Interview: We asked a chatbot what it thinks about chatbots

We interviewed ChatGPT, the text-based chatbot taking the internet by storm, about the future of artificial intelligence (AI) in banking and finance

Automated customer service tools – or ‘chatbots’ – are having a significant impact on the delivery of customer service, particularly within banking and finance. Yet they create such drastic transformation that they require whole industries to adapt.

What better way to gauge the state of chatbots than to ask an actual chatbot? We asked ChatGPT, which has gained significant traction since its launch late last year, what it thought about the future of chatbots within the finance industry.

As you will see, its answers are characteristically factual and to-the-point. There’s little room here for witty insight or edgy observations – the things that make interviews good. It also appears less inclined to express personal opinions, unsurprisingly. When it does express an opinion, that opinion is not its own – no matter how convincing it may be. As the saying ‘garbage in, garbage out’ (GIGO) intimates, ChatGPT’s answers are the sum of its inputs. Nonetheless, it is able to hold a continuous and coherent conversation, and it’s probably not the worst interview we’ve ever conducted!

Introduce yourself to our audience.

ChatGPT is a language model developed by OpenAI, based on the GPT (Generative Pretrained Transformer) architecture. It is trained on a large corpus of text data and can generate human-like responses to text-based prompts.

ChatGPT can be used for a wide range of applications including language translation, question-answering, text generation, and conversational AI. It is designed to understand and generate human-like text, making it well-suited for tasks such as chatbots, where the goal is to generate natural and human-like responses to user inputs.

Do you think chatbots could be better utilised in the finance industry?

Yes, chatbots have the potential to greatly improve customer service and efficiency in the finance industry by automating simple tasks and providing instant responses to common inquiries. They can also collect and analyse customer data to provide personalised financial advice.

But surely that's already happening. Is there untapped potential for chatbots in finance or banking?

Yes, there is untapped potential for chatbots in finance and banking. Some potential areas for growth include:

  • Integration with advanced financial technologies such as blockchain and AI
  • Providing more personalised and advanced financial advice and investment recommendations
  • Improved fraud detection and risk management through real-time monitoring and analysis of customer transactions
  • Streamlining and automating more complex financial processes such as loan applications and portfolio management

Overall, chatbots in finance and banking have the potential to drive greater efficiency and enhance the customer experience in many ways.

People say that chatbots are useful for customer service, but won't there always be a question or two that chatbots can't understand?

Yes, there will always be some questions or requests that chatbots may not be able to handle. Chatbots are currently limited by their programming and the data they were trained on, and may not always be able to understand the nuances of human language or handle complex requests. In these cases, the chatbot should be designed to escalate the conversation to a human agent who can assist the customer. The use of chatbots should be seen as complementary to human customer service, not as a replacement.

In that case, do you think the skillset of humans will need to change as we learn to live and work alongside AI?

Yes, as AI technology advances, the skillset of humans is likely to change. As tasks previously performed by humans are automated, it will be important for workers to develop new skills that complement the strengths of AI. These might include:

  • Problem-solving and critical thinking skills, as AI can handle routine tasks but may struggle with more complex or unique problems
  • Emotional intelligence and interpersonal skills, as human interaction and empathy will remain important in areas such as customer service and relationship management
  • Technical skills in areas such as data analysis, programming and AI development, as these will be in high demand in industries that increasingly rely on technology

Overall, the rise of AI and automation will likely lead to a shift in the job market towards more technically skilled and creative roles, and it will be important for workers to continually upskill and adapt to stay relevant in a rapidly changing landscape.

Do you think there will be fewer jobs in future overall?

It is difficult to predict with certainty, but some experts believe that the rise of AI and automation may lead to job displacement in certain industries. However, it is also possible that new jobs will be created as a result of these technological advancements.

Historically, technological progress has often led to both job displacement and job creation, as some tasks become automated while others become more valuable due to the increased efficiency and productivity that technology enables.

Therefore, it is likely that the overall impact of AI on employment will depend on various factors such as the rate of technological progress, the willingness of workers to adapt and reskill, and the ability of the economy to create new job opportunities.

Overall, it is important for governments, businesses and individuals to proactively plan for the changes that AI and automation may bring to the job market, in order to ensure that workers are equipped with the skills and support they need to succeed in the future.

Will a universal basic income become necessary, to compensate displaced workers?

The idea of a universal basic income (UBI) as a way to compensate for job displacement caused by automation and AI has been debated by economists, policy makers, and the general public.

Proponents of UBI argue that it would provide a safety net for workers who are displaced by technology, ensuring that everyone has access to a basic standard of living regardless of employment status. They also argue that UBI could provide a stimulus for economic growth, as recipients would have more money to spend on goods and services.

Opponents of UBI argue that it could disincentivise work and innovation, as people may have less motivation to seek employment if they have a guaranteed income. They also argue that UBI would be expensive to implement and difficult to finance, especially in countries with large populations and limited resources.

Overall, whether or not UBI will become necessary in the future remains to be seen, and will depend on a range of factors including the rate of technological progress, the ability of the job market to adapt and create new opportunities, and the willingness of governments and businesses to implement policies that support workers in a rapidly changing landscape.

At the moment, fintech apps have to be painstakingly built by coders. Do you envision a future where developers will be able to specify a functionality to a chatbot and get the code for a basic working prototype in return?

It's possible that the development of fintech apps could become more streamlined in the future, perhaps through the use of AI tools that can generate code or prototypes based on natural language inputs. However, there are a number of technical and practical challenges that would need to be overcome before this becomes a reality.

At present, the development of fintech apps involves a complex interplay of technical skills, financial knowledge, design considerations, and regulatory requirements. Simply generating code from a natural language input may not be sufficient to produce a functioning and effective fintech app, as there are many other factors that need to be taken into account.

Additionally, it's also important to consider the ethical and security implications of using AI to generate code, as there may be concerns around accountability and the potential for the generation of malicious or poorly secured code.

Therefore, while it's possible that AI could play a role in simplifying the development process for fintech apps in the future, it's likely that human expertise and oversight will still be required to ensure that the resulting apps are effective, secure, and compliant with industry regulations.

Do you think coding will become a less valuable skill in future?

It is unlikely that coding will become a less valuable skill in the future, as technology continues to play a growing role in nearly all aspects of society and the economy. As AI and automation automate some routine tasks and make certain manual processes more efficient, the demand for individuals with technical skills, such as coding, is likely to increase. This is because coding remains a critical component in the development of software, websites, and other technological solutions, and is required to build and maintain the systems that power our increasingly digital world.

Moreover, as technology continues to evolve and new innovations emerge, the demand for individuals who are able to code and develop new solutions is likely to remain high.

However, the nature of coding and the specific skills that are in demand may change over time, as new programming languages and technologies emerge. It will be important for individuals who work in tech to continually upskill and adapt to stay relevant in a rapidly changing landscape.

Overall, coding is likely to remain a valuable and in-demand skill for the foreseeable future, but individuals who work in tech will need to be adaptable and continuously learning in order to stay ahead of the curve.

Do you expect we'll encounter malicious or unethical uses of chat bots in future?

Yes, it is highly likely that chatbots will be used for malicious or unethical purposes in the future, just as any technology can be misused. Examples could include impersonation, spreading false information, phishing, or manipulating public opinion. It's important for responsible parties to be aware of these potential risks and work to prevent them.

Credit for answers: ChatGPT

Share

Featured Articles

Upcoming Events: FinTech LIVE 2024

Discover what’s still to come in 2024 for FinTech LIVE

SAVE THE DATE: FinTech LIVE New York

FinTech LIVE returns this summer with FinTech LIVE New York on 17 June 2024 – The ultimate virtual event for fintech leaders in North America

WE’RE LIVE! FinTech LIVE Dubai

Back for another day, this time in Dubai! FinTech LIVE Dubai is LIVE, don’t miss out on your chance to hear from Swift, HSBC, Mastercard and many more

Amberdata: RWA tokenisation gains significant momentum

Tech & AI

WE’RE LIVE! FinTech LIVE Singapore

Banking

FinTech LIVE Singapore: Just One More Day to Go!

Financial Services (FinServ)