You get exactly what you asked for. Not what you meant.

I watch people write prompts like they’re Googling something. A few keywords, a vague direction… Then they’re frustrated when the output is generic, wrong, or just weird.

But the model did exactly what you told it to do… and that’s the problem.

The old genie story works because the genie isn’t malicious… it’s literal. “I wish for a million bucks” and a million male deer appear in your yard. The genie did exactly what you asked it, you just didn’t think about your question.

LLMs operate on the same principle, minus the malice and the deer (usually). When you prompt “write me a marketing email,” you’ve described approximately four billion possible outputs. The model picks one. You hate it. You try again with the same vague prompt. You hate it differently. You conclude the tool doesn’t work.

The tool works fine. You made a genie wish.

What changes everything is realizing that prompt engineering isn’t about clever tricks or magic words (usually). It’s about the same skill that makes someone effective in any leadership role: the ability to articulate what you actually want with enough specificity that another intelligent entity can deliver it.

Tell it who it’s writing for. Tell it what tone. Tell it what success looks like and what failure looks like. Give it an example of something you loved and something you hated. Tell it what to leave out (the negative space is just as important as the positive).

In other words: do the work you should have been doing with your human teams all along.

The uncomfortable truth about prompt engineering is that it isn’t an AI skill. It’s a communication skill. The people who are bad at prompting are usually the same people who send their teams vague Slack messages and then get frustrated when the deliverable misses the mark.

The genie didn’t get it wrong. It followed the rules exactly.

I started writing this series because I needed to air my mind. A career in technology, nothing constant but change, and a compulsion to say something about what I was watching happen.

Ten essays later, this is the last one.

It’s called Dead Reckoning, and it’s about the difference between knowing how to use the instrument and knowing how to read the water when the instrument is incomplete. A Micronesian navigator named Mau Piailug sailed 2,500 miles without a compass in 1976 because he could do both. We’re building an entire industry around people who can only do one.

If you’ve been following along, thank you. If this is your first one, the bar’s been open for a while, and there’s a seat.

(Read, The Room Where It Gets Built — Essay #10: Dead Reckoning)
 

They were successful enough that Microsoft has built grammar checking into Word since 1992. Grammarly alone has 30 million daily users.

For forty years, the message has been clear: use the tools, improve your writing.

Now a student in Palo Alto is staring down a C on his transcript because an AI detector flagged his essay. His family submitted over a thousand pages of evidence… drafts, timestamps, full Google Doc revision history. The district’s response was “we can’t resolve this” so the student pays the price.

The detector’s own maker admits to a +/- 15% margin of error. Independent researchers have shown these tools flag non-native English speakers at higher rates (likely because they’re working harder to master the rules). Grammarly use alone can trigger a positive. I’ve seen it in my own tests!

But the problem goes deeper than bad tooling. AI writing models were trained on good human writing. They learned to mimic it. Which means the better you write (whether you use assistance tools or not) the more you look like a language model. If you’ve learned to write competent, clean, well-structured prose, you are now statistically indistinguishable from the thing we’re trying to detect.

The detectors aren’t broken. The premise is. We trained AI to write like skilled humans, then built tools to catch skilled humans writing like AI. That’s not a technology gap waiting to be closed. It’s a circle.

We either use the tools or we don’t. This half-a**ed middle ground where students, teachers, and families all get caught in the crossfire helps no one.

Data Has Black Holes Too: Why “hallucination” is the wrong word for AI’s deepest failure mode.

The AI industry calls every wrong answer a “hallucination.” That word is hiding a much bigger problem.

When a model fabricates a seahorse emoji, that’s obvious and fixable. When a model produces a confident, well-structured answer that’s wrong because of assumptions buried in the training data it was never designed to question, that’s something else entirely. That’s structural. And nobody’s talking about it in the right terms.

I fed the same degraded 1957 film image to three frontier models. All three independently produced WWII propaganda. The only correct result came after I supplied the actual movie context up front.

The new essay is about what’s really happening inside these systems, why your 500-word prompts are fighting a losing battle against gravity, and how to stop fighting the landscape and start navigating it.

(Read, The Room Where It Gets Built — Essay #9: Data Has Black Holes Too)
 

You walk into a store. The price tag makes no sense. “Who’s paying for this?!?”

Not you. The store did the math. They figured out they don’t need you. They don’t need ten of you. They need one of a different customer who pays sticker and doesn’t blink.

I wrote an essay about how this same dynamic is playing out across the entire hardware market and most people haven’t noticed. About what happens when data center equipment comes off cycle in three to five years. And about why even a flood of cheap enterprise surplus might not help you, because the consumer operating system is being redesigned to lock you out of it.

Thirty years of pattern recognition on this one.

(Read, The Room Where It Gets Built — Essay #6: You Are a Decimal Point)