The intersection of human cognition and machine intelligence
61 posts
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.
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.
Autonomous agents don't develop taste. They execute the taste someone was disciplined enough to write down. A worked example from a real pipeline.
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.
A department of a hundred writers documented mainframe billing programs. Every one of them had something else they'd rather be doing. They knew.
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.
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.
Stop accepting reports. Ask for the artifact — the actual numbers, the actual error, the actual file — and the confident-sounding failure disappears.
Arnold's most famous line is a Spanish phrase in an English-language film spoken in a thick Austrian accent. What it tells us about how language acquisition actually works — and how you can learn from his mistake.
AI is intelligence without a limbic system. It will operate your tools, not replace your judgment — and most professionals are bracing for the wrong loss.