Feed

This is a feed of links I've run across and found interesting or noteworthy. The images, content and opinions in them are owned by their respective authors.
The Secret Weapon in .NET 9 for Building AI-Powered C# Apps That Actually Scale

The Secret Weapon in .NET 9 for Building AI-Powered C# Apps That Actually Scale

Sukhpinder Singh - medium.com

Discover how .NET 9 and Microsoft.Extensions.AI enable scalable C# apps and a GPT-5 pipeline using embeddings and vectors.

C#, .NET 9, Microsoft.Extensions.AI, AI, GPT-5, embeddings, vector

Read More

Ollama vs LM Studio: Which Local AI Tool Wins in 2025?

Savage Reviews - youtube.com

Compare Ollama's CLI flexibility and speed with LM Studio's GUI ease for local AI running. Choose based on your needs: automation or content creation.

Ollama, LM Studio, AI tools, CLI, GUI, local AI

View

The Easiest Ways to Run LLMs Locally - Docker Model Runner Tutorial

Tech With Tim - youtube.com

Docker's new model runner simplifies local AI model management, similar to Ollama, integrating seamlessly with Docker Desktop for easier deployment.

Docker, AI, LLMs, model runner

View

EASIEST Way to Fine-Tune a LLM and Use It With Ollama

Tech With Tim - youtube.com

Learn to fine-tune LLMs in Python for Ollama with step-by-step guidance, code examples, and setup instructions.

Python, Ollama, LLM

View

Optimize Your AI - Quantization Explained

Matt Williams - youtube.com

Learn AI model optimization via quantization techniques (q2, q4, q8) to enhance performance on basic hardware while saving costs.

AI Optimization, Quantization, Ollama, Machine Learning

View

Can We Fix Software Engineering Estimation?

Kent Beck & Kevlin Henney - youtube.com

Exploring the feasibility of software estimation and techniques in modern engineering practices.

software estimation, no estimates, techniques, software engineering

View
Google's New LLM Runs on Just 0.5 GB RAM — Here’s How to Fine-Tune It Locally

Google's New LLM Runs on Just 0.5 GB RAM — Here’s How to Fine-Tune It Locally

Civil Learning - medium.com

Google's new AI model, Gemma 3 270M, requires only 0.5 GB RAM for local fine-tuning, enabling efficient use for software engineers.

Google, LLM, AI, Gemma 3, Fine-Tuning

Read More
Why software developers burn out, and how to fix it

Why software developers burn out, and how to fix it

Unknown - infoworld.com

Developer burnout is a significant issue exacerbated by AI. Learn about its causes and solutions.

developer burnout, AI, solutions

Read More
Kickstarting your libraries with the .NET Library Starter Kit

Kickstarting your libraries with the .NET Library Starter Kit

Dennis Doomen - dennisdoomen.com

A reliable starter kit for crafting open-source and internal NuGet libraries, proven by extensive usage.

NuGet, libraries, .NET, open-source

Read More
Top 10 GitHub Copilot Features Every Developer Should Know

Top 10 GitHub Copilot Features Every Developer Should Know

C# Corner - c-sharpcorner.com

Explore essential GitHub Copilot features to enhance developer productivity, including smart code completions and Copilot Chat.

GitHub Copilot, features, developer, productivity, code completions

Read More