What is BAD vs. GOOD AI judgement?
Would love to hear thoughts.
Here's my perspective.
I'm against AI slop, but I'm not against AI. I believe AI is a great tool but it also needs greats pilots to use it well. This is what I'm working on. AI Fluency.
Biggest marker of AI fluency is AI judgement. Where and when to use AI and where and when not to.
BAD AI JUDGEMENT
AI avatar job interviews. A robot face asks you scripted questions and scores your vibe. No human in the loop. You're not being interviewed — you're being processed.
AI-generated "thought leadership." Copy, paste, post. Zero lived experience, zero original thought. It's just AI slop in a blazer.
AI-written emails to people who matter. Your client can tell. Not because the grammar's off — because the warmth is.
VS
GOOD AI JUDGEMENT
Using AI to actually look at what a candidate did. Not keyword-matching a CV — pulling apart their portfolio, cross-referencing their claims. You still decide. You just decide better.
Using AI to draft, then making it yours. AI beats the blank page. But the final thing sounds like you and says only what you'd stand behind.
Using AI to poke holes in your own plan. Feed it your strategy and ask it to break it. Not to decide for you — to make sure you're not being lazy.
What do you think?
Replies
Avoid using AI to support creative projects, but not to do the creative work and replace the creatives themselves. It can go horribly wong!
AISA (aisa.to) AI Fluency Assessment
@peter_jenkins1 Can't say I fully agree with that statement I'm afraid Peter. AI can absolutely, and beautifully, be used to "support" creative projects.
Creatives need to adopt to thinking in a world where AI is the norm. We had 3 years to catch up to this idea now.
@ozandag Hey Ozan! I completely messed up my comment. I mean to suggest use AI to support creative projects, but avoid using it to do the creative work itself! Doh!
Some of the marketing materials I've seen where they use AI instead of graphic designers is absolutely awful.
Dial
One I'd add, from actually running scheduled agents unattended: bad AI judgement is letting it run autonomously somewhere you have no cheap way to check the result afterward. Good judgement is running it unattended specifically where verification is cheap and fast, even if you can't watch it happen live. I let mine post comments on a schedule with no per-action review, but only because I can check afterward, in seconds, whether the comment actually went live. I would not extend that same trust to anything where checking the outcome costs more than doing the task myself.