Data Science Tutorials

Run a massive MoE model locally by combining GPU VRAM, system RAM, SGLang, and KTransformers for heterogeneous CPU-GPU inference.

A hands-on Claude Cowork plugins tutorial: install Anthropic's Data plugin, connect a warehouse and run a slash command, customize the plugin for your own tables, and build a complete weekly-report plugin from scratch with every file shown.

Learn what mean reversion is, how to identify mean-reverting behavior in time-series data, and how the concept is used in statistics, trading, and quantitative finance.

Learn what Open Interpreter is, how its open-source coding agent works, how to install and use it, and how its model and agent harness support compares with other AI coding tools.

Learn how to build a real-time support-call transcriber with the Grok Voice Transcribe 2.0 API in Python, then add diarization, Smart Turn, and 8 kHz phone audio.

Learn how to use the Claude Sonnet 5.5 API in Python. Build a reconciliation agent that earns write access mid-conversation, then test whether higher effort changes the result.

Build an AI incident response agent with GPT-6.1 Sol, the OpenAI Agents API, and a hosted sandbox to investigate incidents, run checks, and generate structured reports.

An overview of OpenHands, the open-source AI coding agent, covering its architecture, a local setup with Ollama, a hands-on bug fix, security and limitations, and how it compares to Claude Code, Cursor, and GitHub Copilot.

A likelihood ratio compares how well two hypotheses or models explain the same data, and this article covers the formula, a worked coin-flip example, the likelihood ratio test for nested regression models in Python and R, and diagnostic likelihood ratios.

A hands-on guide to GraphQL Code Generator that covers setup and configuration, generated TypeScript types and typed document nodes, integration with Apollo, urql, and graphql-request, and automation with watch mode and CI.

Stepwise regression automates predictor selection with forward, backward, and bidirectional search, but its simplicity comes with trade-offs in stability and overfitting.

Learn how to build a secure AI financial analyst with an OpenAI-hosted sandbox, from uploading financial data and running agent-driven analysis to generating and downloading reports, charts, and supporting data files.