data-science |

How I Made a Voice-Activated AI Assistant That Actually Controls My Smart Home

How Cracking Python’s Interpreter Internals Changed the Way I See Code

From Prompt to Prototype I Built an AI That Designs Full Apps Using Figma + Streamlit

Docling: The document alchemist

You’re Wasting Time If You’re Not Using These Python One-Liners Yet

Building Long-Term Memory in Agentic AI

Why Your RAG System Fails Complex Questions? (And How Structure Fixes Everything)

Why My Spotify Thinks I Love K-Pop: A Lesson in K-Means Clustering

5 Python Design Decisions That Separate Senior Devs From Coders

How Three ML Models Transform Product Analytics

How Three ML Models Transform Product Analytics

How to Tell If a Policy Actually Worked: A Step-by-Step Causal Inference Example in Python

From Data Drift to Compliance: Building Robust Machine Learning (ML) Lineage in ML Applications

Important LLM Papers for the Week From 22/09 To 28/09

Building a Multi-Layered Agentic Guardrail Pipeline to Reduce Hallucinations and Mitigate Risk

This Python Tool Cleans My Desktop Every Night And It’s Smarter Than Me

Comparing the Performance of LangChain-Based Systems in Python and Go

The Hidden Lessons I Learned From Writing My Own Python Package Manager

Integrating Data CI/CD Pipeline to Machine Learning (ML) Applications

5 Common Python Mistakes That Are Secretly Slowing Down Your Code

4 Best Python Linters and Formatters to Keep Your Code Clean

The Cornerstone Secret: What Elite Data Teams Know About Snowflake Tags and Zero-Friction…

A Guide to Google Meridian’s Key Priors

Matplotlib Quick Reference Cheat Sheet

Exploring Machine Learning Techniques for LTV/CLV Prediction

The Hidden Economics of Your Vacation: Why a 2-Hour Transfer in the Alps Can Cost More Than a Flight

The Python Library That Made Me Delete 3,000 Lines of Code With Zero Regrets

Rectified Flow: The Easiest Path to Learn Image Generation

Time Series Forecasting with XGBoost

A Developer’s Guide to DolphinScheduler 3.1.9 Worker Startup Process

Dissecting the Master Server: How DolphinScheduler Powers Workflow Scheduling

Developers Gain Direct Insight Into Data Flows With CocoIndex Update

How to Create a Fuzzy Matching App with DuckDB and Taipy

Building 17 Agentic AI Patterns and Their Role in Large-Scale AI Systems

Writing Your Own Python Package Manager From Scratch

Knowledge Graphs Gain Traction as AI Pushes Beyond Traditional Data Models

Risks of Synthetic Data: A Technical Overview

How I Implemented Batch Gradient Descent, Softmax Classification, and a Mini CNN on MNIST Without…

AgentFounder: First Open-Source AI Agent to Rival OpenAI’s Deep Research Capabilities

AI Agent, You’re Better Off Alone. Debate Is a Trap

The Most Valuable AI in Your Company Is the One Your CEO Doesn’t Know Exists

Data-Driven Decisions at Scale: A/B Testing Best Practices for Engineering & Data Science Teams

Building an Advanced Agentic RAG Pipeline that Mimics a Human Thought Process

OpenAI Thinks Overconfidence is LLM’s Hallucination Cause

How to choose the right embedding model for your RAG application?

Debugging Data Pipelines Shouldn’t Be a Guessing Game

Debugging Data Pipelines Shouldn’t Be a Guessing Game

(I) Principles of Data Model Architecture: Four Layers and Seven Stages

Stop Waiting: Make XGBoost 46x Faster With One Parameter Change

The #1 Habit That Silently Destroys Self-Taught Devs’ Careers

Detecting Potential Outliers in Text Data Through a Semantic AI Pipeline

Detecting Potential Outliers in Text Data Through a Semantic AI Pipeline

Python Superpowers: From Small Utilities to Full Automation Systems

From 1 Million to 1 Billion Rows: The New Era of Scalable Data Science

From 1 Million to 1 Billion Rows: The New Era of Scalable Data Science

From 1 Million to 1 Billion Rows: The New Era of Scalable Data Science

The Future of Data Science: Trends, Tools, and Skills for 2025

Creating a Complete Evaluation Lifecycle to Build High-Confidence AI Agents

Master the Power of Logit Models in R (With Real-World Churn Data)

The Limits of Embeddings: Why One Vector Can’t Fit All Queries