skip to content

Archive

AI controls, agent systems, banking governance, production practice. 409 essays, newest first.

  1. AI Controls Architecture

    Risk teams know risk. The open problem is designing controls for systems that are non-deterministic, probabilistic, and attackable in natural language.

  2. Governing Agents the Way Cells Govern Themselves

    Six cell biology mechanisms that reveal what the networking 'control plane' metaphor misses about governing AI agents.

  3. The Risk Without an Engineering Solution

    Every other agentic AI risk has an engineering answer. Prompt injection doesn't. That changes everything about how you design controls.

2026
  1. From Chatbots to Event Loops

    The shift from agents you summon to agents that watch. Enterprise AI workflows are becoming continuous loops — and the failure modes are different.

  2. What MCP Actually Changes for Enterprise AI

    Not better function calling — decoupling. When tools expose MCP servers, any agent can compose any system freely. The heterogeneity problem becomes a configuration problem.

  3. Language Is the Medium, Not the Purpose

    We called them language models and spent years confused about why they could reason. The name stuck to the interface, not the mechanism.

  4. LLMs Are Better at Editing Than Writing

    Ask an AI to write from scratch and you get the average of the corpus. Give it something rough and it amplifies what's already there. The workflow implications are significant.

  5. Consulting Is Mostly About Reducing Uncertainty

    Clients hire consultants to solve problems. What they're actually paying for is the reduction of a particular feeling. The distinction matters.

  6. The Case Against Knowledge Management Systems

    Most PKM tools are procrastination with better aesthetics. The problem isn't the software — it's that filing a note feels like understanding it.

  7. What It Actually Feels Like to Use AI for 80% of Your Work

    Not productivity. Something stranger — the cognitive texture of days when the bottleneck shifts from execution to articulation.

  8. When the Platform Is Mature, the Architect's Job Changes

    The hardest phase of AI architecture isn't building the stack. It's the moment after the stack is built and eighteen teams start making independent decisions on top of it.

  9. The Calibration Trap

    The comfort trap is about effort. This one is about epistemics — and it's harder to see.

  10. The Comfort Trap

    The right test for any AI interaction isn't 'did it help me?' but 'am I more capable after it?'

  11. The Personalised System Era

    AI coding agents didn't just make developers faster. They changed who gets to have a bespoke system.

  12. Let the OS Schedule, Let Your Tool Dispatch

    The moment I stopped building scheduling into my tools, everything got simpler.

  13. The Nag Tax

    When building automation around a third-party app, the first question to answer is: what's the one thing this app does that nothing else can replicate? That feature becomes the tax you pay on everything else.

  14. Benchmark Your Research Stack

    Running 10 real queries through 5 tools revealed that theoretical routing rules have systematic gaps — and the surprises were more useful than the confirmations.

  15. The Queue Should Live Where Your Thoughts Live

    AI agent results should be push, not pull. The feedback loop should close on mobile. Most tools miss all three — not from ignorance, but because dashboards photograph better.

  16. The Infra Trap

    Building tools to support your work can quietly become a substitute for the work itself.

  17. The Queue That Texts You Back

    Personal AI infrastructure should report results to you, not wait for you to go looking. A small architecture shift changes the whole dynamic.

  18. Eliminate the Reminder, Don't Schedule It

    When you catch yourself setting a reminder to check something later, that's usually a signal that a tool is failing to report what it should.

  19. Where Rules Live

    The difference between a rule that works and a rule that doesn't is usually not the content of the rule — it's where it lives.

  20. When Better Is Worse

    Upgrading to a more capable model made my tool sixty times slower. The lesson isn't about models — it's about the difference between capability and fit.

  21. The QDAP annuity trap: what the tax saving doesn't tell you

    Hong Kong's QDAP annuity is sold on a real tax benefit. But the HK$60K deduction cap is shared with MPF top-ups — and that changes everything.

  22. The Experiment Loop Without the GPU

    Andrej Karpathy's autoresearch project is being read as a demo of what H100s can do overnight. It's actually a discipline for doing rigorous work on anything measurable.

  23. Instructions Don't Enforce Behavior. Templates Do.

    Why the structure of an output matters more than the instructions that produce it.

  24. The Silent Stall: Debugging GPT-5.4-Pro's Responses API

    Three hours of debugging revealed two non-obvious behaviours about GPT-5.4-Pro that aren't in the docs: a minimum token budget requirement and a wall-clock timeout gap in Rust async code.

  25. I Didn't Mean to Kill My Todo App

    A coding assistant quietly made three productivity apps redundant. Not by replacing them — by making context collapse the boundaries between them.

  26. What it actually takes to run an AI agent in a bank

    The resistance to AI agents in banking isn't mostly cultural. It's infrastructure — and the gap is more interesting than the politics.

  27. AI Fixed My Perfectionism (Sort Of)

    On why the blank page stopped being the hard part.

  28. Exa Indexes WeChat

    WeChat is supposed to be a walled garden. Exa didn't get the memo.

  29. The Problem With Clever Browser Automation

    The most sophisticated solution to a problem is usually a sign you haven't found the right abstraction yet.