Archive

Persona prompting generates the exact type of hallucination that automated LLM judges reward as 'depth.' Two experiments, blind evaluation, and a fact-check that flipped the finding.

What a company has already built tells you more than what they say they're about to build.

When you don't have enough information to narrow, stop narrowing.

The strongest slide in my interview deck wasn't about what I'd built. It was about how I built the deck itself.

Most people use AI like a tool. Here's what thinking with AI actually looks like — and the skills that make the difference.

The best guardrails work like river banks — they don't stop the water, they focus it. Constraints create capability.

AI agrees with you by design. That's great for creative flow and dangerous at the decision point. Know when to switch modes.

The companies that win with AI agents aren't deploying the most agents — they're redesigning their organisations to work with them.

A two-tier honesty framework: be honest by default, override only when truth would harm someone vulnerable.

If you could only keep one mental model, keep compounding. It applies to skills, reputation, writing, and tools.

Don't filter during capture. Capture is cheap. Ideas are expensive. The cull is where quality happens.

Event-driven hooks in AI coding tools aren't just for linting — they're programmable triggers for life routines, habits, and systems.

Rushing is a habit, not a response to reality. You break it by deliberately not rushing when you could.

The best time to improve a CLI isn't when it breaks — it's when you review the breakage log at the end of a work session.

Your AI already knows things that would make it better at helping you. The trick is extracting that knowledge and making it permanent.

How a real need on a Hong Kong bus turned into a GPS-powered alert system in under two hours

Independent parallel reviews produce overlapping findings. The cross-critique round produces resolution. That's where multi-agent value actually emerges.

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.