Writing

Why the thinkers who make you feel like hard questions are resolved deserve the most scrutiny.

LangGraph is the SAP of agent orchestration — powerful at scale, overkill for most. Here's the line.

Most AI workflows are parallel-then-aggregate, not agent graphs. Knowing the difference saves you from framework theatre.

Why 'you are an expert' is the most popular and least useful prompt engineering technique

A 3-pass AI planning pipeline caught 0 out of 6 design issues. The same planning done in-session with tool access caught 2.5. Planning isn't a prompt problem — it's a tools problem.

Not tools that search your notes — personalities that live in them, form opinions, and disagree with each other.

Documenting a rule is half a loop. The rule only works when it fires at the moment of decision — not when it sits in a file nobody reads.

A calculator doesn't simulate forgetting — it manages its context budget. What to cherry-pick from cognitive science for AI agent memory, and what to leave behind.

Most LLM pipelines don't need agents. The ones that do share a specific pattern — the step needs to decide what to do next, not just process what it's given.

I benchmarked 10 memory backends and multiple embedding models on actual agent memory retrieval. The results challenge common assumptions about what matters.

DeepSeek V4 launching on Huawei Ascend NPUs signals that China's AI ecosystem is decoupling at the silicon layer — deeper and more durable than model-level divergence.

The DoD-Anthropic dispute reveals a new category of operational risk: foundation model vendors can unilaterally revoke access based on their own values, not just SLA violations.

MAS, PBOC, and HKMA are independently arriving at similar AI governance requirements. Banks regulated by all three have a narrow window to build one superset framework instead of three silos.

Agentic AI isn't a future governance problem — it arrived ungoverned, and this week saw the first enforcement action.

Agent memory isn't knowledge management. It's performance infrastructure — and the gap between a stateless agent and one that accumulates context is measurable.

Enterprise AI keeps promising to capture institutional knowledge. The most valuable kind resists capture by design.

I built an AI landscape intelligence pipeline for zero marginal cost. Here's what it does and what it can't.

The scarce AI skill isn't building — it's knowing if what you built actually works.

Which parts of an AI dev workflow can be wrapped in a CLI, and which can't — learned the hard way by building the wrong thing and measuring it.

The debate about AI agent autonomy is wrong. It's not a binary choice — it's a graduated trust system with observability.

AI can reproduce smart arguments on demand. I'm not sure that's different from thinking. But the uncertainty itself is worth sitting with.

The people who examine the system they're inside tend to make better decisions within it.

After a decade in financial services, I've stopped believing that what you earn reflects what you contribute.

I use AI every day. I genuinely can't tell if it understands anything. That question is harder than it looks.

I work in AI in financial services. The honest list of where gen AI is real is shorter than the industry wants you to think.

Supporting a family in a system you see clearly isn't selling out. It's the most honest position there is.

My career looks like a plan in retrospect. It wasn't. It was a series of pushes, wrong calls, and adjustments.

The most successful piece of propaganda in modern economics is the idea that what you earn is what you deserve.

People confuse the LLM with the helpful AI assistant. They're not the same thing. The LLM is a prediction engine. The assistant is a role it's playing. The distinction changes how you use it.

An LLM can't feel accountability pressure. But structured role-play — simulated rejection, persona assignment, adversarial review — produces measurably better output. The mechanism is opaque; the effect is real.