Writing
Thinking out loud about
AI in production
Engineering notes, case studies, and opinions on building AI systems that actually work.
Kategori
The Potential Relationship Between Artificial Intelligence and Blockchain
Explore the complex and often conflicting relationship between Artificial Intelligence and Blockchain technology. This post delves into how AI's data-driven nature clashes with Blockchain's immutable data principles, questioning the feasibility of their integration for secure data solutions.
GPT-5.5: From Chatbot to "Thinking" Agent—A Technical Deep Dive
Explore the technical architecture of OpenAI's GPT-5.5. Learn how "Test-Time Compute" and "Computer Use" are transforming AI from chatbots into autonomous agents, and the technical risks involved in this mimetic revolution.
From Demo to Production: Engineering Discipline to Keep AI Agents “Well-Behaved” (FSM + LLM)
LLM-based AI agents often work well in demos but become unpredictable in production due to their probabilistic nature. The solution is to control system behavior using Finite State Machines (FSM) while using LLMs only for reasoning. This hybrid approach makes AI systems more reliable, traceable, and production-ready.
Python's 30-Year Legacy: Is the GIL Departing or Devolving? A Deep Dive into an Engineering Trade-off
Is the GIL leaving Python? Explore the impact of PEP 703 and sub-interpreters on parallel programming, and discover how these innovations are reshaping the future of CPython and the engineering world.