This week’s collection features a mix of critical .NET lifecycle updates and practical strategies for optimizing your database interactions. These selected articles offer helpful insights into everything from edge computing deployments to the evolving landscape of AI in modern workflows.
AI
AI Raised the Bar (And Now We're All Tired) (Golnaz) - It's so true! So much can be done quickly today. An interesting question is: how do we avoid burning out resources and tokens? How, as human we stay smart? After all, life is a marathon, not a sprint!
EF Core vs Dapper in .NET: When to Use Each (Nick Cosentino) - Great post for developers or architects planning a future project. Both tools are great, so the decision factor depends on the context.
Reka just released Reka Edge, a compact but powerful vision-language model that runs entirely on your own machine. No API keys, no cloud, no data leaving your computer. I work at Reka and putting together this tutorial was genuinely fun; I hope you enjoy running it as much as I did.
In three steps, you'll go from zero to asking an AI what's in any image or video.
What You'll Need
A machine with enough RAM to run a 7B parameter model (~16 GB recommended)
Git
uv, a fast Python package manager. Install it with:
curl -LsSf https://astral.sh/uv/install.sh | sh
This works on macOS, Linux, and Windows (WSL). If you're on Windows without WSL, grab the Windows installer instead.
Step 1: Get the Model and Inference Code
Clone the Reka Edge repository from Hugging Face. This includes both the model weights and the inference code:
git clone https://huggingface.co/RekaAI/reka-edge-2603
cd reka-edge-2603
Step 2: Fetch the Large Files
Hugging Face stores large files (model weights and images) using Git LFS. After cloning, these files exist on disk but contain only small pointer files, not the actual content.
First, make sure Git LFS is installed. The command varies by platform:
Then pull all large files, including model weights and media samples:
git lfs pull
Grab a coffee while it downloads, the model weights are several GB.
Step 3: Ask the Model About an Image or Video
To analyze an image, use the sample included in the media/ folder:
uv run example.py \
--image ./media/hamburger.jpg \
--prompt "What is in this image?"
Or pass a video with --video:
uv run example.py \
--video ./media/many_penguins.mp4 \
--prompt "What is in this?"
The model will load, process your input, and print a description, all locally, all private.
Try different prompts to unlock more:
"Describe this scene in detail."
"What text is visible in this image?"
"Is there anything unusual or unexpected here?"
What's Actually Happening?
You don't need this to use the model, but if you're anything like me and can't help wondering what's going on under the hood, here's the magic behind example.py:
1. It picks the best hardware available.
The script checks whether your machine has a GPU (CUDA for Nvidia, Metal for Apple Silicon) and uses it automatically. If neither is available, it falls back to the CPU. This affects speed, not quality.
2. It loads the model into memory.
The 7 billion parameter model is read from the folder you cloned. This is the "weights": billions of numbers that encode everything the model has learned. Loading takes ~30 seconds depending on your hardware.
processor = AutoProcessor.from_pretrained(args.model, trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained(args.model, ...).eval()
3. It packages your input into a structured message.
Your image (or video) and your text prompt are wrapped together into a conversation-style format, the same way a chat message works, except one part is visual instead of text.
4. It converts everything into numbers.
The processor translates your image into a grid of numerical patches and your prompt into tokens (small chunks of text, each mapped to a number). The model only understands numbers, so this step bridges the gap.
5. The model generates a response, token by token.
Starting from your input, the model predicts the most likely next word, then the next, up to 256 tokens. It stops when it hits a natural end-of-response marker.
6. It converts the numbers back into text and prints it.
The token IDs are decoded back into human-readable words and printed to your terminal. No internet involved at any point.
If you prefer watching and reading, here is the video version:
That's Pretty Cool, Right?
A single script. No API key. No cloud. You just ran a 7 billion parameter vision-language model entirely on your own machine, and it works whether you're on a Mac, Linux, or Windows with WSL, which is what I was using when I wrote this.
This works great as a one-off script: drop in a file, ask a question, get an answer. But what if you wanted to build something on top of it? A web app, a tool that watches a folder, or anything that needs to talk to the model repeatedly?
That's exactly what the next post is about. I'll show you how to wrap Edge as a local API, so instead of running a script, you have a service running on your machine that any app can plug into. Same model, same privacy, but now it's a proper building block.
Red Teaming with Leron Gray (Hanselminutes with Scott Hanselman) - A quite interesting episode about playing the bad guys for the good cause. I enjoyed each second of this episode. I new those them existed, but it's great to learn more about them.
Baking Bread with Eric Wolfinger (Wild Ideas Worth Living) - I've been doing my bread for probably fifteen years, and just recently start messing around with sourdoughs... I'm not crazy.. Making bread is both simple and complex... and of course so fun.
Every Monday, I share my "reading notes". Those are the articles, blog posts, podcast episodes, and books that catch my interest during the week and that I found interesting.
It's a mix of the actuality and what I consumed. This week I was less in a reading mode...
Azure Logic Apps - Retry Policy (Sriram Hariharan) - This post explains how to customize a key feature to build successful integration solution in cloud programming.
DocumentDB protocol support for MongoDB (Vincent-Philippe Lauzon) - Woooo. That huge! We can now swap any mongodb for a documentdb and your tooling or app will continue to work.
Microsoft shows how bad Chrome is for your laptop’s battery (Tom Warren) - Wow when a friend of mine shared me that post, I didn’t expect Edge to be that good. And with the new release that is bridging back add-ons… Does Microsoft just came back in the race to be the best web browser?!
