Sir
How you configure your AI assistant — what you make it call you — says nothing about the AI. It's a bumper sticker. You're the truck owner.
Human-Machine Synthesis
The intersection of human cognition and machine intelligence
63 posts
I Taught an AI to Write Like Me. Now It's Teaching Me.
I built an AI skill to write in my voice. Its own files warn the voice may be a loop — the machine's habits, published under my name, taught back as mine.
Why You Should Ask How Before You Ask a Model to Do the Job
Before you ask a model to do the job, ask how it would do the job. You find out what it misunderstood, what it was about to assume, and occasionally that it knows a better route than the one you had in mind.
Honestly
LLMs say "honestly" most where they're most likely to confabulate. Here's the mechanism — and why it backfires exactly like a sociopath's professions.
I Know It When I See It
Autonomous agents don't develop taste. They execute the taste someone was disciplined enough to write down. A worked example from a real pipeline.
Why AI Gives You a Different Answer When You're Angry
Losing your temper at a model does not produce a worse version of the same answer. It produces a different kind of answer — one built to end the argument rather than solve the problem.
What You Had to Do
A department of a hundred writers documented mainframe billing programs. Every one of them had something else they'd rather be doing. They knew.
The Bewilderment Test
Karpathy built the foundations of modern AI and says he can't keep up with it. That's the most credible signal the field has produced.
Why Your AI Can't Add (And the Tool That Fixes It)
If you would reach for a calculator, tell the model to reach for one too. It cannot add reliably and it can write a formula that adds perfectly — and you get to keep the formula.
Why You Should Always Ask for the File
Stop accepting reports. Ask for the artifact — the actual numbers, the actual error, the actual file — and the confident-sounding failure disappears.