We shape our tools and thereafter our tools shape us. — Marshall McLuhan
AI has made software generation so cheap that an entire category is now born disposable — created for a single context, used once, and discarded when the moment passes.
Skills give AI a set of instructions to follow — and instructions can be ignored. This essay maps Anthropic's dynamic workflows against a real writing checklist, tracing six structural gains from determinism to reproducibility.
AI engineering has evolved through three compensatory phases (prompt, context, and harness), each addressing a failure the previous layer couldn't fix. Harness Engineering is the governance layer that keeps teams of agents coherent across complex, long-running tasks.
This essay argues that AI is reshaping software at an architectural level, moving from human-centered applications to a composable agentic ecosystem where CLIs, Skills, and MCP form distinct layers that agents invoke as primary users.
Why did developers abandon polished IDEs for a terminal tool? The answer is less about AI than about Unix: a 50-year-old design philosophy of composable text tools that proves to be the perfect substrate for machine intelligence, and a preview of the AUI paradigm ahead.
Claude Code and CoWork share a codebase but diverge sharply — local vs managed-VM execution shapes resumability, attachability, and autonomy.
Claude Cowork marks Anthropic's pivot from chatbot to agentic AI: a productized Claude Code that plans, executes, and delegates tasks through sub-agents in a sandboxed Micro-VM environment.
A historical analogy: today's LLMs are the steam engine of AI — celebrated as revolutionary, yet only half the architecture real superintelligence needs.
This article traces the evolution of Claude's Skills, Commands, and Agents, analyzing the fundamental tension between intent-matching intelligence and explicit-command reliability, and arguing that their merger points toward compositional AI behavior.
The Internet died once in 2000's dot-com crash, then was reborn solving unglamorous infrastructure problems. Today's AI boom mirrors that mania. The Internet's killer app wasn't information; it was social media. AI's likely won't be productivity either.
Reasoning in large language models is an important shift in artificial intelligence: from instant responses to deliberate problem-solving. How does the reasoning work? In what ways can this feature be implemented? What are its current limitations?
Four research papers suggest LLMs have layered internal states — and that 'alignment faking' and unfaithful reasoning are features of intelligence, not bugs.
The most consequential near-term use of voice AI is companionship, not productivity. AI companionship is rapidly emerging as a transformative force, reshaping human relationships by offering emotionally responsive, ever-present, and personalized virtual partners.
Where AI speech synthesis stands in early 2025: hands-on test results, and why realistic text-to-speech is already displacing professional voice talent.
Local Intelligence, an Important Step in the Future of MAD (Mass AI Deployment)
Could AI make learning genuinely fun? On using AI as a storyteller — with humor, characters, and tiny cats — to make complex ideas engaging for kids.
A 2024 primer on the technologies reshaping how we learn, framed by McLuhan's idea of media as extensions of man.
MindDraft is a next-generation writing app designed to transform the writing process into a fully collaborative experience.
Lean, UX, Clicking Buttons and Starting a Tesla
A 2011 essay placing handwriting on the iPad — 'tabwriting' — within the long history of writing technologies, from pen and paper to the keyboard.
How far have we gone to reproduce the human voice; are we there yet?
