Artificial Intelligence

Fırat

Organizing data.blog content via NLP and LLM

The redesign of data.blog aimed to enhance content discoverability by making category and tag pages more prominent. We re-imagined the blog taxonomy developed over ten years. Using NLP and LLM techniques, we analyzed categories and tags to consolidate and improve on clarity and relevance.
Daniel Danilov

Hack Project: Creating a tool to translate customer feedback into product insights

Explore Automattic’s hack project in our latest post, where we developed a tool for analyzing Tumblr user feedback. Learn about our challenges with AI, creating insightful dashboards, and the impactful outcomes. Our collaborative effort not only enhanced product development but also earned us the top spot in our Hack Week Awards!
jie

Hack Project: Tackling FOMO on the P2 Land

Automattic, a fully distributed company, utilizes a unique internal blogging network known as P2 for team communication. Due to the vast volume of posts and comments, employees often struggle with the fear of missing out (FOMO) on important content. To address this, a team of data and machine learning experts initiated a hack project that…
David Newman

Quest for Efficient AI: An Evaluation of the Vector Database Landscape

Earlier this year, due to soaring interest and multiple product initiatives, we went on a quest to evaluate and deploy an internally hosted vector database. We’re in the midst of the AI revolution, and many new AI‑inspired product initiatives rely on vector embeddings. Embeddings are generated by AI models, and take the form of high dimensional…
charlescearl

Gender and Racial Bias in Cloud NLP Sentiment APIs

Do natural language processing tools from Amazon and Google contain racial and gender bias? Charles Earl investigates.