Lessons

first stable v1.0 release in late October 2025. After spending the past two months working with their latest APIs, I genuinely feel that is essentially the most coherent and thoughtfully designed version of...

a decade old now. Back then, OpenAI felt like one (well-baked) startup amongst others. DeepMind was already around, but not yet fully integrated into Google. And, back then, the “triad of deep learning” —...

couple of years, RAG has became a type of credibility signal within the AI field. If an organization desires to look serious to investors, clients, and even its own leadership, it’s now expected...

across industries. Traditional engineering domains are not any exception. Previously two years, I’ve been constructing LLM-powered tools with engineering domain experts. Those are process engineers, reliability engineers, cybersecurity analysts, etc., who spend most of...

in machine learning are the identical. Coding, waiting for results, interpreting them, returning back to coding. Plus, some intermediate presentations of 1’s progress. But, things mostly being the identical doesn't mean that there’s nothing...

my stuff, then you realize that not too way back, I wrote a chunk concerning the Model Context Protocol (MCP)—explaining what it's, how it really works, and even walking you thru constructing your...

or vision-language models is a strong technique that unlocks their potential on specialized tasks. Nevertheless, despite their effectiveness, these approaches are sometimes out of reach for a lot of users as a result...

in the sphere of enormous language models (LLM) and their applications is very rapid. Costs are coming down and foundation models have gotten increasingly capable, capable of handle communication in text, images, video....