ai-productivity, software-engineering, career-development, intent-engineering, technical-leadership, future-of-work
AI agents are commoditizing tool-specific knowledge, shifting the scarce skill from knowing a tool's syntax to knowing which problem is worth solving. Engineers who can define goals, constraints, and success criteria will capture the premium that tool expertise once held.
ai-coding-tools, database-migration, devops, ai-operations, human-in-the-loop
We pointed an AI coding CLI at a high-stakes database migration and treated it as the operator, not a code generator. What followed changed how we think about AI in infrastructure: the real frontier is leverage under human control, not autonomy.
agentic-ai, ai-system-design, llm-safety, prompt-injection, ai-architecture, model-routing
Six false assumptions break most agentic AI systems before they scale. This post names each fallacy, documents the real-world damage it causes, and outlines the design patterns that prevent it.
ai-adoption, enterprise-ai, ai-implementation, change-management, ai-strategy
Building an impressive AI demo has never been easier, but most organizations fail to turn prototypes into production systems that deliver real business value. The true barriers are data fragmentation, workflow integration, organizational change, and undefined success metrics, not model quality.
open-source, ai-development, code-review, software-maintainership, developer-tools
Open source is more important than ever in the AI era, but the contribution model built on drive-by pull requests is collapsing under AI-generated submissions. The fix is not to close the gates but to redesign how contributions are accepted, verified, and credited.
ludismo, modern-luddism, anti-ai-bias, generative-ai, ai-criticism, content-evaluation
When a genuine Monet painting was mislabeled as AI art, critics panned it as soulless. The episode is a case study in modern Luddism: reflexive anti-AI bias that overrides honest evaluation of content.
generative-engine-optimization, answer-engine-optimization, ai-search, content-strategy, seo, blog-automation
GEO structures content so AI answer engines cite it directly. This post shares the research-backed rules we encoded, the two-pass blog automation tool we built to enforce them, and why the answer must always come first.
quantization, local-llms, small-models, ai-development
We shipped a 1.5B router that produced valid JSON 97% of the time. One quantization step took it to two. Here is the day we spent finding out why — and why the rules everyone repeats about quantization were written for models ten times the size. It started with a
training-data, prompt-engineering, local-llms, ai-development
We set out to teach a small model how to route developer prompts. The data taught us that our taxonomy — and our sources — encoded a picture of developers that doesn't exist. It started with a quota. I wanted a small, fast model that could sit in front of
generative-ai, ai-art, online-communities, data-analysis
A wallpaper, 7,700 views, 293 votes, and a question about how many of those votes belonged to people. It started with a wallpaper. I took the iconic Ultima Online splash art — the one every former player from the late nineties can still picture from memory — and asked Flux 2
coding-agents, open-source, business-models, ai-development
How a coding agent turned a capped open-source project into its full-featured paid equivalent in under two hours — and what that means for every company betting on artificial scarcity as a revenue model. It started with a monthly bill. I was evaluating a self-hosted communication platform — the
coding-agents, automation, n8n, developer-tools
How an MCP server turned a visual automation tool into something a developer can actually move fast with — and what that means for the way we build workflows. It started with a newsletter. Our AI think tank, AIpster, needed a daily digest: aggregate news from the best AI sources, summarize