200 Classic Games, One Playground for Algorithms and AI
Why I want to build a complete browser-based library of classic games—and a separate laboratory for search algorithms, reinforcement learning, and agents that learn to play.

Notes and writing11 posts
Why I want to build a complete browser-based library of classic games—and a separate laboratory for search algorithms, reinforcement learning, and agents that learn to play.

Exploring the computer vision, game-state reconstruction, chess engines, and cloud engineering behind my Chess Assistant AI project—and why seeing a board is not the same as understanding a game.

AI agents can browse, write files, call tools, and operate applications. That makes them powerful—and creates new risks around prompt injection, permissions, confirmation, and safe execution.

A behind-the-scenes look at building an AI-powered educational product, from scripts and voiceovers to captions, visual storytelling, and the engineering challenges behind a video-generation pipeline.

Apple’s 2026 Foundation Models updates highlight a broader shift: smaller local models, better privacy boundaries, and practical ways to build AI into everyday applications.

A look at how I'm building practical AI-powered applications for macOS, connecting voice assistants, automation, and everyday tools—and what I've learned along the way.

Google DeepMind’s October 2026 world-model announcement points toward environments that respond to actions in real time. Here is what makes that different from video generation—and what remains unsolved.

AlphaGenome Atlas is a striking example of AI applied to biology. But predicting molecular effects is not the same as predicting disease—and that distinction matters.

Exploring an ambitious FlyBrain Simulator concept using the FlyWire connectome, and the crucial distinction between mapping neural connections and simulating a living nervous system.

Vision-language-action models are beginning to connect perception, reasoning, and robot movement. A look at Gemini Robotics 2, physical-world uncertainty, and the engineering problems beyond a polished demo.

From classic cellular automata to predator–prey interactions, vegetation, disasters, and evolving ecosystems: the design challenges behind an ambitious simulation concept in Rust.
