an unemployed college dropout, had been tracked down using store surveillance video, cellphone signals and witness accounts of a strange-looking customer making purchases in a disguise that included a blonde wig and gloves. His motive remained a mystery. Police finally found the 23-year-old early Wednesday at a hotel in a suburb north of Austin known as the scene for filming portions of "Friday Night Lights."

Veritone, a company which uses artificial intelligence (AI) to gain actionable insights from unstructured data like video and audio, announced last week that their system, Conductor, is operating at 82% accuracy, as opposed to the previous best of 75%. This success may herald a new dawn for Veritone, who announced their concerns over whether they may ever achieve or sustain profitability in May this year. Chad Steelberg, Veritone founder and CEO, has focused on investing in an AI platform and moved away from Veritone's media buying and placement business, traditionally seen as more lucrative. Developers told Access-AI that Veritone's improvements are due to Conductor, a technology which acts as a kind of managing editor, optimising the results of the 70 third-party engines that form the Veritone platform, in a seemingly unique instance of machine learning (ML) being applied to machine learning. The screenshot below shows an example of Veritone collecting instances of media figure Emily Chang.

Schulze's rule and ranked pairs are two Condorcet methods that both satisfy many natural axiomatic properties. Schulze's rule is used in the elections of many organizations, including the Wikimedia Foundation, the Pirate Party of Sweden and Germany, the Debian project, and the Gento Project. Both rules are immune to control by cloning alternatives, but little is otherwise known about their strategic robustness, including resistance to manipulation by one or more voters, control by adding or deleting alternatives, adding or deleting votes, and bribery. Considering computational barriers, we show that these types of strategic behavior are NP-hard for ranked pairs (both constructive, in making an alternative a winner, and destructive, in precluding an alternative from being a winner). Schulze's rule, in comparison, remains vulnerable at least to constructive manipulation by a single voter and destructive manipulation by a coalition. As the first such polynomial-time rule known to resist all such manipulations, and considering also the broad axiomatic support, ranked pairs seems worthwhile to consider for practical applications.