Category: AI Stack
-
RAG: How to Stop Your AI Making Things Up (GenAI Series, Part 13)
Retrieval-augmented generation lets a model answer from your own documents by fetching the relevant passages at question time. How RAG works, and why it beats fine-tuning for facts.
-
Prompt Engineering That Actually Works (GenAI Series, Part 12)
Prompt engineering is not secret incantations, it is clear communication. The four moves that do most of the work, system vs user prompts, and the anti-patterns that waste tokens.
-
Why AI Models Make Things Up (and What Temperature Does) (GenAI Series, Part 11)
AI models generate by sampling likely words from a probability distribution. Why that produces confident hallucinations, what the temperature setting really does, and how to reduce it.
-
The Context Window, and Why Models Forget (GenAI Series, Part 10)
The context window is everything an AI can see at once. Why models have no memory between turns, why longer prompts cost more, and why details get lost in the middle.
-
Training vs Inference: Why Using AI Is the Real Cost (GenAI Series, Part 9)
Training builds a model once in three stages; inference runs it on every request, forever. Why the recurring inference bill, not the headline training cost, decides AI economics.
-
Attention, the Idea That Made Modern AI Work (GenAI Series, Part 8)
How attention lets every word in a sentence weigh every other word, why it replaced slow left-to-right models, and why running in parallel is what let AI scale.
-
How Neural Networks Learn, Without the Math (GenAI Series, Part 6)
Neurons, layers, and weights in plain English. How a neural network learns by guessing, measuring its error, and nudging its dials, repeated across millions of examples.
-
What Generative AI Can and Cannot Do (GenAI Series, Part 5)
An honest look at generative AI: what it is genuinely good at, where it quietly fails, and why hallucination comes from the same machinery that writes its best answers.
-
What a Model Really Is (GenAI Series, Part 4)
A model is not a database of answers. It is one large function that predicts the next token, built from billions of parameters. What model sizes and open vs closed weights really mean.
-
How We Got from If-Statements to ChatGPT (GenAI Series, Part 3)
AI did not appear overnight. The road to ChatGPT runs through four eras, hand-written rules, machine learning, deep learning, and the 2017 transformer, explained in plain English.
-
The GenAI Words Everyone Uses, and What They Actually Mean (GenAI Series, Part 2)
Model, tokens, parameters, inference, embeddings, hallucination: the words everyone uses about generative AI, sorted into build time and use time and explained in plain English.
Architect’s Toolkit
PJ’s Tools
VMware Cloud Foundation
- VCF Documentation
- VCF 9 Planning & Preparation Workbook
- VCF Bill of Materials (BoM)
- VMware Compatibility Guide
- VMware Interoperability Matrix
- VMware Configuration Maximums
- VMware Ports & Protocols
- VMware Hands-on Labs
- RVTools Download
Nutanix
AI & Cloud-Native Platform
- NVIDIA Build (Model Catalog)
- NVIDIA AI Enterprise Reference Architecture
- NVIDIA NIM Performance Benchmarking
- NVIDIA NGC Catalog
- NeMo Microservices Helm Chart
- Helm Charts Repository
- Hugging Face Models
Architecture & Design
About the Author
Dr Pranay Jha
Dr. Pranay Jha is a Cloud and AI Consultant with 18+ years of experience in hybrid cloud, virtualization, and enterprise infrastructure transformation. He specializes in VMware technologies, multi-cloud strategy, and Generative AI solutions. He holds a PhD in Computer Applications with research focused on Cloud and AI, has published multiple research papers, and has been a VMware vExpert since 2016 and a VMUG Community Leader.
You May Have Missed
