AI in Practice

Working with AI systems directly — models, tools, workflows and the knowledge infrastructure behind them. From hands-on experiments with Claude, ChatGPT and Gemini to structuring content for intelligent systems.

AI in Practice

From Ideas to Precision: Why I Use Mermaid with LLMs

Image generation is messy for structure. With Mermaid + LLMs, diagrams become clear, tweakable, and practical. A real tool for strategy and logic.

AI in Practice

AI Fine-Tuning for Non-Engineers

Compact AI models make fine-tuning possible for non-engineers. I tried it myself and learned how AI becomes portable, local and real.

AI in Practice

Running GPT-OSS Locally: What OpenAI Just Made Possible (And What It Didn't)

OpenAI released GPT‑OSS under an open licence. Here's what that really means, how I ran it on a Mac mini, and where you might start experimenting too.

AI in Practice

From API Users to Embedded Agents: How Systems Are Becoming Smarter From Within

From passive APIs to embedded agents: systems now host autonomous, AI‑powered modules that live inside and act proactively rather than wait for calls.

AI in Practice

Running a Local LLM on Your iPhone

I explored how far mobile AI has come by running LLMs directly on my iPhone. No cloud, no upload. Here’s what I learned from testing Haplo AI.

AI in Practice

Rules and Guesses: The Twin Engines Behind Smarter AI

AI isn’t just smart, it’s a duet. One part rigid and logical, the other fluid and generative. Together, they form the neuro-symbolic systems behind real insight.

AI in Practice

ChatGPT Connectors: The Emergence of a New Interface Layer

ChatGPT just got a new superpower: connectors. Real-time access to your tools like Drive, HubSpot and Notion—without uploading a thing.

AI in Practice

Google's AI for Individuals and SMBs: Clarity, Costs, and Strategic Choices

Google's AI options are powerful but confusing. Here's how I compared Google One vs Workspace—and why SMBs should think twice before locking in.

AI in Practice

Choosing ChatGPT Team: From AI-Confidant to Trusted Colleague

Migrating to ChatGPT Team reshaped my digital workflow—less friend, more colleague. Here’s what I learned from shifting accounts, data, and mindset.

AI in Practice

How OpenAI o3 Became a Geospy and Found My Photo’s Location

I asked OpenAI’s o3 model to play geospy—like a human OSINT analyst. It zoomed, searched, reasoned, and nailed the photo’s location. Watch it unfold.

AI in Practice

Who Is the Author? Authenticity in the Age of AI

AI helps us write—but are we still the ones deciding what’s worth saying? A reflection on authorship, ethics, and identity.

AI in Practice

What Zeta Alpha Gets Right About AI (That Others Don’t)

AI you can trust, built for complexity. Zeta Alpha shows how European companies can take back control with search that works—across formats, securely.

AI in Practice

Scaling RAG Applications with Weaviate.

Learn how Weaviate's open-source platform supports AI agents and knowledge bots through advanced vector search capabilities.

Signals, Systems, and Speech

What happens when language models meet logic? Larry Swanson and I explore neurosymbolic AI, voice tech, and the human meaning behind machine-readable content.

Speech recognition, Speech-to-Text, Dictation, and Transcription: What’s the Difference?

Just like picking the right writing tool, choosing the right speech technology makes all the difference—here’s how to decide.

AI in Practice

The Silent Revolution: How AI is Transforming Speech Recognition

Speech recognition is no longer a clunky afterthought—it’s seamless, fast, and nearly human-like. Thanks to AI’s self-attention, our devices now truly listen.

AI in Practice

Lost in ChatGPT's Models? A guide (March 2025)

Overwhelmed by GPT-4o, GPT-4.5, and o3-mini? This guide clarifies ChatGPT’s AI models, helping you confidently pick the right tool for every conversation.

AI in Practice Featured

Fireflies.ai: Meeting Transcriptions & Automation

Fireflies.ai changed how I handle meetings, capturing every conversation with ease. Its AI-driven transcription is powerful, but some features need fine-tuning.

AI in Practice

Transcribing Speech on a Mac and iOS: My Workflow and Tools

Need seamless transcription on Mac & iOS? Apple’s built-in tools are limited—here’s how I use Transcribe for accurate, multilingual, cloud-based audio transcription.

AI in Practice

OS-Level Translation: A Multilingual Productivity Hack

Apple’s OS-level translation makes switching between languages effortless. Built into iOS/macOS, it’s fast, private, and eliminates app-switching.

AI in Practice

Google Gemini's Video AI: What's New and Why It Matters

Google Gemini’s video AI is fast, smart, and a game-changer. But why am I amazed while AI experts remain unimpressed? A shift in perspective explains it.

AI in Practice

DeepSeek R-1: Open-Source AI model

DeepSeek R-1 rivals OpenAI’s o1 at 13x less cost. A groundbreaking, open-source model reshaping AI innovation—open for all to explore.

AI in Practice

LLM-Driven Automation and Anthropic’s Computer Use

Anthropic’s Computer Use, make.com, and Automator: See how LLMs simplify automation, analyze tasks, and redefine productivity. Watch examples and learn more!

Beyond keyboards and screens

Reconnecting with Bram led to a bold experiment: writing this entirely by voice. Here’s why the future of work may no longer need keyboards or screens.

AI in Practice

The Power of Sequences

Language, music, biology—at their heart, it's all sequences. This realisation reshaped how I understand AI, making LLM's more tangible, less a mystery, and truly insightful.