I have chat pre-prompted to always push back on me and challenge my assumptions. Today it gave me this lovely one-liner:

“But “easy” is doing a lot of work in that sentence, so I’m going to poke at it.”

Well, that was neat. I have a ClickUp integration that I use for an internal task system at Novatorius, but wanted something similar for Trello.

Claude Code just churned it out flawlessly, given the ClickUp example.

One of my favorite AI prompts to leverage ChatGPT to help me edit:

You’re an editor and you’re going to help me fine tune this post so I can get it published.

Let’s start with a chainsaw, then an axe, then a knife.

Hack away, move, and organize paragraphs with the chainsaw, Then cut at the individual paragraph level with an axe.

Then fine tune sentences with a knife.

Start with chainsaw.

Do not rewrite. Only make suggestions on things you think could be done better.

[Insert blog content]

Remember in th 2000s when we all developed “ad blindness?” That’s happening with AI content on social media right now.

We can all tell when something is lazily slipped out with AI, and because of the lack of effort and thought that went into it, people just skip over it.

If I wanted to talk to chatGPT, I would. But I’m on here to talk to YOU. So let me hear YOUR voice.

Your social profile should be you. Not a robot acting like you. All that does is water down your brand, and make your word less valuable, and noticed.

People: LLMs are simply predicting the right thing to say in response to you. They can’t think.

Me: Uh…isn’t that exactly what we do in conversation?