Independent Research
Experiments with real numbers. Agentic systems, strategy, and engineering craft. Honest findings, full limitations — for engineers and leaders shipping AI.
Research
11 posts
Real experiments with numbers. Benchmarks, security tests, and RAG evaluations on open-source models.
Strategy
9 posts
How to think about AI at the org level. Architecture decisions, build vs buy, adoption patterns.
Craft
3 posts
Concrete engineering. Patterns, code, and the non-obvious decisions that separate good AI from great.
Recent
The dominant pattern — check the role, grant the tool — works for API gateways. It breaks down in real business processes, where what an agent is allowed to do depends on which step it's on, not just who it is. The gap is known; adoption of the fix isn't.
StrategyMIT studied enterprise AI pilots. 95% delivered no measurable business impact. The cause wasn't model capability — it was integration gaps and governance gaps. Here's the architecture that fixes it.
StrategyAt Build 2026, the Microsoft AI team led by Mustafa Suleyman announced the MAI model family: 7 models covering reasoning, coding, images, voice, and transcription — every one built entirely in-house.
CraftDumping your notes into an LLM context is easy. Giving an AI agent structured, safe, scoped access to a living knowledge graph is not. Here's the architecture I built.
ExperimentI wanted AI that runs with no internet and keeps everything private. No API keys, no cloud, no data leaving the machine. So I built it in Rust using llama.cpp. Here's what that actually looks like.
ExperimentGemma 3 1B has 1152 dimensions. Gemma 3 4B has 2560. They speak different sizes. I trained a single layer to translate between them and logged every number.
Stay current
One email per post. Real findings, honest limitations. No roundups, no sponsorships.
Suggest something to test. If it’s interesting, I’ll run it and publish the results.