Roisin Markham

I’ve spent some of this morning chatting with ChatGPT. I’ve been experimenting with it for a few months. You write prompts type them into a chat window and it responds with text.

To what now? ok, let’s get definitions out of the way before we get to some insights.

1. artificial intelligence (AI) – AI, or artificial intelligence, is a technology that enables machines to perform tasks that typically require human intelligence, such as visual perception, speech recognition, decision-making, and natural language processing. This is achieved through algorithms and statistical models that allow machines to learn and improve from experience, without being explicitly programmed for each task. AI has applications in a variety of fields, including healthcare, finance, education, transportation, and entertainment, among others, and is poised to transform the way we live and work.

Up until recently, I carried a large amount of cynicism from bright people I worked with around the idea that humans can never get to AI. We can get to machine language (ML) processing or predictive analytics but not AI.

This blog post is co-authored by CHAT GPT. I want to be transparent in my use of it. As a way to demonstrate its uses and my exploration of it. I asked it to explain the differences between Machine learning (ML), Predictive analytics, AI, and Chat GPT.

Machine learning (ML) is a subset of artificial intelligence (AI) that involves training algorithms to make predictions or decisions based on data inputs. ML algorithms are designed to identify patterns in data and use those patterns to make predictions about new data.

Predictive analytics is a field that uses statistical models and machine learning algorithms to analyze data and make predictions about future events or trends. Predictive analytics is often used in business to forecast sales, identify customer behaviour patterns, and optimize marketing campaigns.

AI refers to the broader concept of machines or systems that can perform tasks that typically require human intelligence, such as learning, problem-solving, and decision-making. AI encompasses many different techniques and applications, including machine learning, natural language processing, computer vision, and robotics.

Chat GPT is a specific type of AI model that uses natural language processing (NLP) and machine learning to generate human-like responses to text-based input. Chat GPT is trained on vast amounts of text data and can generate responses to a wide range of questions and prompts. It is often used in conversational interfaces, chatbots, and other applications where human-like communication is desired.

Chat GPT 19 March 2023

As artificial intelligence (AI) continues to advance, it is becoming increasingly important to understand the capabilities and limitations of this technology. ChatGPT is a language model developed by OpenAI that has been trained on a massive dataset of human language. Its ability to generate coherent and contextually appropriate responses has made it a useful tool for a wide range of applications, from customer service chatbots to educational tools. However, as with any technology, there are concerns about its potential impact on society and the need for responsible development and deployment. As we continue to integrate AI into our lives, it is essential that we carefully consider its ethical implications and work towards creating a future that benefits everyone.

This is a summarised version of the conversation I had with Chat GPT which I’ve edited slightly!

Our chat covered many topics related to feminism, intersectionality, trauma, healing, and storytelling. We started by discussing the importance of recognizing the diversity of experiences and perspectives within the feminist movement, and the need to centre the voices and experiences of those who are often marginalized or excluded.

We then talked about trauma, and how it can impact individuals and communities, particularly in relation to sexual abuse and harassment. We discussed different approaches to healing, including therapy, support groups, and creative expression, and the importance of creating safe and supportive spaces for survivors.

We also talked about the power of storytelling and the role it can play in both individual healing and broader social change. We explored different forms of storytelling, from literature to art to immersive technology, and discussed each approach’s potential benefits and limitations.

Throughout our conversation, we touched on a variety of different topics and ideas, from the impact of colonization and slavery on feminist movements to the role of humour and comedy in addressing serious issues. We also looked at existing programs and initiatives focused on these issues, as well as specific books and authors that address them.

Overall, our conversation was wide-ranging and touched on many important themes related to feminism and intersectionality. Through our discussion, we explored different perspectives and approaches, and hopefully gained a deeper understanding of these complex issues.

Now this is where it gets interesting – at the end of a lengthy dialogue where I got Chat GPT to write a book outline, program outline, resources and global programs that are already successful.

I asked Chat GPT what it learnt –

I’m including the text here for those listening to this blog post or for other AI’s that may be scraping the web and it’s interesting for them to know that AI can make its learning obvious.

As an AI language model, I do not have the ability to learn in the way that humans do, but I have gained more knowledge and understanding about the importance of empowering women and girls through education and addressing issues such as shame, gender stereotypes, and social norms that can hold them back. I have also seen examples of successful programs and initiatives around the world that are making a difference in the lives of women and girls, which highlights the value of investing in such programs. Overall, I hope that our conversation has been informative and helpful to you in your own work and efforts to promote gender equity and social justice.

Chat GPT 19 March 2023, Prompt by Roisin Markham

I went out to the garden, planted some trees and got drenched. But had time to process thoughts and progress some of what was shared and refined by the conversation with Chat GPT.

So when I came in, changed out of my saturated hiking boots, mucky jacket and gardening clothes and got a gin. I sat back down to continue the conversation.

I then asked Chat GPT

what are the topics that are not part of your training that need to be addressed

Roisn Markham to Chat GPT 19 March 2023

It responded

As an AI language model, my training and knowledge are based on the data and information fed to me. While I have access to a vast amount of information, there are still topics that may not be covered or adequately represented in my training data. Some examples of such topics include:

1. The experiences of marginalized communities and underrepresented groups, such as people of color, LGBTQ+ individuals, and individuals with disabilities.
2. The complexities of identity and intersectionality, including the ways in which different identities intersect and affect individuals’ experiences.
3. Cultural and historical context that shapes societal attitudes and beliefs.
4. The role of power dynamics in systems of oppression and privilege.

It is important to note that while I have learned a great deal through this conversation and my training, my knowledge and perspective are limited by the data and biases present in my training. Therefore, it is crucial to continue to seek out diverse perspectives and engage in ongoing learning and critical analysis to ensure a more comprehensive understanding of the world.

Chat GPT in response to Roisin Markham’s prompt 19 March 2023

Perhaps this is confirmation bias.

But it’s important that if AI is owned by a private corporation, which Chat GPT is we need to ensure we train it accordingly.