After the democratization of sufficiently intelligent systems like ChatGPT/Claude/Gemini behind closed APIs, naturally the fear of being reduced to prompting away the problems is quite high. I feel this fear is rather deep, as previous workflows provided a sense of (more) control. At the same time, for many who take pride in the raw code get offended when this reduction to 'mere' prompting happens. Thus, when a solution that addresses the ego or the fear comes along, it will be well received among these groups first and then later adopted by others.

Hackathons are in full swing this year and as I wanted to catch up on MCPs, I decided to attend a Hackathon by ToolHouse focused on MCP. MCP servers and clients I created are at the end of this post.

This is an implementation of the classic Tic Tac Toe game, powered by Reinforcement Learning (RL)! This project demonstrates how an RL agent can learn to play Tic Tac Toe optimally through self-play and Temporal Difference (TD) learning.

Optimization is everywhere - in tuning machine learning models, industrial processes, and even in everyday decision-making. But what happens when the problem you want to optimize is a black box, expensive to evaluate, and has way too many parameters? That's where my master's thesis comes in: Latent Space Bayesian Optimization with Transfer Learning. Here's a deep dive into what I did, why it matters, and what I learned along the way.

Clustering evolving data streams is one of those topics that sits right at the intersection of machine learning, big data, and real-time analytics. With the explosion of data from IoT devices, social media, and continuous sensors, we're not just dealing with big data - we're dealing with fast data that never stops coming. In this post, I'll walk through the core ideas behind clustering evolving data streams, the unique challenges, and some of the leading algorithms and concepts in this space.