The explosive growth that we’ve seen from AI in the past few weeks is absolutely unprecedented, but just about everybody is using it wrong.
Tech business is prone to hype-cycles where the latest app/trend/platform gets blown out of proportion, dominating all of the attention and headlines for a short period of time until it all comes crashing down when our collective attention moves onto the next hot new thing.
This cycle is different for a few important reasons:
- It is, quite literally, the fastest growing technology of all time (see below)
- The developer community has just barely started building more applications, interfaces, and use cases on top
- We have only scratched the surface of how it can be used
That third point became shockingly clear to us this week, as we’ve been consuming content from every reputable source of tech information we can find about how AI is going to change the way that we all work. Here are just a few of the best that we’d recommend checking out (start from the top):
- Hard Fork Podcast featuring OpenAI founder Sam Altman
- TechCrunch article: Hands-on with Bing’s new ChatGPT-like features
- The Daily Podcast: The Online Search Wars
- The All-In Podcast: The AI Search Wars
The general consensus, at least among the sources we’ve seen so far, is that the tools are fun, interesting, far from perfect, and only somewhat better than traditional search. I felt like that last point missed out on the real magic that’s happening here – that this isn’t an incrementally better search engine, it’s a radically new tool that can be used to do real work and help us to solve real problems.
Then, I came across a tweet that perfectly illustrated that idea:
In the writer shared how, in just 4 prompts, they were able to create an entire SWOT analysis of agriculture that compared the use of AI in agriculture between the US and China, and it even placed all of the findings in a neatly organized table. For reference, a report like that may take a typical consultant days of research and analysis to produce.
Given that we are a consulting firm, you may think that the example would make us nervous, but instead we wanted to try it our for ourselves. So, in a recorded lesson for eLearningU (our tourism digital marketing education platform) I put together a series of tasks and plans that a hotel marketing manager would typically need to complete, including the following:
- What are a few content marketing ideas for a small hotel that’s looking to attract families on vacation?
- Based on those content ideas, develop a content calendar for the month of March 2023 that would require no more than 10 hours per week to complete
- That same hotel is going to launch surfing lessons in May 2023, create a digital marketing campaign that it could run to attract guests that will cost no more than $5,000
- Write an email newsletter that announces our hotel’s new surfing lessons that could be used to attract new customers
- The restaurant at our hotel is going to be offering cooking classes, what are a few blog post ideas that we could write that would be likely to attract search engine traffic?
- Create an SEO checklist that I can follow to make sure that my blog posts get the best possible rankings in Google’s results
The AI bot nailed the answers to each question, and in just a few minutes we had not only a series of useful content ideas, but a budget for a marketing campaign and a step-by-step task list we could use to publish blog posts that will rank in search.
Were the ideas creatively ground breaking? Of course not, but they were as good or better than most of what we’ve seen marketers spend weeks building, and it took less than 10 minutes.
The final question we put to ChatGPT may have produced the most helpful result:
What is one piece of advice you would give to a marketing professional about working with ChatGPT?
“Take the time to understand how ChatGPT works and how it can be best leveraged for your specific marketing goals. ChatGPT is a complex system that requires some technical understanding, so it’s important to familiarize yourself with its capabilities and limitations before diving in.
Additionally, it’s important to remember that ChatGPT is a machine learning model that learns from the data it is trained on. So, if you want to get the best results from ChatGPT, you need to provide it with high-quality input data and carefully curate the responses it generates.
Finally, keep in mind that ChatGPT is not a replacement for human creativity and expertise. While it can be a powerful tool for generating content and insights, it still requires human oversight and input to ensure that the content it generates is on-brand and effective.”
I’m leaving the experiment more confident than ever that this tool is going to give those who embrace it abilities that would have seemed like super powers only months before. I’m equally confident that it will only truly be effective when paired with human creativity and insights (at least for now).
Our advice for anyone thinking about how ChatGPT can be used in their own work is to understand that this is not a better search engine, the way that everyone seems to be saying. Instead, it’s a fundamentally different way of gathering information. It can, and should, be used to take care of the mindless parts of our work, freeing us up to do what we are best suited for, which is creative thinking and novel solutions.