"It is not the strongest or the most intelligent who will survive but those who can best manage change." - Charles Darwin
Hello data delvers! It's been some time but I'm back with more delves! In the time since my previous delve the landscape for local llm development has already shifted quite a bit so I want to come back with a refreshed setup guide!
"The right tool doesn't just make a job easier; it changes how you think about the problem." - Gemini 3
Hello data delvers! Though I am cautiously skeptical of the hype around AI, one area that I have seen my own productivity increase is by leveraging AI as a pair programmer. Up until this point, I have primarily relied on Github Copilot as my AI assistant. However, I recently gave Claude Code a try at work and was pleasantly surprised at its ability to go beyond what I had seen from Copilot and really "pair" with me. Based on these results, I resolved to set it up on my own machine to use for my personal projects. However, not wanting to spend money on tokens I wanted to be able to run an LLM locally and connect it to Claude Code. Fortunately with the latest release of Ollama this is a pretty straightforward thing to do!
"Self-reflection is the school of wisdom." - Baltasar Gracian
Happy 2026 data delvers! As we enter a new year I wanted to take some time to reflect on the past year, share some thoughts about how I think it went, and shed some light on my goals for 2026!
"Containerization is the new virtualization." - James Turnbull
Greetings data delvers! In part eight of this series we deployed our first multi-service system. In this part, we examine more deeply how we are deploying our services with Docker and look for opportunities to make our deployment more optimized and secure.
"The first rule of any technology used in a business is that automation applied to an efficient operation will magnify the efficiency. The second is that automation applied to an inefficient operation will magnify the inefficiency." - Bill Gates
"What are the biggest challenges you've faced when integrating AI into your work?"
Greetings data delvers! I had the opportunity to serve on a multi-disciplinary panel recently where I was asked that very question. At the time, my answer focused on immediate challenges with data quality and access to tooling. While those are legitimate concerns, the question has stuck with me for the past few weeks as requiring a deeper answer. As I've been thinking more about it, I've developed a more nuanced view which I'd like to capture here. Hopefully, it may be of use if you are looking to adopt more AI into your workflows!
"Academia is about discovering truth. Industry is about delivering value." - Cassie Kozyrkov
Hello data delvers! I recently had the opportunity to give a guest lecture at my Alma Mater to students about the differences between practicing data science in academia vs industry. It was a lively discussion and I wanted to capture some of my thoughts as I think they could be particularly useful to individuals transitioning from an academic setting to an industrial one. The objectives, methods of working, and ultimately what determines your success are vastly different in academia compared to industry. To illustrate this here is an example of a conversation I had early in my career:
"The only constant in life is change." - Heraclitus
Hello data delvers! I recently revisited my Raspberry Pi after a long hiatus. As part of this I made sure to update all the packages and OS to the latest version. If you've read my previous Raspberry Pi delve, you'll know that being able to make applications full screen isn't as straightforward as it should be. Much to my surprise, after updating everything my fullscreen keyboard shortcut broke! After spending some time internet sleuthing I'd like to share what the fix is with you all!
"Only a small fraction of real-world ML systems is composed of the ML code... The required surrounding infrastructure is vast and complex." - Hidden Technical Debt in Machine Learning Systems, Sculley et al.
Greetings data delvers! In part seven of this series we finally deployed a model! For this part we'll examine how to utilize our model as part of a larger microservice ecosystem!
"Your work is going to fill a large part of your life, and the only way to be truly satisfied is to do what you believe is great work." - Steve Jobs
Hello data delvers! I recently successfully wrapped up a journey to find a new job! Along the way, I had the opportunity to interview at several different companies, experience many different styles of interviews, and explore different types of roles. For this delve, I intend to distill some thoughts about this process and share some lessons learned in the hopes they may be useful to others either looking to break into this field or find their next opportunity within it. If that sounds of interest stick around!
"Machine learning models are only as good as their deployment strategy. An unused model is just a fancy equation." - Chat GPT
Hello data delvers! In part six of this series we containerized our application, making it portable and easy to deploy. For this part we will take a step back. Introduce machine learning (finally!), and explore how we can begin to incorporate machine learning models into our microservice ecosystem!