Recent Articles
Long-form writing on AI engineering, product development, and technical leadership.
-
The Rust Language + Toolchain: Robust Guardrails Against Agent Hallucinations, Dead Code, and Runtime Bugs
How Rust’s strict compiler, type system, and ownership model create a tight feedback loop that catches agentic coding mistakes at compile-time rather than runtime, transforming the language’s perceived barriers into productivity multipliers for AI coding agents.
-
The Commoditization Trap: Why Model-Agnostic AI Products Will Win
Why LLM companies that lock their products to proprietary models are undermining their own competitive advantage, and how model-agnostic architectures that keep models hot-swappable will ultimately capture more value as state-of-the-art models inevitably commoditize.
-
Bringing AI Functions to the Llama Family
Releasing an open source dataset and fine-tuned Llama-2 7B chat model that brings OpenAI-style function calling capabilities to open source LLMs through synthetic data generation, QLoRA fine-tuning, and multi-objective optimization.
-
Empathizing with Users and Being Product-Minded
Great software engineering requires more than technical skills—it demands empathy for users and product-minded thinking that balances business needs, technical feasibility, and user experience to create truly valuable solutions.
-
The Art and Science of Evaluating Senior Engineering Skills
Why the path to senior engineering roles resists checklists and algorithms, and how continuous dialogue through regular one-on-ones provides better guidance than quantifiable metrics for developing nuanced leadership and judgment skills.
-
Engineering Values and Principles for High-Performing Teams
A comprehensive framework for building exceptional engineering teams, covering good judgment, healthy collaboration, effective communication, value delivery, and sustainable practices drawn from years of technical leadership experience.