Artificial Intelligence

We’ve embraced the future. AI agents like Cline are now the primary “builders” of software, executing complex engineering plans from high-level specifications. As I’ve argued in “The Architect vs The Builder”, the human role is shifting from execution to architectural oversight and defining intent. But this shift introduces a profound, often uncomfortable, question: How do we know it actually works? In a world where AI is writing the code, generating the data, and even orchestrating deployments, traditional notions of testing and reliability are breaking down. AI reliability is weird, and it demands a complete re-evaluation of our verification strategies. ...

An exploration of Cline, the autonomous AI coding agent that lives in your IDE and handles complex, multi-step engineering tasks through tool-use and agency.

The job search has long been a one-way mirror - companies deploy AI to filter applications while candidates manually juggle spreadsheets, tailor cover letters, and hope their resume gets past the automated screener. Career-Ops flips that script entirely. Built on Claude Code, it’s an open-source system that gives job seekers their own AI advantage: intelligent evaluation of opportunities, automated customized applications, and systematic candidate strategy. The Problem It Solves The traditional job search is a grind of low-signal noise. You find 30 job postings. You read them. You customize a resume. You write a cover letter. You track applications in a spreadsheet. You wait. You compare offers using gut feel and spotty spreadsheet columns. The process burns time and attention - exactly when you need both to think clearly about your career. ...

In the evolution of agentic software engineering, one critical gap remains: the disconnect between project management and code execution. Your Kanban board tracks what needs doing, but your AI assistant lives in your IDE. Cline + Kanban closes that gap. The Problem: Two Separate Systems Most teams operate with a frustrating split: Kanban board (Linear, GitHub Projects, Jira, Trello): “Build the user authentication flow” IDE with Cline: “Let me write code” Manual sync: You paste the task, manually update the board status, context-switch constantly This handoff is where developers lose hours to context-switching and where tasks fall through the cracks. ...

For years, extracting structured data from LLMs meant post-processing their text output: parse JSON, handle edge cases where the model forgot to close a bracket, write validation code to check if the output matched your schema, implement fallback logic when parsing failed. Then came structured outputs - a way to constrain LLM responses to match a JSON schema before they’re returned to you. Structured outputs sound simple but represent a fundamental shift in how to build production LLM systems. And yet, most teams are still extracting data the old way - waiting for the post-processing disasters that guaranteed outputs prevent. ...

Every week brings a new headline: “Model X reaches 1M token context!” “Model Y supports 2M tokens!” The LLM industry seems locked in an arms race where the stated goal is always “bigger context window,” as if this single metric determines whether a model is useful. It doesn’t. The context window arms race reveals a gap between what engineers think matters and what actually works in production systems. And if you’re building with LLMs, understanding that gap will save you from infrastructure that doesn’t solve your problems. ...

There’s a persistent myth in tech: AI will get cheaper. The argument is straightforward - Moore’s Law, scale effects, competition, and raw compute efficiency improvements mean costs should plummet. Yet in April 2026, Claude costs roughly what it did in 2024. GPT-4 Turbo pricing hasn’t moved in eighteen months. Gemini’s cost structure remains sticky. Why? The answer isn’t that progress hasn’t happened. It’s that the economics of modern AI are fundamentally different from hardware commoditization. Once you understand the actual constraints, the stability of pricing becomes logical. ...

By early 2026, the “Local vs. Cloud” debate has moved past the experimental phase. We are no longer just “trying to see if Llama runs on a Mac.” Instead, professional engineers are building sophisticated Hybrid AI Stacks where local and cloud models work in tandem. The landscape has shifted because the hardware caught up to the software. With the prevalence of unified memory on Apple Silicon and the accessibility of 24GB+ VRAM cards like the RTX 50-series, the “local” ceiling has been smashed. ...

The Rise of Small Language Models: Why Size Isn’t Everything For years, the narrative was simple: bigger is better. GPT-4 was massive, Claude was massive, and the race seemed to be about who could train the largest model on the most data. But that story is changing. Small language models - typically under 15 billion parameters - are proving that you don’t need 175 billion parameters to solve real problems. The shift isn’t just about efficiency. It’s a fundamental change in how we think about AI deployment, cost, and what actually matters for most use cases. ...

If you’ve spent time running language models locally through Ollama or another inference engine, you’ve probably discovered the same friction point: the command-line experience works, but it’s clunky. You’re juggling terminal windows, managing conversation context manually, managing files through the filesystem. Open WebUI solves this by offering what Ollama itself didn’t: a genuinely usable interface. What Open WebUI Does Open WebUI is a web-based chat interface designed to work with language models. It’s styled after ChatGPT, with a familiar conversation layout, sidebar for conversation management, and all the modern UX conveniences you’d expect. The critical difference: you control the backend entirely. ...