Blog
In this section, I write on topics ranging from Artificial Intelligence to business to astrophotography. If you are seeking more technical depth, feel free to explore the Experiments section.
How I use Generative AI for my blog: mainly polishing my writing drafts. and for boilerplate code. Ideas and math are mine; storytelling often by GenAI.
Expect a new entry every second week.
The Geometry of Memory: How Actions Leave Traces in Your Body
Tangential Action Spaces (TAS) provide a geometric framework for embodied agency, modeling agents as a hierarchy of abstract physical, cognitive, and intentional spaces . This model reveals a fundamental trade-off between an agent's energetic efficiency and its capacity for experiential memory. The central finding is a "cost-memory duality," which states that path-dependent memory is never free and incurs a quantifiable excess energy cost. This predictive framework unifies cost, memory, and learning, providing a new language to analyze agent behavior, self-modification, and social dynamics.
Learning Machine Learning Through Interactive Exploration
The field of machine learning evolves at a relentless pace. New architectures emerge monthly, terminology shifts quarterly, and what seemed cutting-edge last year becomes foundational knowledge today. This creates a unique challenge: how do we build educational resources that remain both accessible to beginners and relevant to practitioners?
Automate the Automation
The average knowledge worker switches between applications 10 times per hour and spends 4-8 hours weekly on repetitive tasks. These patterns, forwarding emails, scheduling follow-ups, and updating documentation, are predictable yet remain manual. Workflow Whisperer addresses this inefficiency through an agent-based architecture that learns from observation rather than configuration.
Evolutionary Algorithms: A Gentle Introduction to Problem Solving, Inspired by Nature
Evolutionary Algorithms (EAs) represent a fascinating branch of artificial intelligence and computer science, drawing their core inspiration from the processes of biological evolution to tackle complex problems. Rather than depending on precisely defined instructions to reach a solution, EAs employ a simulated version of "survival of the fittest."
The Hidden (R)Evolution
This blog post is about my small booklet "The Hidden (R)Evolution". I document how scientists are moving beyond traditional machines made of metal and silicon and instead using living materials to create new kinds of systems. The idea to write about this topic emerged during my collaboration with Dr. Michael Levin, a Professor at Tufts University. Michael is a developmental biologist.
