Towards Data Science

2 min read Original article ↗

  • Tokenmaxxing is out. Real patterns for reducing costs without sacrificing AI effectiveness

  • But don’t let the model check itself

Latest

  • t0-alpha is a decoder-style patch transformer for probabilistic time-series forecasting. Raw series are split into…

  • Enterprise Document Intelligence [Vol.1 #6ter] – Six positions on the question-parsing brick that contradict the…

  • The next leakage problem is not only temporal. It is spatial, structural, and coverage-related. AI-generated…

  • Every hand-off in your multi-agent pipeline is an expensive tokenization round-trip. Discover how Inductive Latent…

  • How Pandas chunking, Dask, and Polars help process millions of records when adding more compute…

  • Build and deploy an agent on AWS with Strands and AgentCore

  • Enterprise Document Intelligence [Vol.1 #7bis] – Tobi Lütke and Andrej Karpathy named the practice in…

  • In the age of AI, standing out here means a lot more than ever. Here…

  • Build a more powerful coding agent setup with a model ensemble

Editor’s Picks

  • A hands-on walkthrough of a hybrid local-cloud workflow using Gemma 4 and GPT-5.4, with reasoning…

  • The tools I use for analytics and reporting have changed more than I expected, yet…

  • An image of scissors cutting off the tail of a bell curve

    Behind a customer’s API, a high-quality answer isn’t enough. It has to be usable, which…

  • Why memorizing for the exam doesn’t mean you understand the subject

  • Enterprise Document Intelligence [Vol.1 #M1] – The thesis behind every architectural choice in this series

  • A reproducible benchmark on latency, cost, and reproducibility, and where agents actually earn their keep.

  • A practical data engineering onboarding workflow for environment setup, automated testing, and AI-assisted development.

  • A practical walkthrough using text-to-SQL as the example

  • Photo by National Institute of Allergy and Infectious Diseases on Unsplash

    How Gemini solved my Pandas problem in seconds, and why data science fundamentals still matter…

The Variable Newsletter

  • Authors can now benefit from updated earning tiers and a higher article cap

  • Sorting through the good, bad, and ambiguous aspects of vibe coding

Deep Dives

  • An end-to-end classical NLP experiment on Kaggle’s Spooky Author Identification task: from Vowpal Wabbit and…

  • Small prompt changes can silently break critical behavior in production. This article introduces a practical…

  • A team cut their AI inference bill by more than half. Three months later, customer…

  • I benchmarked raw chat history, vector-only RAG, and a context graph on the same multi-agent…

  • Whether you should stick to a classic Ordinary Least Squares regression, introduce interaction terms, or…

  • Beat the 8GB VRAM limit. Learn how to run three different LLMs on a single…