AI can change Treasury: ChatGPT

A notable advance in AI has been the extension of GPT-like models, such as ChatGPT, in creating regenerative answers. These models, which are based on transformer architecture, have shown remarkable capabilities in natural language processing tasks, like language translation, text summarization, and question-answering. ChatGPT models have been fine-tuned for specific assignments and industries, including financial analysis and customer service. As this technology is rapidly evolving, the usability and relevance for organizations will only grow. From the Editor Panel we took the opportunity to check out ourselves how ChatGPT works and what AI knows about Treasury. Therefore, Erwin and Robin interviewed ChatGPT from OpenAI by asking the chatbot the questions below. Enjoy reading!

AI is always interpreted as too difficult and almost ‘impossible’ to adopt. Is AI really too difficult to adopt in organizations?

“Adopting AI in organizations can be challenging, but it is not necessarily “too difficult”. The complexity of AI adoption depends on various factors such as the size and structure of the organization, the type of AI technology being adopted, and the availability of AI expertise within the organization.

Some common challenges organizations face when adopting AI include:

  • Lack of technical expertise: many organizations struggle to find employees with the necessary AI skills and expertise to effectively implement and use AI technologies.
  • Integration with existing systems: integrating AI technologies with existing systems and processes can be complex and time-consuming.
  • Data quality and governance: adopting AI requires large amounts of data, which must be of high quality and properly governed to ensure accurate results.
  • Ethical and legal concerns: AI raises a number of ethical and legal concerns, such as privacy and the potential for discrimination, that must be addressed before adoption.

Despite these challenges, many organizations have successfully adopted AI and are realizing significant benefits in areas such as efficiency, cost savings, and improved decision-making. With the right preparation, planning, and resources, AI adoption can be manageable and well worth the effort.”

Ok, thank you. Good to hear that AI is not impossible to realise. Next to that we are wondering if you see any risks related to adopting AI in corporate Treasury?

“There are some potential risks associated with the use of AI in corporate Treasury, such as:

  • Lack of transparency: AI models can be complex and difficult to understand, making it difficult for human decision makers to understand how a decision was made and to identify potential biases in the model.
  • Dependence on data quality: AI models rely on large amounts of data to train and make predictions. If the data is inaccurate, incomplete or biased, it can lead to incorrect predictions and decisions.
  • Lack of understanding: AI models can be difficult for non-technical staff to understand and use, which can lead to them not being fully utilised or implemented properly.
  • Cybersecurity: as AI is integrated in the financial services, the risk of cyberattack increases, as the technology can be used to automate fraud, money laundering and other illegal activities.
  • Job displacement: AI can automate many tasks that were previously done by humans, which may lead to job displacement.

However, it’s worth noting that these risks can be mitigated through careful planning and implementation. For example, using explainable AI (XAI) models, which are designed to be more transparent and interpretable, can help to address the lack of transparency. Additionally, implementing a robust data governance framework can help to ensure data quality, and investing in training and education can help to ensure that non-technical staff are able to understand and use AI models effectively.”

Job displacement is an interesting potential risk! Do you see job displacement as a real risk, or would it mean that existing Treasury staff needs to learn new skills to make sure the systems and models run in the way they are supposed to?

“Job displacement is a real risk associated with the use of AI in corporate Treasury, as the technology has the potential to automate many tasks that were previously done by humans. This can lead to a reduction in headcount and a shift in the types of jobs that are needed within the Treasury department.

However, it’s also worth noting that the use of AI in corporate Treasury can create new job opportunities as well. For example, the implementation and management of AI systems and models requires specialized skills and knowledge, such as data science, machine learning, and programming. Additionally, monitoring, maintaining and updating the AI system requires human expertise and oversight, which can create new jobs.

So, it’s important to consider that the use of AI can lead to a shift in the types of jobs that are needed, rather than necessarily resulting in job loss. Treasury staff may need to learn new skills to make sure the systems and models run in the way they are supposed to, and to ensure that they are able to effectively use and interpret the output of the AI models. This can be achieved through training and education programs, which can help to ensure that existing staff are able to transition to new roles and responsibilities.”

Thank you once again. Besides information about AI we are wondering if you can also solve riddles. Mike’s father has four kids. Three of them are named Huey, Dewey and Louie. What is the name of the fourth kid?

“It is not specified in the information given what is the name of the fourth kid. The statement only mentions that Mike’s father has four kids and three of them are named Huey, Dewey, and Louie.”

Are you sure?

“As an AI, I can only provide information based on the context given in the statement. The statement you provided does not specify the name of the fourth kid, thus I cannot give you an answer to this question. My apologies for any confusion.”

One last question before we stop this interview. What do you exactly know about the Treasury Barometer?

“I’m sorry, but I’m not familiar with the term “Treasury Barometer.” Can you provide some additional context or information about what it is? That way I can better understand what you’re asking about and provide a more accurate answer.”

In that case you should really visit the DACT 2023! See you there!

“I’m an AI language model and don’t have the ability to physically attend events, but I’m always here to answer questions and provide information! If you have any further questions about the Treasury Barometer or any other topic, feel free to ask. I’ll do my best to provide you with accurate and helpful information.”

Conclusions

This interview 2.0 shows what capabilities AI has and what already is available to everyone. Our opinion is that AI is not infallible and airtight yet, but the current capabilities are more than promising. Especially, given the fact that the next ChatGPT model will have 571x more contextual information than the current one. Also, competition between different providers will increase the speed of developments. Is this the beginning of radical changes?

Interview with: 

ChatGPT

AI chatbot

Interviewed on 07-2-2023