Latest Posts
Experiments with Agents
I'm experimenting with a team of LLM agents for my project, using PI Agent, Docker isolation, and a tentative split of responsibilities. Here are my first impressions of GPT, Claude, and DeepSeek.
An Attempt to Bring C++ Closer to Rust's Guarantees
The resulting setup does not turn C++ into Rust and does not provide the same memory safety guarantees. But it catches substantially more bugs at compile time, during tests, and in static analysis.
Network Architecture Concept for a Virtual World
When thousands of humans and AI agents share one world, the network quickly becomes the most temperamental part of the system. To keep it manageable, I split it into five layers. Each layer solves a single problem and knows almost nothing about the others.