LoRA transformed how we fine-tune massive AI models like GPT-3. By adding tiny low-rank matrices instead of retraining billions of parameters, it made adaptation faster, cheaper, and accessible to everyone. This article explores the origins, mechanics, and lasting impact of the “small trick” that tamed the giants of artificial intelligence.

This article explores how to optimize large language model inference at scale, detailing techniques such as quantization, pruning, distillation, attention and cache optimization, speculative decoding, and dynamic batching. It explains the architectural bottlenecks, trade-offs, and engineering practices that enable faster, cheaper, and more efficient deployment of LLMs in real-world systems.

This article explores the Model Context Protocol (MCP), a standardized interface that enables AI agents to dynamically discover and invoke external tools. It covers MCP’s architecture, real-world applications, and security risks across its lifecycle. By decoupling tool logic from AI behavior, MCP empowers agents to perform complex workflows with greater flexibility, setting a foundation for the next generation of tool-integrated AI systems.

Active Inheritance curates synthetic data to control LLM behavior, preventing AI model collapse and improving diversity, safety, and bias.

Effectively handling missing data with univariate and multivariate imputation ensures reliable analysis and accurate machine learning models

Dive into the world of Retrieval-Augmented Generation! See how RAG transforms AI responses by blending retrieval with generation.

In this article I share a experimentation framework I work with in my daily job. It uses MLFlow and Hydra to facilitate hypothesis testing.

In this article we'll explore Hydra, a tool for managing multiple configuration parameters and file when doing machine learning for research

In this article, we will see how we can leverage FastAPI and Docker to build a wrapper REST API around ML models and deploy it.

In this article I'll share with you some advice based on personal experience when doing practical machine learning for the industry.