Adding a column to a pandas DataFrame comes up in almost every data cleaning or feature engineering task I’ve worked on, and pandas gives you more than one way to do it because each method fits a different situation. Some…
Say you’ve got a sales CSV with a city column and a hundred thousand rows, and someone asks for the total per city. Looping over the DataFrame row by row would work, but it’s slow and easy to get wrong.…
Artificial intelligence (AI) and machine learning (ML) interviews test more than definitions. These 100 multiple-choice questions cover model training, evaluation, data preparation, neural networks, natural language processing, and reinforcement learning, with each answer hidden until you choose. Test the AI…
Retrieval-augmented generation (RAG) gives an AI coding assistant selected evidence from your repository before it answers. The useful version of RAG for codebases is a retrieval pipeline with access controls, ranking, context limits, and tests for whether the chosen evidence…
Perplexity and ChatGPT can both search the web, analyze files, and answer follow-up questions, but they make different work easier. I checked their plan pages, developer pricing, and product documentation on July 16, 2026, and the useful choice comes down…
GPT-4o mini remains available through the OpenAI application programming interface (API), but it is now a legacy choice rather than OpenAI’s recommended small model for a new build. OpenAI’s current model catalog recommends GPT-5.6 Sol for complex work, GPT-5.6 Terra…
A multimodal AI developer workflow gives a model the visual evidence that text logs leave out, but a screenshot alone rarely explains a bug. My image-preparation test used Node.js 26.5.0 and Sharp 0.35.3 so the workflow starts with a reproducible…
AI does not create an offer, find a buyer, or guarantee useful work. I checked five current guides on how to make money using AI in July 2026, and the useful dividing line was consistent across them: you earn from…
Low-Rank Adaptation (LoRA) lets you adapt a code large language model (LLM) without updating every weight in the base model, so the useful question is whether your task needs learned behavior, retrieved context, or both. What LoRA changes during fine-tuning…
LLM latency optimization starts with separating model time from retrieval, network, and application work. The Node.js example below ran independent preparation steps in 121 ms on the parallel path and 211 ms on the sequential path, which makes orchestration the…
