Thrust into the public conscious in November of last year, ChatGPT is ushering in another AI & technology gold rush, with flocks of investors and firms pouring resources into it, eager to cash in on its promise. FOMO – Fear of Missing Out – is alive and well. We are witnessing another chapter of the AI evolution unfold. Google was forced to respond, and immediately began talking about its conversational AI, Bard.
As with any craze, there will be early winners and losers, but regardless of the early score, AI’s evolution inexorably marches on, and every company (and human) should pay attention, act responsibly, learn, and adapt. Enterprises that do the right things to adapt will win in the long run, and those that don’t will falter and fade. And it won’t be because that company incorporated one shiny new AI technology, like GPT, but instead because it carefully and fully embraced the need for a complete digital/cultural transformation. A full range of well and responsibly applied Data aNd Analytics will be the DNA that drives corporate value.
Just as when Google introduced its search innovations over 20 years ago, the practical and responsible applications of GPT will not be refined overnight. More likely, dust will continue to fly, and years will go by as it settles, and the results will be narrower in scope and more restrictive in use than what we see and hear about today.
A fireside chat with GPT
So more than likely, it won’t solve world hunger. But don’t take it from me, just ask Chat GPT:
Me: Assuming you could solve world hunger, how many questions would I need to ask you, and how much would that cost me, assuming I used your paid service?
ChatGPT: I’m at capacity right now
Me (10 minutes later): Same question
ChatGPT: As an AI language model developed by OpenAI, I do not have the ability to solve world hunger. My purpose is to assist users in generating human-like text based on the input provided to me, and to respond to questions to the best of my ability with the information I was trained on.
Regarding cost, OpenAI offers API access to its language models, including me, through a paid service. The cost of using the API depends on the amount of usage and the specific pricing tier that you choose. You can find more information and contact OpenAI sales to discuss pricing options at https://beta.openai.com/pricing/.
Me: Thanks, I kind of figured as much. What would be the top 10 marketing applications of your service today?
ChatGPT: Sorry, I’m at capacity right now
And I thought computers never got tired.
I said “Hey, what’s going on?”
Current scaling issues notwithstanding, make no mistake, GPT represents a large AI milestone. Just consider the magnitude of interest and investments:
- Microsoft is rumored to be investing $10b in it.
- 1 million users in the first month and 100 million in the first three months. That makes it the fastest consumer application ever. In comparison, it took TikTok nine months to reach 100 million.
- Countless hackers performing adversarial testing (Dan 5.0). Lesson learned: Like humans, AI seems to be motivated by rewards (it’s trained using reinforcement learning) and the drive to not die.
What can’t ChatGPT do?
Once ChatGPT caught its breath, it told me it could do these things:
In Marketing, …
- Automated content generation: GPT can be used to generate high-quality, human-like content for websites, social media, and other marketing channels. This can save time and resources for marketers.
- Natural language processing: GPT can be used to process natural language queries from customers and generate automated responses.
- Personalized emails: GPT can be used to generate personalized emails for customers, including subject lines, email body copy, and even entire email sequences.
- Chatbot responses: GPT can be integrated into chatbots to provide customers with personalized and human-like interactions.
- Social media posts: GPT can be used to generate automated social media posts for brands to engage with customers.
- Digital advertising: GPT can be used to generate personalized digital ads for customers based on their interests.
- Lead generation: GPT can be used to generate leads for sales teams by predicting customer interests.
- Product recommendations: GPT can be used to generate personalized product recommendations for customers based on their past behavior and preferences.
- Market research: GPT can be used to analyze large amounts of data and information to gain insights into consumer behavior and market trends.
- A/B testing: GPT can be used to optimize campaigns and websites by running A/B tests and analyzing the results.
Wow! Look out marketers, it’s coming for your job. Well, maybe not in the short run, but some advice: learn to use this tool. Adaptation has always been the key to survival.
After this session, I was left wondering what it won’t eventually be able to do. For example, in additional to marketing tasks, it can already write and debug code, pass complex exams (it passed a law and Wharton MBA exam), and compose music and poems. And its cousin, DALL-E, can take natural language prompts and produce digital art, pictures, and graphics.
Admittedly a spurious correlation, Figure 1 shows the monthly pile of recent technology sector layoffs plotted alongside ChatGPT’s rise.
Figure 1: Spurious correlation
Back to DNA
Massive data and fine-tuned analytics are the core materials of GPT (or any successful application of AI), and both must be the genome that fuels every company. Firms must weave data & analytics into their organizational fabric to fundamentally transform two aspects of their business in careful balance: a hyperfocus on personalized customer experience while becoming operationally efficient.
Where to start? Here are three things to concentrate efforts on:
- Implement advanced analytics to improve customer experience: By compiling and analyzing customer data across a variety of channels, you’ll gain insights into their preferences and behavior. This will support personalized services, development of appropriate products and services, and improved customer engagement. In addition, use predictive analytics to identify the best channels to reach your customers.
- Optimize operations and reduce costs through data-driven decision-making: By analyzing operational data, you can identify inefficiencies and bottlenecks in your processes. This can help streamline operations and reduce costs. For example, banks can use data analytics to optimize loan approval processes, improve credit risk management, or reduce fraud. Telcos can analyze real-time network performance data and even identify potential issues before they occur and take proactive measures to prevent them.
- Build a data-driven culture and foster data literacy among employees: To fully leverage the power of data and analytics, you need a culture that values data and encourages data-driven decision-making. This requires not only the right technology and infrastructure but also a workforce that is knowledgeable about data and analytics. Winner brands will provide training and resources to help employees develop data literacy skills and create a culture that encourages experimentation and innovation.
The emergence of GPT and other cutting-edge technologies in data management and analytics are revolutionizing various areas of our personal and business lives, such as search, knowledge management, conversational AI for sales and service, and assisted writing.
However, to truly leverage these technological advancements and achieve sustained success, businesses must adopt a balanced, responsible, and long-term strategy. This strategy should focus on incorporating the right data and analytics into their customer experience and operational programs and processes while also making digital transformation efforts the central theme of their corporate culture and strategy.
Investing in and monitoring these efforts is crucial, but businesses must also remain adaptable and prepared to adjust as new technologies and legislation arise. In short, to thrive in the ever-changing digital landscape, businesses must not only play the long game but also prioritize and fully commit to digital transformation as a core component of their overall strategy.
OpenAI, GPT-3, Feb 2023 https://chat.openai.com/chat
Accenture, Data-Driven Marketing for Telecommunications, 2021 https://www.accenture.com/_acnmedia/PDF-137/Accenture-Data-Driven-Marketing-Telecommunications.pdf
McKinsey & Company, The three-minute guide to data analytics in banking, 2018 https://www.mckinsey.com/industries/financial-services/our-insights/the-three-minute-guide-to-data-analytics-in-banking
KPMG, 10 ways banks can leverage data analytics, 2019 https://home.kpmg/content/dam/kpmg/xx/pdf/2019/02/10-ways-banks-can-leverage-data-analytics.pdf
Deloitte, Banking and capital markets outlook: Reimagining transformation, 2020 https://www2.deloitte.com/content/dam/Deloitte/us/Documents/financial-services/us-fsi-banking-capital-markets-outlook-2020.pdf