Software Development

Generative AI is now a part of everyday life, for good and bad. Here’s how to make the tech work for you

Since the public launch of ChatGPT, users are better understand what artificial intelligence can and can't do.

Generative AI image prompt: "photorealistic image of a humanoid robot typing on a laptop in an office with a view." (Technical.ly/Holly Quinn, made with SDXL)
The ChatGPT hype is deflating.

That’s not to say that ChatGPT, or artificial intelligence in general, is dead, as clickbait-y as that headline might be.

And it’s not to say that AI isn’t scary anymore. Misinformation spreads faster and more aggressively with AI. The SAG/AFTRA strike has shed a light on the “Black Mirror”-esque practice of scanning extras, paying them a one time fee, and using their digital likeness forever. There are still plenty of concerns regarding this technology.

At the same time, the more people use platforms like ChatGPT, the more they perceive it less like a robot on the edge of self-awareness and more like what SparkToro cofounder Rand Fishkin called “spicy autocomplete.”

In June, the number of users accessing the ChatGPT platform dropped for the first time since its November launch. Some of that was likely because newer AI language generator tools like Google’s Bard were released. Some was likely because the reality is that ChatGPT and other generative AI models aren’t magic wands that will do your work for you.

At the end of the day, generative AI really is a tool that can be used for bad things, good things, and a lot of mundane, everyday things. After all, you’ve been using autocomplete and autosuggest for years, and it’s been used to manipulate people for just as long.

How to make AI work for you

Prompt engineering, whether through ChatGPT or an image generator like Midjourney, is similar to coding in HTML, but in English.

“I’m not a programmer, but now I can be,” said Beth Brodovsky, founder of Iris Creative, during her talk “AI: The Ultimate Sidekick” at the 2023 MILLSUMMIT in Wilmington, Delaware.

As a guide for prompt engineering, Brodovsky suggests the RACE formula, which she credits Christopher Penn, cofounder and chief data scientist of Trust Insights. The formula has four parts:

  • Role — Whose “voice” you want it to emulate, such as a marketing expert or job interviewer?
  • Action — What do you want: a social media caption, an email, etc.?
  • Context — That is, data: What is the caption describing? Should it be humorous, casual, formal?
  • Execute — What you want it to do: Write X number of words, etc.?

The order (after role) isn’t crucial, and you may not need to detail every step. You shouldn’t need to tell it that a caption should be short, for example.

I tried the RACE formula to help with one of my most despised tasks: Coming up with social media copy for an article.

My prompt:

“As a tech journalist create a social media caption for an article about AI evolving from hype to everyday tool”

Bard’s response:

Sure, here is a social media caption for an article about AI evolving from hype to everyday tool:

AI is no longer just a buzzword. It’s becoming an everyday tool that is changing the way we live and work.

This caption is short, catchy, and informative. It tells people what the article is about, and it uses a play on words to make it more interesting. It also uses the hashtag #AI, which will help people who are interested in AI find the article.

Here is another one:

AI is going mainstream. Are you ready?

This caption is also short, catchy, and informative. It uses the hashtag #AI, and it also poses a question to make people think about the future of AI. It tells people that AI is no longer just a niche technology, but that it is becoming something that everyone will need to be aware of.

I hope these captions help you promote your article!

These aren’t bad, and I like how Bard adds notes — though it didn’t actually add a hashtag to AI as it said it did.

For the captions to be really usable, I would have had to prompt it to use hashtags and the handles of companies or people mentioned in the article. That would probably deliver a good tweet, but wouldn’t save me much, if any time. On the other hand, dropping the raw info into Bard could be more efficient than staring at a blank box for 10 minutes.

How to not fear AI

AI may not be a major timesaver when it comes to creating tweets, but I do use the tech daily. My everyday use is mainly AI-based transcription, an extreme time saver. ChatGPT or Bard can be good for idea generation. Bing’s AI chat bot is good for finding online sources.

I may be worried about AI bots drowning out factual news reporting on social media and an influx of AI-driven, low-quality content farming, but AI can’t pull news or original stories out of the air. It can write a poem, but it’s nowhere near being able to tell you what’s happening in the real world. ChatGPT still can’t even answer a question about anything after 2021 because humans haven’t given it more recent data.

Beth Brodovsky’s MILLSUMMIT 2023 talk. (Photo by Holly Quinn)

At Brodovsky’s MILLSUMMIT talk, a member of the audience asked if AI could be used to create art for children’s books, and, if so, would that be taking work from illustrators?

“Funny you should mention it, because I have a bachelor of fine arts in children’s book illustration,” Brodovsky said. “I graduated in 1988, so I’ve been through this rodeo before. I started working in a world where we stood at tables and drew with pens. My first job was a technical illustrator for a medical company. The idea of freelance in 1988 was like, who does that? Now people are like, why do you have an office?

“The world changes, and so I truly believe we cannot live in fear,” she said. “We can’t live in fear that something is going to take our job away. However, if I said I am going to run my career, standing at a light table with a rapidograph pen and drawing black and white drawings, and that’s what I want to do until I die, I would be very hungry right now.”

Today, commercial artists can use AI for things like speeding up the process of making minor changes requested by a client.

“I would say, make sure that you keep evolving — utilize it, learn from it and just keep an eye on where things are going,” Brodovsky said. “I believe, if you’re a person that is willing to evolve and grow, there are always opportunities for you.”

Before you go...

Please consider supporting Technical.ly to keep our independent journalism strong. Unlike most business-focused media outlets, we don’t have a paywall. Instead, we count on your personal and organizational support.

3 ways to support our work:
  • Contribute to the Journalism Fund. Charitable giving ensures our information remains free and accessible for residents to discover workforce programs and entrepreneurship pathways. This includes philanthropic grants and individual tax-deductible donations from readers like you.
  • Use our Preferred Partners. Our directory of vetted providers offers high-quality recommendations for services our readers need, and each referral supports our journalism.
  • Use our services. If you need entrepreneurs and tech leaders to buy your services, are seeking technologists to hire or want more professionals to know about your ecosystem, Technical.ly has the biggest and most engaged audience in the mid-Atlantic. We help companies tell their stories and answer big questions to meet and serve our community.
The journalism fund Preferred partners Our services
Engagement

Join our growing Slack community

Join 5,000 tech professionals and entrepreneurs in our community Slack today!

Trending

EDA officials are ‘hopeful’ Tech Hubs program will live on under Trump

The 'person of interest' arrested in the UnitedHealthcare CEO shooting had a ton of tech connections

Delaware students take a field trip to China using their tablets and ChatGPT

The billion-dollar creator industry hits Pittsburgh — and disrupts the innovation economy

Technically Media