Search Tech Journey

Find topics, journeys and posts

Series · 8 parts

Applied LLMs — Origins to Production

A read-in-order path through large language models as they actually get used: the historical arc, the mechanics of attention, retrieval augmentation, prompting that holds up, and applied case studies. Start at the origins and walk forward.

  1. 1Where LLMs Came From, and What They Actually AreThe 80-year origin story, the five ideas that actually matter, and a verified watch-list to go deeper — no maths required.
  2. 2How Transformers actually attendBeyond the textbook diagrams — what a single attention head is really computing, how multi-head splits the world, and why scaling laws keep rewarding bigger context.
  3. 3RAG architecture basics and workingsRetrieval-Augmented Generation from first principles — embeddings, vector databases, chunking, retrieval, prompt construction, evaluation, and common failure modes — enough depth to build one yourself.
  4. 4Best LLM Prompt for understanding any concept in-depthUse this prompt for gathering information all at one place
  5. 5Automating audio generationFrom text , generate audio files and publishing them to webapp
  6. 6Reading on MEDICAL ERROR DETECTION AND CORRECTION IN CLINICAL NOTESThis blog explores a paper on detecting and correcting medical errors in clinical notes using Large Language Models (LLMs)
  7. 7Stanford CS229: Machine Learning CourseCS229 provides a broad introduction to statistical machine learning (at an intermediate / advanced level) and covers supervised learning (generative/discriminative learning, parametric/non-parametric learning, neural networks, support vector machines); unsupervised learning (clustering, dimensionality reduction, kernel methods); learning theory (bias/variance tradeoffs, practical ); and reinforcement learning among other topics
  8. 8Basics of Azure AI FoundryA self-sufficient guide to Azure AI Foundry — what it is, how the hub/project/deployment model works, how to ship a grounded agent end-to-end with SDK + Bicep, and the security/eval/cost levers you cannot skip.