Tag archive
A post framed fine-tuning as a 2026 interview trap. Here is the AWS version: the ladder before you touch weights, the four job types and three serving paths Bedrock forks 'fine-tune' into, and what each one costs, priced today.
Last year I wrote an article that used an AI system to research and predict the probability of...
AI image generation has moved from producing blurry synthetic faces to generating photorealistic...
For the past few days, I have been using Cursor to refine a personal project. It has been a...
What Are Neural Networks? A neural network is a way to model data by stacking layers of...
Previously, on Day 15: Explained why visualizing word embeddings is useful, introduced the challenges...
When developers start building RAG, Agent, or MCP applications, a lot of time still goes into the...
A step-by-step guide to pairing spec-driven development with stacked pull requests — from specify...
Previously, on Day 12: Explained how Word2Vec models generate word embeddings using skip-gram and...
What Are Word Embeddings? Words like "cat," "run," or "happiness" are just symbols to a...
Most teams building Retrieval-Augmented Generation (RAG) systems invest their engineering effort in two places: the LLM and the retrieval layer. They tune prompts, experiment with embedding models, compare vector databases, and benchmark retrieval precision. When the system underperforms in production, they go back to those same two layers and tune again.
A six-hour workshop plan that takes students from zero to a deployed retrieval-augmented app: prerequisites, four build blocks, the evaluation exercis