They say AI can be a godsend for cranking up productivity into the stratosphere. I say, it's like an enthusiastic pup. Fail to train it right and lo and behold, it's gnawing on your favorite sandals and tearing your content to shreds.
Now, I'll need you to keep a straight face for this part because I’m about to unveil a ridiculous oversight of mine. It turns out past prompts work like chew toys for generative AI.
Your AI pooch gets so fixated on the shiny old toy that it loses sight of the purebred task at hand. Should I have seen this coming? Absolutely. Did I? Not in a million years.
So, here I am, swallowing my pride. This is a PSA to save you from falling into the same trap. 👇🏽
A summary that took a detour
I asked AI to write a quick summary of an article. But I did it in a long chat full of fun ideas. Suddenly, I found myself scratching my head. Did the marketing article really talk about big meals and famous chefs? Nope. That was the AI taking a creative stroll and grabbing ideas from our chat history.
Eager to claw back my dignity, I tried my luck in a different chat. This one was about a job research task. And guess what? Now, the marketing article seemed to be about people who work for themselves.
W.W.R.D.?
- All that to say, keep old prompts from sending your AI on a wild squirrel chase. Be specific. Better yet, start a new chat for each task with a unique context.
About Susan Rov
Susan traded cocktails and lattes for words that move. As a copywriter on a mission to end boring, she brightens brands and makes an impact. Number 463 on the list of fiction readers left standing, you'll find Susan at sunrise—running, writing, and wondering how to change the world next. That drive led her to become a founding team member of BRIL.LA.