by scottfalconer on 4/22/2025, 5:28:54 PM with 1 comments
I see at least one email or LinkedIn post a day that screams "written by AI".
Using AI is fine, but if there’s no human fingerprint I drift off midway...same reaction as if I realize a cool photo is a fake.
Why do we spot the bot voice so fast?
* We riff off our audience. Models average everyone.
* Real people leave fingerprints...jokes that land, typos that don’t.
* Polished‑generic prose feels like a local news anchor gate‑crashing your group chat.
How I keep drafts human:
1. Spell out who's talking and why. "Support rep, one frustrated customer."
2. Paste the customer’s actual rant. Makes the model sweat.
3. Drop a paragraph in my voice, ask it to revise. Works better than rules.
4. Crank temperature a notch, then chop anything weird.
5. Read it aloud. If it sounds like corporate wallpaper, I rough it upswap a comma for an em dash, toss in a "whoops."
That’s my routine. What’s yours? I’m collecting tricks so my inbox stops looking like office ceiling drop in tiles.
Why do we spot the bot voice so fast?
* We riff off our audience. Models average everyone.
* Real people leave fingerprints...jokes that land, typos that don’t.
* Polished‑generic prose feels like a local news anchor gate‑crashing your group chat.
How I keep drafts human:
1. Spell out who's talking and why. "Support rep, one frustrated customer."
2. Paste the customer’s actual rant. Makes the model sweat. 3. Drop a paragraph in my voice, ask it to revise. Works better than rules.
4. Crank temperature a notch, then chop anything weird.
5. Read it aloud. If it sounds like corporate wallpaper, I rough it upswap a comma for an em dash, toss in a "whoops."
That’s my routine. What’s yours? I’m collecting tricks so my inbox stops looking like office ceiling drop in tiles.