Black Tusk Data
Finding the signal in unstructured data
Home
Articles
Book
AI-Derived AI-Derived Consumer Insights: Weaknesses in Herbal Essences' Product Lineup
Consumer insights teams at beauty brands already have access to huge amounts of unstructured feedback. Commonly, this feedback is run through sentiment analysis in order to gauge how favourably c...
Codebase Modelling
Software code presents a really interesting problem for knowledge extraction. Code is unique because it is highly structured, but expressive enough that it makes sense to parse as natural lan...
Copilot and productivity
"One good dev with Github Copilot ships what entire teams did five years ago." - This is one example of some bold claims that have been made about Github Copilot. Discussions about A...
Late chunking and improved embeddings
The motivation for this discussion is to pull meaningful information out of an earnings call. Specifically, we'll look at the Zoom 2024 Q3 earnings call, which you can find a transcript of at...
Introduction to GraphRAG
In theory, the concept of At a high level, GraphRAG is really a combination of 3 distinct tasks: So what is a 'knowledge graph' exactly? Knowledge graphs are a way of modelin...
Articles
AI-Derived AI-Derived Consumer Insights: Weaknesses in Herbal Essences' Product Lineup
Codebase Modelling
Copilot and productivity
Late chunking and improved embeddings
Introduction to GraphRAG
Crash Course in Linear Algebra
Practical Guide to PCA