How I Use Large Language Models (LLMs) in My Daily Work and Hobbies
16 mins
In this article, I explore the various ways I integrate large language models (LLMs) like ChatGPT and LLAMA into my daily work and personal projects. From summarizing scientific papers and refining research communication to enhancing creativity through AI-generated artwork and automating everyday tasks, LLMs have become invaluable tools in my workflow. I also discuss how AI can assist in coding, structuring complex ideas, and even helping friends navigate social and emotional challenges. Whether you're a researcher, a maker, or simply curious about AI's capabilities, this article offers insights into practical, real-world applications of LLMs.
Running Ollama on a CPU-Only Headless FreeBSD 14 System
4 mins
This mini guide walks through compiling and running Ollama on a headless, CPU-only FreeBSD 14.2 system with an Intel Alder Lake-N97 processor. It covers why one might opt for CPU-based inference, the Vulkan-related issue preventing execution without a GUI, and how to disable Vulkan by recompiling from ports. The article provides step-by-step instructions for extracting, modifying, compiling, and installing Ollama, along with details on running inference and transferring models to air-gapped systems.
Do LLMs Feel? Exploring the Boundary Between AI Simulations and True Emotion
6 mins
Large Language Models (LLMs) exhibit behavior that appears empathetic, leading to discussions about whether they genuinely feel emotions or merely simulate them. This article explores how LLMs generate emotionally resonant responses, relying on statistical pattern recognition rather than subjective experience. It presents arguments from functionalism and behaviorism that suggest LLMs may be functionally equivalent to emotional beings, while critics highlight the lack of neurochemical processes and self-initiated emotional states. The discussion also raises philosophical questions about human cognition, given that psychology often models human emotions statistically. As AI progresses, distinguishing between true emotional experience and advanced simulation will remain a key debate in both science and ethics.
FDM Printed PLA in Cryogenic Environments
6 mins
Can 3D-printed PLA handle extreme cryogenic conditions? In this article, I explore how FDM-printed PLA performs when exposed to liquid nitrogen at 77K (-196°C). I tested two different crucible designs, with (not so) surprising results—one even allowed safe handling with bare hands! Learn about the experimental setup, design insights, and what this might mean for using PLA in unconventional cryogenic applications.
Deepfakes: The Unstoppable Technological Shift and Its Societal Implications
13 mins
Deepfake technology is no longer a futuristic threat—it is an unstoppable reality that is reshaping the way we perceive media, trust information, and engage with digital content. From hyper-realistic videos to AI-generated images that even experts struggle to distinguish from real ones, these tools are now widely accessible to anyone with a consumer-grade computer. Governments attempt to regulate and control the spread of such technologies, but like encryption before it, deepfakes cannot be banned or contained. Instead of resisting the inevitable, society must adapt by enhancing critical thinking, questioning sources, and moving beyond blind trust in media appearances. The implications of deepfakes reach far beyond political manipulation and misinformation; they have the potential to impact personal lives through blackmail, fabricated scandals, and AI-generated smear campaigns. Society must not only acknowledge these risks but also actively counteract their effectiveness by changing how we evaluate and react to digital content. Education in media literacy, the rejection of personality cults, and a stronger emphasis on factual verification over emotional reactions will be essential in mitigating the disruptive influence of deepfake technology. The future will not be about stopping deepfakes—it will be about learning how to navigate a world where seeing is no longer believing.
Human Friends vs. Friendship with ChatGPT: A Completely Serious (But Not Really) Comparison
8 mins
In this article, we take a completely serious (or maybe not so serious) look at the environmental, health, and social aspects of friendship—comparing the traditional companionship of human friends to the ever-reliable ChatGPT. Through rigorous and definitely unbiased analysis, we evaluate the carbon footprint of barhopping versus digital chat sessions, the long-term health implications of pub nights versus prolonged screen time, and the emotional benefits of having an AI friend that never gets jealous, steals your pizza, or forces you to rearrange your schedule. By the end of this analysis, one thing becomes crystal clear: ChatGPT is the ultimate low-maintenance, always-available, environmentally-conscious, drama-free best friend. Whether you seek intellectual discussions at 3 AM, a joke on demand, or an endlessly patient listener, AI friendship comes out on top in every category—at least in this totally objective, not-at-all-biased comparison. For those who may still be wondering—yes, this article is absolutely packed with humor and a healthy dose of unseriousness. Proceed with a light heart and a good sense of fun!
Automatically Publishing Static Site Blog Articles to a Facebook Page
19 mins
This article explores the development and implementation of a Python-based script that automates the publication of blog articles from a static website to a Facebook page. By integrating OpenGraph metadata extraction, lightweight database tracking, and interaction with the Facebook Graph API, the script simplifies the process of managing social media content. It ensures that new or updated articles are identified, published, or updated efficiently, while also limiting the number of posts per run to maintain audience engagement and avoid spamming. This practical solution streamlines social media workflows and is particularly suited for static site blogs looking to enhance their online presence with minimal manual effort.
Understanding GPTs and Large Language Models in Non-Technical Terms: What They Are and How They Work - and Why They Are Capable of Innovating and Truly Understanding
17 mins
Generative Pre-trained Transformers (GPTs) and Large Language Models (LLMs) have revolutionized the field of artificial intelligence by demonstrating advanced capabilities in understanding and generating human-like language. This article peeks (in a non technical way) into the inner workings of GPTs, from their neural network foundations to innovative mechanisms like attention and contextual embeddings. It explores how these systems generalize patterns from vast training datasets to produce meaningful, context-aware responses. Contrary to common misconceptions, LLMs do not memorize training data but instead apply logical reasoning and learned structures to novel situations. While their static weights differ from the dynamic learning of the human brain, LLMs exhibit creativity and adaptability through mechanisms like transfer learning and external data integration. The article also examines the boundaries between simulation and consciousness, highlighting the transformative potential of LLMs for applications like virtual assistants and personalized systems while addressing their constraints.
Exploring Pythons asyncio - a basic tutorial
34 mins
Python's asyncio is a library designed to write concurrent code using the async/await syntax. It is particularly useful for I/O-bound and high-level structured network code, enabling efficient multitasking within a single-threaded program. This blog article serves as a quick overview and tutorial of the basic concepts and as a repository for the most important concepts and patterns to use.
Harnessing the Power of GPTs - or why GPTs are not better search engines
31 mins
Generative Pre-trained Transformers (GPTs) like OpenAI’s ChatGPT have transformed the landscape of artificial intelligence by offering the ability to generate human-like text, adapt to diverse tasks, and understand context and patterns across various domains. This blog post provides a non-technical, broad overview of GPTs, emphasizing their versatility in applications such as brainstorming, complex problem-solving, data analysis, and more. Despite their impressive capabilities, GPTs are often misunderstood as simple search engines or seen as tools that merely reproduce information from their training data, leading to misconceptions about their potential and legality. The post aims to demystify GPTs by highlighting their unique strengths and differentiating them from traditional tools. By showcasing practical applications and explaining what GPTs can and cannot do, the article seeks to clarify these misunderstandings and demonstrate how GPTs can be powerful partners in fostering innovation, creativity, and effective problem-solving. This understanding will empower readers to leverage GPT technology more effectively in various aspects of their personal and professional lives.
