We have not accounted for the true costs of AI coding
It is time to face the true costs of AI coding. Reliable results require compute, supervision, review and maintenance that our productivity estimates often leave out.
Ndamulelo Nemakhavhani · AI · Cloud · Data
Systems worth understanding.
Field notes from building with artificial intelligence, cloud platforms, data systems, and the software connecting them.
Latest field note
The Era of Throwing Frontier Models at Everything Is Over
The Economics of Agents: Why GPT-6 Luna and DeepSeek V4.1 Flash class models matter more than you think
Read the essay →Recent writing
All 67 articlesWhat VS Code Remembers on Your Mac
VS Code stores configuration, extension state, workspace state, local file history, plugins, and logs across several locations on macOS. This post maps those directories, explains what they reveal, and separates local editor state from GitHub Copilot CLI and cloud data.
Discussing the Trust Planes of Autonomous AI Work
How to establish trust in autonomous AI systems through identity, secrets management, and continuous assurance.
Stop Prompting Your Agents to Behave: Use Sandboxing Instead
Prompts can shape what an AI agent tries to do. Sandboxing and capability controls determine what it can actually do.
Why Desktop Apps Are Making a Comeback in the Age of AI
The browser won the last decade on reach. AI workloads are local, stateful and long-running, and the browser sandbox was never designed for that. The most serious AI tools of the last two years shipped as desktop apps, and this post argues that is not a coincidence.
Selected work
View all projects
Azure Batch Migration for Deduplication Workloads
I led the redesign and migration of a VM-based deduplication solution to Azure Batch. Moving the workload to managed batch compute improved scalability and reduced annual client infrastructure costs by approximately $8,000.
Language Models for Tshivenda and Bantu Languages
I owned the research and training of masked language models for Tshivenda and other indigenous Bantu languages. The work expanded language-technology coverage for languages underserved by mainstream NLP systems.
Regulatory Document Intelligence
I applied NLP and large language models to extract key information from regulatory documents. The workflow was designed to make review more structured, traceable, and less dependent on repetitive manual handling.