is a good way to test NLP models because it focuses not only on what a sentence says, but also on how it is written. Kaggle’s Spooky Author Identification competition is a compact version of this challenge: given a single sentence from gothic or horror fiction, the model has to predict whether it was written by Edgar Allan Poe (EAP), Mary Wollstonecraft Shelley …
# Introduction The average data scientist spends roughly 45% of their working time on data preparation and cleaning, not on modeling, not on insight generation, not on the work that requires genuine judgment. That estimate keeps appearing across industry surveys because it keeps being true. The tasks eating up that time — profiling columns, flagging …
5 Agentic Workflows to Automate Your Data Science Pipeline Read More »
cut their AI inference bill by more than half last quarter. Eight weeks of clean engineering work. It was the win the engineering team had been chasing all year. It was also the wrong optimization. Three months later, customer satisfaction was dropping, churn was ticking up, and the cost savings were structurally tied to the …
We Built a Routing Layer to Cut Our AI Costs. It Broke the Product. Read More »
# Fine-Tuning Language Models on Apple Silicon with MLX Fine-tuning a language model used to mean renting cloud GPUs and watching the meter run. If you own a Mac with an Apple Silicon chip, you can now adapt an open model to your own data locally, at zero cloud cost, using a framework built specifically …
Fine-tuning Language Models on Apple Silicon with MLX Read More »
Making computer use safe in 3.5 Flash To mitigate some of the prompt injection risks for agents operating in live environments, we use targeted adversarial training for computer use in Gemini 3.5 Flash. We’re also releasing two optional enterprise safeguard systems that enable enterprises to: Require explicit user confirmation for sensitive or irreversible actions. Automatically …
All code used in this article is available on GitHub. The business logic and modeling functions are located in the src/selection directory, specifically in the following file: src/modeling/score_computation.py The corresponding analysis and results are documented in: 09_score_computation.qmd The images, tables, and charts were generated with the help of the Codex coding assistant. , your credit score follows you …
How to Build a Credit Scoring Grid From a Logistic Regression Model Read More »
# Introduction Local coding models are finally getting serious. I have been a big fan of this new wave of local large language models (LLMs), especially the open models and community GGML Universal File (GGUF) releases that make them easier to run on consumer hardware. We are now at a point where some of these …
my series on Outlier Detection. In this article, we look at working with categorical data. Generally when performing outlier detection with tabular data, we start by converting the data so that it is either entirely categorical or entirely numeric. There are some exceptions, but for the most part this is necessary: most outlier detection algorithms …
# Introduction Focusing only on SELECT, WHERE, and GROUP BY is enough for basic aggregation, but many real analytical tasks require patterns that go beyond simple queries. Examples include detecting consecutive activity streaks, segmenting customers by spend tier, smoothing noisy time-series data, or tracing plan upgrade paths across rows. This article walks through 7 practical …
Practical SQL Tricks Every Data Scientist Should Know Read More »
Introduction , AI examples of data engineering revolve around one thing: fixing a pipeline. An engineer opens up Claude Code, pastes some logs, and a pull request is made. Semantics are fundamental here. Because when people say “self-healing” what they mean is “self-managing”. The key to success in AI is not defined by manual intervention …
7 Crucial Barriers Between Data Teams and Self-Healing Data Architecture Read More »
