Gajen Dissanayake·Aug 5My first LLM deploymentIn my career transition from DevOps to MLOps, soon after I passed the AWS exams for AI Practitioner and Machine Learning Engineer, I tried…
Shirley Singleton·May 20Temperature Is Not a Defense: Indirect Prompt Injection Across Four Open-Weight LLMsTL;DR
Raj·Dec 15, 2025Building a Text-to-SQL Model: What I Learned Spending $60 and Two WeeksI recently built a model that converts natural language into SQL queries. The goal wasn’t just to train a model — it was to understand…
Sebastian Buzdugan·Dec 3, 2025Mistral 3 and Mistral Large 3 Explained: The Complete Guide to the New Open-Weight AI ModelsThe open-source AI world moves fast, but every once in a while a release lands that resets expectations. The new Mistral 3 family…
Prasanta Kumar Mohanty·Oct 1, 2025Deploying Ollama with Docker Compose: A Simple Guide to Local LLMsSpin up your own AI assistant using Ollama and Docker Compose. This guide includes everything from container setup to accessing the web UI.
InTowards AIbyDevi·Sep 29, 2025Running Small Language Models (SLMs) on CPUs: A Practical GuideThe what, why, and how with a practical example, to solidify your learning!A response icon6A response icon6
Santhosh Dhaipule Chandrakanth·Jun 21, 2025Why Mistral 7B Is the Smartest Base Model for Local LLM Prototyping (Even on Low-RAM Machines)Real-world benchmarking and product rationale from an AI builder running full LLM stacks on a MacBook with 8GB RAM.
Raju kumar·Jun 3, 2025Day 27 of 30 Days of LLMs LLMs on the Edge: Tiny LLMs for Mobile and IoT Excite Developers —…Okay, so I have to confess something before we dive in…
Santhosh Dhaipule Chandrakanth·Jun 3, 2025How I Built a Local RAG Pipeline with Mistral & Benchmarked GPU Layer Speedups on a MacBook M1Fast, free, and API-free LLM retrieval — ideal for solo developers & edge deployments
Santhosh Dhaipule Chandrakanth·May 29, 2025🚀 Benchmarking ctransformers vs llama.cpp: Local LLM Inference on M1 MacBook with Zephyr & MistralHow fast can you run 7B parameter LLMs locally on your MacBook? Let’s benchmark two leading tools — ctransformers and llama.cpp — using…
