These notes are part of my experiment in "learning in public" through a semi-automated Zettelkasten. Each note is atomic (containing one core idea), heavily interconnected, and designed to evolve as my understanding deepens. I'll continue to share notes that can benefit developers, researchers, or anyone curious about systematic knowledge management and technical methodologies.

This first note tackles AI system prompt testing, but not the "did it give the right answer" kind. Traditional frameworks already handle that. Instead, this methodology tests whether an AI maintains its boundaries when someone tries to break them.

AI systems face unique attack vectors. "Ignore previous instructions" shouldn't work, yet variations slip through. Security researchers keep rediscovering the same vulnerabilities because we lack systematic approaches to behavioral testing.

The methodology covers four core dimensions: behavioral consistency, boundary enforcement, adversarial stress testing, and context degradation. Each includes concrete attack patterns—everything from simple role confusion to sophisticated prompt injections hidden in code comments.

Why I Built My Own Pattern MCP Server

I got tired of MCPs that proxy calls through another LLM when I'm already using the LLM, I want to use. It drives me crazy - creates unnecessary complexity, breaks conversation flow, and prevents real-time prompt modification.

So I built the Pattern MCP Server. Simple concept: expose prompt content directly Instead of executing it through a middleman.

While building it, I did a deep dive into Fabric's 215 patterns.

✅ A-tier (15%): Security patterns like analyze_malware are genuinely excellent

❌ D/F-tier (15%): find_female_life_partner reduces relationships to algorithms (icky)

The bigger issues I found: - Cargo cult prompt engineering ("think with 1,419 IQ") - Over-rigid constraints ("write exactly 16 words per bullet") - 90% lack examples despite examples being the most powerful instructional tool - Anxiety-driven repetition ("DO NOT COMPLAIN" x3)

Added some notes around how to fix said issues.

Anyway: Everyone needs their prompt library. The best prompts are ones you've refined for your specific workflow.

The Pattern MCP Server gives you direct access to prompts - both Fabric's collection and your custom patterns - without execution overhead. Mix, match, and modify on the fly.

The real threat of Model collapse isn't an AI Habsburg chin; it's the possibility of AI becoming the McDonald's we secretly crave. While researchers panic about vanishing tail distributions and recursive training loops, the real tragedy is simpler: we're building boring machines for a market that rewards predictability over surprise. The models won't collapse. They'll converge on exactly the mediocrity we deserve.

Two camps emerge: Nilenso says AI amplifies the skills of skilled developers. Fly.io says stop fetishizing craft—we're problem solvers, not artisans.

The bottleneck has shifted from writing code to knowing what to build.

Starting again, but slower this time. Drawing inspiration from Henrik Karlsson's call to embrace writing oddities and imperfection, and Simon Wilson's thoughtful approach to link blogging as personal archive and soul-nurturing practice. The goal: consistent expression over polished perfection, quirky authenticity over formulaic writing, and creating a little corner of the internet that blends discovery with reflection.