ChatGPT is fun, but will it replace programmers (and marketers)?
Since the rapid ascension of ChatGPT, an artificial-intelligence (AI) chatbot developed by OpenAI, some are predicting that in about five years, an unemployed human race will be staring back at a sentient, ChatGPT-powered robot army that is ready to shed its mammalian overlords. Others predict that these same robots might eventually ‘liberate’ us from our jobs as we ring in the 0-day work week, introduce a universal basic income, and edge closer to a Star Trek-like world where human subsistence is no longer a concern.
In the meantime, cooler heads are advising that we not panic about widespread job losses and economic upheaval being presaged by AI pessimists. On the contrary, AI-powered tools like ChatGPT could very well help us augment the nature of human work by automating the tedious and repetitive aspects of our jobs, allowing us to focus on more creative work.
“While the launch of large language models such as ChatGPT, the premium service ChatGPT Plus and the enhanced GitHub Copilot have resulted in headlines about jobs that are at risk of being replaced by AI (with programmers at the top of some lists), the question of how real the threat is, and how the potentially displaced adapt, is very open at the moment as it is early days in the evolution of the tools,” says Shane Hastie, InfoQ’s Lead Editor and Podcast Host for Culture & Methods, in a recent InfoQ report.
Even in these early days however, AI-technology has already become an integral part of developer tooling, increasing overall productivity by handling many of the mundane tasks related to coding, debugging, and even monitoring (AIOps), freeing developers up to focus on the more creative aspects of software engineering.
“Based on our research, programmers spend 35% of their time on understanding code, 5% on writing code, 10% on other coding-related activities, and 50% on other non-coding activities,” says Nikita Povarov, Data Analytics and Machine Learning Team Lead at Jetbrains. “Helping programmers perform small tasks more efficiently is a vast area for AI usage: AI can help to complete the code, to teach the user to utilize new features, and to search in the code and beyond.”
But can tools like ChatGPT ultimately take over the entire task of creating complex software systems, thereby replacing the need for programmers? We decided to ask ChatGPT what it’s true intentions are:
“ChatGPT is not intended to replace programmers. While ChatGPT is capable of generating code snippets, it is not a full-fledged programming language and cannot create complex software systems or solve programming problems on its own.
Programmers are still essential in the development of software and technology. They have the ability to think critically, understand business needs, design software architecture, and write efficient and secure code.
ChatGPT, on the other hand, can assist programmers by suggesting code snippets, helping with syntax and language-specific knowledge, and even identifying potential bugs in the code. However, it cannot replace the human creativity and problem-solving skills that are necessary in software development.”
(Response from ChatGPT when asked “Will ChatGPT replace programmers?”)
A Brave New (AI) World for Marketers
Surely, if AI-powered tools like ChatGPT can augment ‘thinking-type’ work like programming, the opportunities for marketing professionals are limitless.
For B2B marketers in particular, lead nurturing is an important part of the pipeline building process. We decided to ask ChatGPT how it can help on this front:
“Overall, ChatGPT can help improve lead nurturing by providing personalized, timely, and automated responses that improve the customer experience and increase the chances of conversion:
Personalization: ChatGPT can be used to create personalized content and messaging that speaks directly to the needs and interests of each lead. By analyzing data on the lead's behavior and preferences, ChatGPT can generate messages that are tailored to their specific interests and pain points.
Timely Follow-Up: ChatGPT can be used to send timely follow-up messages to leads based on their actions and behavior. For example, if a lead downloads a whitepaper, ChatGPT can send a follow-up email with additional resources on the same topic.
Automated Responses: ChatGPT can be used to respond to leads automatically, even outside of business hours. By using ChatGPT to answer common questions and provide basic information, leads can receive immediate responses, improving their experience and increasing the chances of conversion.
Qualification: ChatGPT can be used to qualify leads by asking questions and collecting information about their needs and interests. This information can then be used to prioritize leads and provide more personalized and relevant content.
Lead Scoring: ChatGPT can be used to assign scores to leads based on their behavior and engagement with marketing materials. This can help sales teams prioritize leads based on their likelihood to convert, allowing them to focus on the most promising opportunities.
By using ChatGPT to analyze data and automate responses, B2B marketers can spend more time focusing on high-value activities, such as developing relationships and closing deals.”
(Response from ChatGPT when asked: “How can ChatGPT improve lead nurturing?”)
Looking Forward
“The companies working on software development tools are quickly developing the ability to productize AI-powered solutions for small tasks, so we expect more such solutions to emerge in the near future,” says Povarov.
“Computers can now write code, but we don’t see this as an industry transformation. The ability to write code is not sufficient to replace a human programmer. It turns out that the ability to consider complex interactions of software components is critical, and AI is not there yet,” he adds.
In the sales and marketing domains too, AI cannot replace the much needed skills of developing customer empathy, storytelling, and adding context to the cold, hard metrics that our systems generate.