Michael B. Halvorsen's Blog

Part 6 of 6 — The Corvue Thesis Series The final installment.

Part 5 of 6 — The Corvue Thesis Series New installments every Tuesday.

Part 4 of 6 — The Corvue Thesis Series New installments every Tuesday.

Part 3 of 6 — The Corvue Thesis Series New installments every Tuesday.

Part 2 of 6 — The Corvue Thesis Series New installments every Tuesday.

Part 1 of 6 — The Corvue Thesis Series New installments every Tuesday.

I went to bed with an idea.

One year after Andrej Karpathy coined "vibe coding," the real shift isn't about code at all.

What if I told you I've been programming for the last year—handling complex workflows, processing massive-scale AI operations, shipping production systems—and the orchestration layer isn't traditional code—it's English, written as markdown?

If you've been using AI tools like ChatGPT, Claude, or Gemini, you've probably wondered: does it matter what language I prompt in?

Having spent decades in software development, I'm seeing something unprecedented: AI isn't just another feature to add - it's forcing us to fundamentally rethink how we build software.

Anyone working with AI systems knows the frustration: your AI hits a limitation, fails silently, and you're left debugging in the dark.

If you've worked with AI language models, you've experienced it: the confident answer that's completely fabricated.