E110 Alastair McKinley, CTO at Analytics Engines

Welcome to episode E110 of the AI Ireland podcast, the show that explores the applications and research of Data Science, Machine Learning and Artificial Intelligence on the island of Ireland.


Harnessing the Power of ChatGPT: A Comprehensive Guide to Boost Your Business

Welcome to the future of business operations, where ChatGPT is transforming the way enterprises function. From content creation to market research, this cutting-edge tool offers an array of benefits that can revolutionize your business. 

In this blog post, we will delve into the world of ChatGPT, explore its capabilities and reveal some groundbreaking ways to maximize its potential for your organization.

Unveiling the Mystery of ChatGPT 

OpenAI’s ChatGPT utilizes generative pre-trained transformers to produce text based on user input. Its formidable power lies in its ability to assist with various tasks, including crafting engaging content and conducting insightful market research.

Exploring ChatGPT’s Boundless Potential 

The versatility of ChatGPT makes it an indispensable asset for businesses of all sizes. It can be employed to research diverse topics, rephrase information, translate text across languages, and even grade tests. However, it’s essential to recognize its limitations and employ it ethically in all applications.

Mastering the Art of Prompt Generation with ChatGPT 

The key to unlocking ChatGPT’s full potential lies in crafting effective prompts. By providing context and engaging with the AI conversationally, you can enhance the quality and relevance of its output significantly.

Ten Game-Changing Applications of ChatGPT 

Embrace the transformative potential of ChatGPT for your business with these ten innovative use-cases:

  1. Streamlining Blog Topics and Keyword Research
  2. Crafting Engaging Website Copy
  3. Enhancing Proofreading and Editing Processes
  4. Developing Customised WordPress Plugins
  5. Assisting in Writing and Debugging Code
  6. Generating Captivating Video Scripts
  7. Creating Interactive Surveys and Quizzes for Market Research
  8. Conducting In-depth Market Research with AI Insights
  9. Crafting Compelling Product Descriptions
  10. Unleashing Creativity with AI-Generated Art
Conclusion: Embracing the Future with ChatGPT 

ChatGPT is more than just a tool; it’s a technological revolution that has firmly established its place in the modern business landscape. By harnessing its capabilities and leveraging it effectively, businesses can unlock unprecedented levels of efficiency and creativity.

Frequently Asked Questions 

We’ve compiled answers to some of the most common questions about ChatGPT to help you understand this tool better and make the most of its potential.

Integrate ChatGPT into your business operations today to create high-quality, SEO-optimized content that drives traffic and propels your enterprise into the future. Embrace the power of AI and let ChatGPT shape the way you do business.

Apply now to the 2023 AI Awards!

Applications for the 2023 AI Awards are still open until August 25th so if you or someone you know is working on exciting projects, products, services and leaders in AI, Data Science and Machine Learning that are making a real impact in the industry, we want to hear from you!It’s free to enter and there are 12 categories you can apply for across industry, academia and leadership. 

Head over to to submit an application or please feel free to contact with any queries about the submission process.


Discover the Top 7 ChatGPT Plugins of 2023

In the rapidly advancing realm of Artificial Intelligence, plugins are paramount for enriching the capabilities and precision of AI systems. OpenAI’s ChatGPT 4 language model is no exception.

In this blog post, we’ll delve into the most exceptional ChatGPT plugins of 2023, as highlighted by AI Ireland, that will significantly enhance your AI experience.

Expedia and KAYAK Plugins: Your Ultimate Travel Companions

Embark on worry-free travel with these plugins that offer comprehensive travel and hotel results. Whether you seek the finest hotel rates or exciting activities in a particular destination, these plugins have got you covered. Remember to double-check the results for utmost reliability.

Ask Your PDF: Simplifying Information Extraction

The Ask Your PDF plugin is a lifesaver when it comes to extracting information from PDF files. Though it requires manual PDF uploading to the AskYourPDF service, the results are remarkably accurate and incredibly valuable.

Link Reader: Summarizing Search Results with Ease

Link Reader is a versatile plugin that not only summarizes search results, but also seamlessly integrates with other plugins. Whether you need specific page information or general topics, Link Reader serves as your dependable assistant.

OpenTable: Your Personal Dining Guide

Consider the OpenTable plugin your personalized dining assistant that effortlessly helps you discover and book restaurant reservations. In collaboration with Instacart, it can also curate a shopping list for meal ingredients.

Prompt Perfect: Crafting Superior Queries

The key to accurate results from ChatGPT lies in crafting precise queries. The Prompt Perfect plugin facilitates this, ensuring you make the most of your AI experience.

VoxScript: Effortless YouTube Transcript Search

VoxScript proves to be a handy tool for swift information retrieval from YouTube transcripts. Keep in mind that it functions solely with videos that have existing transcripts.

WolframAlpha Expert System: Unmatched Accuracy

For unparalleled precision, the WolframAlpha expert system stands above any conventional AI program. Its prowess is particularly beneficial for technical, medical, mathematical, physics and financial inquiries.

Bonus Plugins

There’s an AI for That Plugin: Your AI Program Finder

This plugin acts as a brilliant tool for discovering the most suitable AI program for your specific needs, streamlining your AI journey.

What to Watch Plugin: Enhancing Your Streaming Experience

Streamline your search for favourite shows across various streaming services with the What to Watch Plugin, elevating your streaming experience.

Zapier Plugin: Streamlining Work Organization Tools

The Zapier plugin optimizes work organization tools and aids in debugging Zapier workflow actions, optimizing your work processes.

A Word of Caution

While these plugins are incredibly useful, they are still in their beta stages and may not always provide precise results. It’s crucial to remain aware of potential risks associated with connecting language models to external tools, including the possibility of unintended or harmful actions. As such, it’s recommended to utilize ChatGPT for obtaining initial insights rather than relying on it as a source of definitive answers.

We welcome your feedback and any plugins that didn’t make the list. Stay tuned for more updates on the world of AI and ChatGPT plugins.

Apply now to the 2023 AI Awards!

Applications for the 2023 AI Awards are still open until August 25th so if you or someone you know is working on exciting projects, products, services and leaders in AI, Data Science and Machine Learning that are making a real impact in the industry, we want to hear from you!It’s free to enter and there are 12 categories you can apply for across industry, academia and leadership. 

Head over to to submit an application or please feel free to contact with any queries about the submission process.



1. What is ChatGPT? 

Chat Generative Pretrained Transformer, commonly known as ChatGPT, is an advanced chatbot and generative language tool inaugurated by OpenAI in November 2022. 

Given an initial phrase or “prompt,” the ChatGPT models calculate the most likely sequence of letters or words. Built upon OpenAI’s GPT-3 family of vast language models, ChatGPT allows interaction with a model via a conversational user interface. The system was trained using 300 billion words sourced from books, internet texts, Wikipedia articles, code libraries and then refined with human feedback. 

In January 2023, Microsoft introduced Azure OpenAI Services, encompassing ChatGPT, additional language models, and supplementary enterprise services. It’s crucial for enterprise planners to differentiate between OpenAI’s ChatGPT and Azure OpenAI Service which, while still evolving, offers promising enterprise operational features.

2. How will ChatGPT be utilised in the Enterprise?

ChatGPT and similar foundation models will serve as tools in conjunction with numerous other AI and hyperautomation innovations. They will be part of architected solutions that automate and augment humans or machines, and autonomously carry out business and IT processes. 

As generative AI finds its place alongside existing work approaches, ChatGPT and other competitors will be deployed to replace, recalibrate and redefine various activities and tasks that are part of many job roles.

3.  What are the primary applications of ChatGPT?

ChatGPT can generate and enhance prose and code development, summarize long-form texts, classify content, answer questions, and translate and convert languages (including programming languages).

4. ROI of ChatGPT: What is its value?

The ROI of ChatGPT hinges on the use case. For augmented scenarios, these tools can save time for writers and programmers, but such time savings may not necessarily benefit employers. Users should maintain realistic expectations about the use cases and the value they aim to derive, especially given that the service as-is has significant limitations, such as reliability issues. 

The generated text or code might be inaccurate or biased, necessitating human validation, which could offset the initial time savings. It is essential to link ChatGPT use cases to KPIs and ensure the project enhances operational efficiency, generates new revenue or improves experiences.

5. How much is ChatGPT?

The 3.5 version of ChatGPT, is free of charge. OpenAI recently announced the launch of the ChatGpt 4.0 subscription plan for at $20 a month. ChatGPT will also be part of the Microsoft Azure OpenAI Service soon, but the pricing is currently being introduced. It’s plausible that substantial elements will be bundled with different Microsoft 365 software subscriptions.

6. Direct Customer Interaction with ChatGPT: Should it be done?

Generally, no – providing ChatGPT-powered experiences directly to customers is considered too high risk for most use cases at the present time, except in rare cases perhaps related to gaming or entertainment, where the correctness or impartiality of the content may not be under rigorous scrutiny.

7. Will ChatGPT replace jobs?

Initially, ChatGPT will primarily enhance specific activities or tasks rather than replace whole jobs. Future iterations of ChatGPT, along with other tools and their combinations, will likely progress beyond augmentation and start executing targeted activities or tasks independently. This process will necessitate testing, quality control, guardrails and governance.

8. Impact of ChatGPT on the Enterprise Workforce: What can we expect?

As stated in response to question 2, ChatGPT will be one among various tools, including other hyperautomation and AI innovations, incorporated in architected solutions that automate, augment humans or machines, or autonomously conduct business or IT processes. It will replace, recalibrate and redefine the activities and tasks that constitute many job roles.

9. What will be the Magnitude of Workforce Impact?

There will be creation of new jobs and the redefinition of others. The net change in the workforce will considerably fluctuate based on factors such as industry, location and the size and offerings (products or services) of the enterprise. 

However, it’s evident that tools like ChatGPT (or competitors), hyper-automation and AI innovations will target repetitive, high-volume tasks with an emphasis on efficiency, such as reducing cycle time, boosting productivity and enhancing quality control (reducing error rates), among others.

10. Future Prediction for the Enterprise: What’s the forecast?

By 2026, over 100 million humans will collaborate with robot colleagues (synthetic virtual colleagues) for enterprise work. This will not solely be powered by ChatGPT (or competitors); it will involve several other technologies and solutions.

11. Is ChatGPT Artificial General Intelligence?

No. Despite the impressive capabilities of ChatGPT and related large language models (LLMs) or foundation models, they cannot comprehend, learn or undertake any intellectual task that humans can. ChatGPT is a type of reinforcement learning approach. While enhanced with human feedback, it fundamentally remains a machine learning construct and lacks the generalization attributes provided by symbolic techniques.

12. Is ChatGPT a New AI Paradigm? 

ChatGPT is more of an evolution of ongoing trends than a new paradigm. Its underlying model is based on transformer neural networks, which have been foundational for over five years, including in vendor applications.

Nevertheless, ChatGPT introduces some new elements to those foundation models, such as conversational and short-term memory layers and massive human-in-the-loop feedback (reinforcement learning) for training. The engineering employed to make the model available for mass consumption is also novel, requiring extensive computational resources and model-serving architecture.

13. What are the multilingual Capabilities of ChatGPT?

ChatGPT was trained on a multilingual corpus, enabling it to respond to inputs and generate outputs in several languages. Gartner has informally observed that ChatGPT performs comparably to the leading commercial machine translation model for English to Spanish, but is not as proficient for other official UN languages (Arabic, Chinese, French, and Russian). ChatGPT’s translation is slower than commercial engines. The use of GPT-3 for translation should be evaluated on a case-by-case basis.

14. What are the different Uses of ChatGPT?

ChatGPT can be utilized in four different ways:

As-is: By entering prompts and receiving results via the web-based interface. This is the most popular usage approach currently.

Prompt Engineering without APIs: This involves using a service like ChatGPT alongside other technologies as part of a workflow, which can be carried out manually or by using screen scrape and robotic process automation (RPA) technologies.

Prompt Engineering using APIs: Although there are solutions on Github enabling an API wrapper around ChatGPT, these are not recommended for production builds or scale, and they are not supported by OpenAI.

Custom Build: Creating a custom build of the core GPT2/GPT3 model for a bespoke implementation is possible, but it wouldn’t have the conversational interaction.

15. What are the current Limitations of ChatGPT?

ChatGPT’s training only covers data up until 2021, which limits its recency. It cannot provide the sources of the information used to generate its answers and lacks explainability. The reliability of the model is dependent on its (unknown) underlying sources, which can sometimes be erroneous or inconsistent. 

While it can generate language and code, it cannot create images. Currently, there is no supported API available. You cannot train ChatGPT on your own knowledge bases. Despite seeming to perform complex tasks, ChatGPT only makes predictions without understanding the underlying concepts. It does not provide data privacy assurances. Although recent updates have improved its ability to handle mathematical queries, it still cannot be relied on for computation.

16. Can I use my own Data with ChatGPT?

At present, you can use your own data only for providing prompts to ChatGPT, but not for training or fine-tuning it. If you’re using ChatGPT as-is, you can include your own data and content with your questions, like pasting in software code for ChatGPT to debug, or inputting text for it to summarize. 

However, presently you can’t add your own industry or domain knowledge data to train or fine-tune ChatGPT, although this functionality is expected to be available in the Azure service in 2023. As an alternative, you can use the GPT2/3 engines without the ChatGPT conversational interface or additions and use transfer learning to train your own version of the model, but it would not result in the same type of model as ChatGPT.

17. Can I personalise content with ChatGPT?

While you cannot personalise the user experience of ChatGPT, users can influence the generative output via their prompts, such as by requesting that the generated content adhere to a certain writing style or educational level. The Azure OpenAI ChatGPT service is likely to add APIs in the future, which will likely make it possible to intercept the input and output and handle the user experience with a different interface.

18. Can I build or Integrate ChatGPT into Other Systems?

Yes, it is possible to use ChatGPT in the building of or integration into other systems. Currently, it is more suitable to construct augmented approaches that support various roles.

19. What are the new features of ChatGPT?

ChatGPT is not a static service. For instance, it was recently improved to handle mathematical prompts more effectively. Microsoft might use the Azure OpenAI ChatGPT service to complement Bing search in 2023. Furthermore, it is expected that more formal API offerings will be added to the service. Recently, updates have been rolled out to Microsoft Teams Premium, utilizing the Azure OpenAI ChatGPT core model of GPT3.5.

20. Is ChatGPT Replacing or Threatening Search?

No, ChatGPT is not a threat to search but rather, it complements it. While ChatGPT generates answers, search is more focused on artifact discovery like finding a particular document or sentence. Many search and insight engine vendors have been using base GPT technology as part of their AI techniques for some time. It is predicted that over time, discovery methods like search will evolve to use foundation models in conjunction with existing approaches.

21. Who are the competitors of ChatGPT?

Yes, ChatGPT does have competitors. Several smaller vendors have utilized large language models, similar to ChatGPT, to deliver specific task usage. However, many of the larger technology vendors have not yet commercialized their offerings. Google announced its own offering, Bard, on February 6, 2023, while it is expected that competitors such as Baidu and IBM will enter the market later in 2023.

22. What are the markets around ChatGPT?

The biggest evolution will be in creating bespoke variants of models like GPT, where system integrators and vendors support end users to input their own knowledge bases via transfer learning. More corpora management and prompt engineering services and tools are expected to emerge in 2023, as well as tools for fact-checking and generated text detection. 

Vendors are likely to differentiate their products through task-specific fine-tuning of their models and by introducing tools to mitigate risks related to the explainability, reliability, fairness, security, and transparency of generated content.

23. What is the effect of ChatGPT on Current Natural Language Technologies? Does it make them obsolete?

No, ChatGPT does not render current natural language technologies obsolete. It intersects two markets in the NLT space: conversational AI and natural language generation. If your chatbot conducts transactional conversations and relies on your own knowledge body, then ChatGPT won’t replace it. At present, ChatGPT serves as a broadly useful, general-purpose conversational tool, not a single-API solution for NLT. 

Within a workflow, ChatGPT and GPT technologies have a role. It might be possible to use the technology within NLT systems, like generating synonyms, utterances, and responses. It’s advisable to check with your current vendors to understand how they are utilizing generative technologies like ChatGPT.

24. Security of ChatGPT for Staff Usage ChatGPT. Should be used with the same caution as public online platforms?

Employees should avoid sharing sensitive personal, company or client information. While there aren’t currently clear assurances of privacy or confidentiality, Microsoft plans to introduce privacy assurances for its Azure OpenAI ChatGPT service, just like its other software services.

25. Does ChatGPT has a toxic content filter for both inputs and outputs?

Due to the nuanced and contextually dependent nature of this task, users should not completely rely on the model’s output for compliance or risk management, and should ensure human oversight of inputs and outputs.

26. Is there a Risk of Misuse of ChatGPT by Bad Actors?

There’s a valid concern that bad actors may misuse ChatGPT to generate false information, create convincing phishing emails, or even generate malicious code. The simplicity and widespread availability of ChatGPT heighten this risk. Users may be required to sign ethical usage agreements, but these could be hard to enforce.

27. Who Can View Conversations with ChatGPT?

ChatGPT service providers, currently OpenAI and Microsoft, can review conversations to improve their systems and ensure compliance with their policies. There are no assurances regarding other parties who might access the posted information. The Azure version of the service is expected to follow existing Azure OpenAI services in this respect.

28. Can conversations with ChatGPT be used for Training?

Yes, conversations may be used for training and could be reviewed by trainers. It is not currently possible to delete specific prompts, so users need to be careful about what they share. While it is possible to delete an account, this action won’t erase the training data.

29. Is there biases in ChatGPT?

ChatGPT’s fine-tuning is aligned to the trainers’ preferences rather than verified facts, leading to plausible but potentially unreliable outputs. Bias may be present in the large datasets used to train the GPT-3 model. Despite OpenAI’s efforts to minimize bias, there have been known instances of it surfacing.

30. Is there regulatory Risks Regarding Training Data Content Ownership?

There are concerns about the ownership of data and intellectual property rights with respect to content used to train GPT-3 and ChatGPT. As of now, there is no clarity on this matter, which poses a risk to OpenAI and the further usage of ChatGPT which needs to be resolved.

31. Can you detect ChatGPT-Generated Content?

There’s currently no reliable method to detect whether content was generated by ChatGPT or a human. Some tools have attempted to do this, but results so far have been mixed.

32. Should I implement a Company Policy on ChatGPT?

It is advisable to establish a policy as knowledge workers might already be using ChatGPT for various tasks. An outright block might result in covert “shadow” ChatGPT usage, giving organizations a false sense of compliance.

Employees should treat information posted through ChatGPT as if it were public. Organizations should monitor usage, encourage innovation, but ensure ChatGPT is used responsibly and never unfiltered with customers and partners.



The provided list of resources highlights the various sources from which information about ChatGPT and related AI technologies has been drawn for the purpose of the FAQ. These resources, provided by the creators and hosts of the technology, offer insights into the development, deployment and implications of using AI models like ChatGPT. Here’s a brief summary of what these resources entail:

ChatGPT and GPT Board Reference Presentation: A deep dive into the workings, application, and impact of GPT and ChatGPT models.

Innovation Insight for ML-Powered Coding Assistants: A resource providing information on how machine learning is being used to facilitate coding, discussing AI models like GPT-3’s code-generation capabilities.

ChatGPT: Optimizing Language Models for Dialogue, OpenAI: A detailed explanation of the development and optimization process of the ChatGPT model, published by OpenAI.

Azure OpenAI Service, Microsoft: Information on Microsoft’s Azure OpenAI service, including its features, capabilities, and use cases.

Introducing ChatGPT Plus, OpenAI: An announcement by OpenAI introducing the enhanced features and capabilities of the ChatGPT Plus model.

General Availability of Azure OpenAI Service Expands Access to Large, Advanced AI Models With Added Enterprise Benefits, Microsoft: A release by Microsoft announcing the broader availability of their Azure OpenAI service, with an emphasis on its benefits for enterprises.

Microsoft Teams Premium: Cut Costs and Add AI-Powered Productivity, Microsoft: A resource detailing the integration of AI technologies into Microsoft Teams for enhanced productivity and efficiency.

Data, Privacy, and Security for Azure OpenAI Service, Microsoft: Information provided by Microsoft regarding data handling, privacy measures, and security features within their Azure OpenAI service

Apply now to the 2023 AI Awards!

Applications for the 2023 AI Awards are still open until August 25th so if you or someone you know is working on exciting projects, products, services and leaders in AI, Data Science and Machine Learning that are making a real impact in the industry, we want to hear from you!It’s free to enter and there are 12 categories you can apply for across industry, academia and leadership. 

Head over to to submit an application or please feel free to contact with any queries about the submission process.


Demystifying ChatGPT: Ten Key Questions Answered

OpenAI launched the chatbot and AI language tool, ChatGPT, in November 2022, and it has been a hot topic ever since. Despite the buzz surrounding ChatGPT and conversational AI, there are still several unanswered questions about what this generative AI can do for individuals and businesses. In this article, AI Ireland’s founder, Mark Kelly, provides invaluable insights into ChatGPT’s potential value and its safety for use and he also addresses the most common queries from AI Ireland’s clientele and members.


1. What is ChatGPT’s Role in the Enterprise?

ChatGPT, along with other foundational models, plays an integral part in hyperautomation and AI innovations. It automates, augments human or machine tasks, and autonomously executes business and IT processes. As such, it will likely redefine, recalibrate, and replace some tasks within various jobs.

2. What are the different Use Cases of ChatGPT?

From improving prose and code development to summarizing and classifying text, ChatGPT has numerous applications. It can also translate and convert language (including programming languages). Deployment methods include: using it as-is, prompt engineering without APIs, using APIs for prompt engineering, or custom building your version of foundational models.

3. What will be the impact of ChatGPT on the Workforce?

The workforce’s response to the introduction of tools like ChatGPT, hyperautomation, and other AI innovations will vary widely based on industry, location, enterprise size, and offerings. The use of these tools will primarily target repetitive and high-volume tasks, focusing on improving quality control and productivity. They will also be integrated into business applications to facilitate adoption and provide contextual information within applications.

4. What are ChatGPT’s Current Limitations?

ChatGPT’s training data only goes up until September 2021, meaning its knowledge of events since then is limited. Other limitations include its inability to cite sources, accept or generate image input, and train on personal knowledge bases. It cannot perform complex tasks; rather, it makes predictions. Its data privacy assurances have not undergone rigorous audits yet, and it cannot be relied on for math despite recent improvements.

5. What is the Security of Using ChatGPT?

While both OpenAI and Microsoft assure confidentiality and privacy of shared information, they have not yet fully clarified their data usage policies. Therefore, users should treat shared information as if it were public. To avoid shadow usage, companies should formulate a policy around ChatGPT, encourage innovation, monitor usage, and ensure the technology augments internal work with qualified data.

6. What does the future of ChatGPT and Generative AI look like?

Expectations for ChatGPT involve moving from its beta phase to early trials and pilots, where best practices for use will mature and adoption into business workflows will increase. However, this phase might also witness backlash over privacy, misuse of information, and bias.

7. What are the Recommended Actions?

While it’s still early days, the potential of this technology is immense. Users should encourage careful experimentation, understand the risks and best practices, and ensure all generated text is reviewed by humans. Form a task force to explore opportunities and threats, plan a discovery roadmap, and determine the skills, services, and investments needed.

8. How is ChatGPT trained?

ChatGPT is trained using a diverse range of internet text. But, it does not know specifics about which documents were in its training set or have access to any personal data unless explicitly provided in the conversation.

9. How reliable is the information generated by ChatGPT?

ChatGPT’s responses are generated based on patterns it learned during its training phase. It does not have the ability to access or retrieve factual, up-to-date information. Therefore, while it strives to provide useful and accurate information, it is always advisable to cross-verify the information from reliable sources.

10. Can ChatGPT replace human interaction?

While ChatGPT can mimic human-like conversation, it cannot replace human interaction. It lacks an understanding of context, personal experience, and common sense reasoning that is integral to human conversation.


“Unleashing the Power of Generative AI” with Kieran McCorry, National Technology Officer at Microsoft Ireland


In the latest episode of the AI Ireland podcast, Microsoft’s National Technology Officer, Kieran McCorry sheds light on the transformational impact of Generative AI and its integration into Microsoft’s overall products and service.

In the episode, Kieran emphasises the role of ChatGPT and its partnership with Microsoft Azure in making AI technology accessible to the masses. The discussion highlighted various applications of Generative AI, including its ability to assist users in creating PowerPoint presentations and even writing code.