Posts

Running Local AI Models

Image
As AI models become more powerful, they are also becoming much more accessible. I have been interested in what happens when you trade a little model accuracy for the ability to run everything on your own machine, without relying on paid cloud infrastructure. For developers, researchers, and hobbyists, that shift is useful for more than just cost. It also changes how private, flexible, and portable these tools can be. This week I spent some time trying two popular ways of running local AI models: Ollama and LM Studio . Both are open source and free to use, and both make it much easier to get started than I expected. What I wanted to understand was not just whether they worked, but how they felt to use in practice and where each one made more sense. What I like about running models locally is that the benefits are immediate. There is the obvious cost saving, especially if you are experimenting often or working through lots of prompts, but privacy matters just as much. When the mode...
Post a Comment
Read more

Prototyping using Google AI Studio

Image
Introduction This week, I experimented with Google AI Studio. The objective was to see how difficult it would be to create a web front-end for a word puzzle solver targeting games like the Nine Letter Word , NYT Spelling Bee , and Scientific American Spellements . Developing the Requirements I had several command line programs that solved the problem. Now I want a web front-end. I had used Flutter before and knew it could deliver not only a web front-end but also native desktop and mobile apps. I drafted a requirements document in Markdown and asked Copilot and Gemini to review and suggest improvements. The document covered puzzle-solver inputs, examples, expected behaviour, and UI style. For this solution, I expected a client-server architecture. You can see the initial application requirements document on GitHub. Once satisfied, I submitted these requirements to AI Studio. First Iteration The first iteration produced a functional website. AI Studio provided a mock solver ...
Post a Comment
Read more

How J.J. Horning Unlocked the Logic of Language

Image
In 1969, computational linguistics was at an impasse. A powerful theorem suggested that neither machines nor humans could learn language without explicit instruction. J.J. Horning, with a brilliant application of statistics, shattered that assumption. His breakthrough laid the conceptual groundwork for how modern artificial intelligence, from Google Translate to ChatGPT, processes the structure of human speech. The Problem: Gold's Pessimism To understand the weight of Horning's contribution, we must first look at the "pessimism" he confronted. Before Horning, E.M. Gold had published Gold's Theorem , arguing that even simple languages could not be "identified in the limit" (learned) if the learner only saw positive examples. In Gold's model, "positive examples" are simply correct sentences ("The astronomer saw stars"). To learn which sentences are incorrect ("Saw astronomer the stars"), Gold argued that a learner ...
Post a Comment
Read more

Running a Digital Office

Image
Back in 1999 I decided to go paperless. This was a significant challenge then as many bills were still being sent via post, and few offered digital alternatives. The challenge was doubly hard as I was (and am still) running Linux as my only operating system. These are a few of the things I had to do to make a digital office work and how things have evolved since then. The Early Days The choice of a Linux desktop meant that I had to find tools that were compatible with my operating system. This limited my options, but I was able to find open-source tools that met my needs. I used GIMP for image editing, LibreOffice for document editing, and PDFtk for PDF manipulation. My Canon printer had a built-in scanner, which I used to digitise paper documents. Canon printers and scanners are well supported by Linux. I used XSane for scanning documents. I also used rsync to maintain a continuous backup of my digital files. Saving these scanned documents and bills as PDFs on my computer w...
Post a Comment
Read more

The End of Effective Antibiotics

Image
Imagine a future where a routine surgery or a simple infection becomes life-threatening—that is the risk antimicrobial resistance (AMR) poses. Informed by warnings that antimicrobial resistance could become the next major global health crisis, I dug into WHO and Scientific American reporting to understand more... Introduction: The Shift in Modern Medicine Since the clinical debut of penicillin in the 1940s, modern medicine has operated under a luxury: the "guaranteed" cure. For nearly a hundred years, antibiotics have underpinned the risky work of routine surgeries, cancer therapies, and transplants. We have lived in an era where the primary risk of an infection was a week of discomfort, not a death sentence. However, we are now witnessing a fundamental collapse of these defences. As the historical record shows, there has always been a delicate "seesawing" balance between the drugs humans develop and the bugs that evolve to survive them. For decades, medical in...
Post a Comment
Read more

Why I Still Maintain a Private Wiki in the Age of AI

Image
For a consultant, the most valuable asset isn’t the hardware or certifications —it’s the knowledge. Too often, that knowledge is left behind when you move between clients. You hand back the hardware, lose access to the Jira tickets, and the internal documentation you wrote becomes a ghost in someone else's machine. Years ago I adopted a private DokuWiki that travelled with me through firewalls, tech changes, and career moves. Here is why, even in the age of LLMs, it remains an important tool. The Consultant’s Dilemma: Firewalls and "Fading" Skills Consulting is a nomadic life. You spend months deep in a client’s infrastructure, often behind restrictive firewalls where online resources are a luxury, not a guarantee. I realised early on that I couldn't rely on the client’s internal systems to store my personal breakthroughs. I needed a knowledge base that moved with me. Whether I was troubleshooting a niche Git conflict or configuring a Linux environment on a lock...
Post a Comment
Read more

Running Code in the Cloud: Comparing GitHub and GitLab

Image
Building a specialised tool such as a word-puzzle solver needs more than automated builds. The real value is letting users run the solver from their browser—enter letters, press a button, and get results without a command line. For example, given letters like "mitncao", users should find every valid word without leaving the UI. That requires a simple run method: press a button, type the letters, and receive results quickly. By implementing this on both GitHub and GitLab I learned how each platform compares in setup effort, input sanitisation, and user experience. Takeaway 1: GitHub is Fast and Simple An Easy Start: GitHub's Straightforward Setup For those who want to move from an idea to a working tool in minutes, GitHub is a strong choice. Setting up a manual start button for the solver was straightforward, largely due to the integration between the platform and AI tools like GitHub Copilot. Instead of digging through manuals, I could describe the required inputs (...
Post a Comment
Read more