What if we’re doing it wrong?

It wasn't until our second kid that I realized I’d been doing it wrong. For years.

Through dozens of blowouts. I’d been pulling poopy onesies over screaming heads at 2am. The hard way. Straight up. Praying not to bump their face on the messy spot. And then, BAM: mid-blowout with kid number two, I actually looked at the shoulders. Those little flaps aren’t fashion. They help the onesie come off down the body instead of over the head.
Instant facepalm.

Same thing with AI. Little facepalms everywhere.

Here's where many people are still forcing a poopy shirt over the head:

We ask one question, read the answer, and log off. Trevin Shirley found the average length of 13,000 ChatGPT chats was 1.7 messages. Like we’re asking Jeeves in 2001. The whole value comes after the first reply. Iteration gets you thinking. One-and-done get you a chatty search bar.

We ask for the answer instead of the thinking. "What should I do about X?" gets a recommendation. "Walk me through the tradeoffs on X" gets you something you can actually use and help you find problems you never typed in. One outsources judgment. The other sharpens it.

We over-engineer the prompt. Architecting three perfect paragraphs of tone, format, and constraints. Trying to think through every angle first. The better move is gardening: Plant something rough, see what grows, then prune it back. 

Don’t force screaming heads through poopy holes.
Keep on the lookout for shoulder flaps.