Never miss a new edition of variablea weekly newsletter featuring a top-notch selection of editor’s picks, details, community news, and more.
With just a few weeks left until the end of the year, authors and readers alike show no signs of slowing down.
We’re delighted to have published some of the most powerful articles of the year last month. Practical guides to LLM workflows and career growth resources, Python-focused tutorials, details on recently released tools, and other outstanding topics. To catch up (or revisit) November’s most read articles, keep reading.
RAG and SQL RAG graphs
Which database paradigm provides more accurate and insightful results? Reinhard Sellmair set out to evaluate the performance of the two types of RAG systems by comparing them against each other using the same dataset and questions.
Time series analysis using LLM
In the second part of Sara Nobrega’s popular series, learn about the prompts needed for advanced model development (think ARIMA and LSTM).
How to build a employable machine learning project
Not all ML portfolios are created equal. Egor Howell shares proven insights into what works and what doesn’t.
More November highlights
Don’t miss last month’s other top articles tackling NumPy, Multimodal RAG, marimo notebooks, and many other topics (both evergreen and cutting edge).
NumPy for absolute beginners: A project-based approach to data analysis by Ibrahim Salami
Understanding Convolutional Neural Networks (CNN) with Excel by Angela Shi
Run Python in C up to 150x faster, by Thomas Reid
How to build an over-engineered search system (by Ida Silfverskiöld)
Building multimodal RAGs that respond to text, images, and tables from sources (Partha Sarkar)
Why I Switched to Marimonaut by Parul Pandey
The next “big” language model may not be big after all, by Moulik Gupta
In case you missed it: Latest Author Q&A
We love sharing our authors’ expertise, career insights, and views on recent developments in the world of data science and AI. The latest author spotlights include:
- “Systems thinking helps bring the big picture to the fore.”
Shuai Guo discusses deep research agents, analytical AI and LLM-based agents, and systems thinking.
- “The success of an AI product depends on how intuitive its functionality is for users.”
Janna Lipenkova talks about AI strategy, AI products, and how domain knowledge can change the shape of your entire AI solution.
Introducing new authors
We hope you’ll take the time to explore the great work from our newest group of TDS contributors.
- Stanford computer science professor and entrepreneur Jure Leskovec explains why an LLM is not a one-size-fits-all solution for companies.
- Sherin Sunny, a senior engineer at Walmart, walked us through the creation of a computer vision project aimed at detecting leaves.
- Manuel Franco de la Peña introduced us to ShaTS, a new Shapley-based explainability method specifically designed for time series models. He co-created it.
We love publishing articles by new authors, so if you’ve recently written an interesting project walkthrough, tutorial, or theoretical reflection on one of our core topics, why not share it with us?
Authors, we’d love to hear your feedback!
Are you an existing TDS author? Please take our 5-minute survey to help us improve the publishing process for all contributors.
