All blog posts

This blog reflects my curiosity and experience across a wide range of IT domains — from hands-on engineering to strategic thinking. You’ll find posts that dive into technologies shaping the future, as well as reflections on how we build products, solve problems, and adapt to a changing workplace.

I write about:

Agentic architecture on the Edge

Beyond RAG

Scenic view of Tilikum Crossing over the Willamette River in Portland, Oregon at sunset.

JSONC

The Missing Layer Between Design and Code

SEO in the era of GenAI crawlers: what it means for websites and embedded content

Search is evolving at high speed. We are now in a world where traditional crawlers like Googlebot and Bingbot are being joined (and in some cases partially replaced) by GenAI-powered crawlers such as Google Gemini, Perplexity AI, and ChatGPT’s browsing agent. This shift changes how we should think about SEO, metadata, and content discoverability, especially when embedding rich media such as videos, podcasts, or interactive widgets.

Abstract glass surfaces reflecting digital text create a mysterious tech ambiance.

Run local LLMs on your Mac: llm-mlx, Apple MLX, and the power of the Mac mini M4

The dream of running powerful large language models (LLMs) locally, without GPU cloud costs or latency trade-offs, is not just alive — it’s thriving. Thanks to Apple’s MLX framework, the llm-mlx plugin, and the silicon magic of the Mac mini M4, running LLaMA 3.2, Mistral, and even larger models locally has become remarkably fast and easy.

an apple m4 processor in front of a computer circuit

Turbocharging transcription: Running whisper.cpp on a Mac mini M4

With the arrival of the Mac mini M4, Apple continues to redefine the balance between power efficiency and raw computing performance. When paired with a highly optimized tool like whisper.cpp — a C++ implementation of OpenAI’s Whisper model — the result is a surprisingly fast and local transcription pipeline that rivals cloud offerings.

sound, wave, voice, listen, digital art, voice, voice, voice, voice, voice

Whisper by OpenAI: a new era for speech recognition

In recent years, speech-to-text technology has seen remarkable advancements, but few developments have stirred as much excitement as Whisper, OpenAI’s automatic speech recognition (ASR) system. Released as open-source in 2022, Whisper quickly captured the attention of developers, researchers, and audio professionals thanks to its state-of-the-art performance, broad language support, and ease of use.