I’m in the field of creating and organizing LARP games as my Hobby and I decided to try using AI to help me in this activity. My task was to write a list of rules, regulations for a game event, namely for a conference that took place within the game. These rules were to include a rather lengthy list of rules and prohibitions, but had enough loopholes that players could use them in the game format if they wanted to. It would have been a challenge to create such a large amount of text on my own, so I decided to take advantage of new technologies and involved ChatGPT in this task.
At first things did not go smoothly, the neural network did not fully understand the task and the specifics of the RPG setting, so it did not give me the results I wanted, but later, when ChatGPT got a sufficient amount of context, it gave me roughly the results I wanted. I discussed some points with the AI separately, asked to change nuances and in the end I was happy with the result.
After I showed the result to my team, they were impressed that I had created this with AI, but they still had questions about the rules, so I took the second round and came to ChatGPT to work on some parts. Since the neural network was already aware of the whole context, it was not very difficult to correct mistakes, I find the memorization functionality within one dialog box very handy.
In the end, I posted these rules for the players and they were more than happy with the result of the work I had done.
In October our group took part in the city festival “Klanglicht”. At this festival, new technologies were used to immerse visitors in a special atmosphere, to awaken feelings and emotions, to make them think.
I like the concept of the festival as a whole, Graz for a few days becomes a huge exhibition platform where artists can realize their most daring ideas and citizens and guests of the city can touch something beautiful and interesting without any special efforts.
It was very interesting for me to look at the organization of the process from the inside, to find out what technologies can be used, what places and locations are involved and so on.
Below you can read an analysis of the article I read according to the SQ3R method.
Survey.
I found the structure of the article simple and clear. It is divided into several parts, namely: Introduction, AI and AI in Education. The titles of the main parts and sub-chapters are conveniently highlighted in colors, so it doesn’t take much effort to do a brief overview.
Questions.
How exactly can chatbots be used in education?
How can they be implemented into the learning process in schools as part of UX design?
The ethical side of the issue.
How might the introduction of AI affect classical educational methods?
Read.
The article briefly reviews the history of the emergence of AI as well as its development, which is undoubtedly important for a general understanding of the issue. Separate subchapters are devoted to chat bots in general and Chat-GPT in particular. Then there is a chapter devoted to a specific topic, namely AI in learning. Both pros and cons of the approach are discussed in detail, and the ethical side of the issue is also not left without attention, and a separate subchapter is devoted to it. Of course, at the end there is a brief conclusion that summarizes the results.
I would say that the article did not disappoint me at all, I got my questions answered and was satisfied with what I read. A few new insights have definitely emerged in my mind and I hope to be able to use the new to me information in writing my Master thesis.
Recite.
Chatbots can be used to personalize the learning process for each student as much as possible, not to mention that, unlike a teacher, a chatbot is always ready to answer any question at any time of the day or night.
The chatbot should behave as much like a real person as possible, the interface should not be very different from a normal chat with a teacher, so for the student such an introduction will be smooth.
There are some concerns that the article provides:
reliability and accuracy of the information it presents
potential biases in the data, resulting in discriminatory or misleading responses
privacy issues since it may collect and store personal information about students
questions about the role of teachers and the impact on the job market for educators
lack of human interaction, reducing the quality of the educational experience for students
over-reliance and dependency on technology
concerns about the rights of intellectual property
transparency and accountability as it might be difficult to identify how decisions are being made by the chatbot
The article says chatbots can make learning a lot easier for teachers and administrators, but they can never replace a real person.
Review.
Revisiting the article and my analysis above I can confidently say that I found the article very helpful. It expands my knowledge in AI and provides certain insights that will be useful to me when writing my paper. At first glance, it may seem that the topic is not that relevant to the topic of my Master thesis, however, the use of chatbots, specifically Chat GPT in training, is a great example of smart use of high technology and from the UX point of view it is also exciting to consider. What implementation methods are already in place, what can be improved, how to deal with ethical issues – all of this is relevant to any field where new technologies such as AI are or will be used.
This week I had a few more discussions about my approach to the Master’s thesis. I was able to take away some valuable points that I hadn’t really considered before. One important point is data protection. I will be working with children and teenagers and in this respect I have to pay attention to guidelines and, above all, parental consent. To do this, I need to carry out detailed research in advance, contact people who are familiar with this if necessary and ensure that I protect myself adequately. Another point, more related to the content, is literature research. There is still a lot that can be done here and existing data can be extracted. As my project is very extensive, this is definitely a valuable point, as I can save myself time by referring to existing studies and literature. In addition, it can be helpful to include the EU directives regarding the protection of minors and use these as a framework. Another point to consider is a gradual structure of the Instagram Youth version. This would mean that features would be activated for each age group and the platform would be adapted to the respective age group. This would mean that teenagers would not be thrown into the deep end of the “real” Instagram version when they reach the age of majority, but would be gradually guided there and introduced to age-appropriate features. With regard to my own studies, I was advised to distribute the questionnaires widely in order to obtain quantitative data. For qualitative data, I could consider a preliminary study with, for example, 5 teenagers to roughly define the project design and then ask targeted questions to the general public. Assuming that the app is divided into age groups, it would also be important to survey teenagers of different ages and see where there are differences between the age groups. This could serve as a good basis for defining the activation of various features.
All in all, I can say that the discussions only motivated me even more for my topic. I was also reminded that I have a lot planned and that it is important to have a well-thought-out schedule. I will draw this up over the next few weeks so that I can get straight to work at the official start of my Master’s thesis. It’s nice for me to see that my topic is also well received by the outside world, that the problem and my goal are immediately understood and that everyone is looking forward to the result. This confirms that I have chosen an important topic that relates to current social problems.
I listened to a podcast on the history and development of neural networks and algorithms that worked with language and speech. It started with studying the very structure of language, not any particular language, but any language, looking for various common features in order to identify patterns and implement them in algorithms for recognizing and generating speech. Then followed the simplest algorithms, for example, the well-known function for button phones “T9”. Then came the simplest machine learning, neural networks learned from huge arrays of text and were able to predict answers. For example, such an algorithm can solve the simplest arithmetic problem without knowing arithmetic at all, it just knows that if there are “2” “+” and “2” in the text, the answer according to the probability theory will be “4”. At this stage, the neural network could already be useful, but it is not perfect at all. Such systems did not look at the whole sentence, but checked one word at a time, so they could produce an incoherent set of words if the sentence was constructed in an atypical way.
In 2015, a company called Open AI appeared, which would later turn the idea of language models upside down, but in the beginning, they were losing the technology race to Google. In 2022, Open AI releases ChatGPT, which was a turning point in how people perceive language models. Users use ChatGPT for literally everything: It to help write an essay, find a bug in code, formulate the right Google query, now it can already draw pictures, and so on.
ChatGPT is a great example of how new technology can be used in real life by real people, and the best part is that it is actually being used.
In October, I took an intensive week-long zerocoding course. We learned how to make a working application for mobile devices using the Glide software. The assignment was to create an app for tracking personal finances so that users could more easily control their daily expenses. I found this quite interesting, especially in the context of my topic, as it directly relates to new technologies and how they can make our lives easier. If the concept of zerocoding is developed further, application development will be ten times faster.
In the course we developed the application interface, several functions such as for example filtering and categorizing expenses, and worked with the database.
During the World Usability Congress 2023 I attended a talk by Ben Anyasodo, who is Principal Research Consultant of Redrock Consulting. the topic immediately interested me, as I am generally interested in AI and new technologies, namely how they can be implemented in classic areas of design, such as UX research. It should be noted at once that the topic is quite ambiguous, it conceals a lot of pitfalls: the ethical side of the issue, privacy issue and so on.
During his presentation, the speaker gave several different examples of AI implementation to conduct UX research in the field. I would like to dwell on one example in more detail. One coffee shop had a video surveillance system that was connected to AI and recorded the work of the employees. It counted the number of cups that were dispensed by a particular barista. On the one hand, this seems like a good tool for measuring the efficiency of employees, but the work of a barista includes not just making coffee, but creating an atmosphere, communication, and just a friendly smile, which can be valued even more than the coffee itself. This is something that AI cannot measure in any way. I was so interested that I found a discussion on the Internet about this innovation and most users found the idea terrible. In fact, I tend to share this opinion, in my opinion, such an application of AI is more likely to harm the efficiency of an organization.
Anyway, the presentation was really entertaining, and gave me quite a few insights that I can use in my master thesis.
I finally got around to watching it, after having it be the number one movie I wanted to watch not only for the design & research impulses but also purely out of personal interest. Considering I have a soft spot for anime movies from that time and loved Akira so much that I more or less based my AI generated movie on its aesthetics and setting, it’s strange that it took me so long, especially considering the thematic relevance for my master’s thesis, not only from a production standpoint, but also because of its themes of a future where cybernetic augmentations and AI are commonplace.
The story
Honestly, I’m a little disappointed. While the themes and concepts were engaging and interesting, I felt like the pacing of the story was a bit strange, but I suspect it has something to do with the movie’s short length of only 82 minutes, 4 of which are end credits and 4 more being reserved for a lengthy title sequence, not to mention the frequent use of long sequential establishing shots that serve to set the mood of the setting.
Some aspects were left unexplained and some political conflicts were only briefly mentioned, but played an important role in the end, which made me feel like i never completely understood the motivations of the parties involved.
The ending, which felt like it happened too early, left me wanting for more, which I guess can be considered a good thing, I definitely want to follow this experience up with the movie’s sequel: ‘Ghost in the Shell 2: Innocence’ (2004), though apparently that movie covers a different arc of the original anime. I’ll just have to see for myself.
Production
Because this is not supposed to be a movie review, I want to talk a bit about the production of the film. Aesthetically it was absolutely gorgeous, its carefully selected color palettes were beautiful, the design of the city, its buildings, objects, vehicles and weapons were tasteful and in general the movie was not as hyperfuturistic as I expected, which helped me relate to its world a little better.
The animation over all was great and made use of some 3D animation, but usually in a stylistic way, as navigational systems or computer generated graphics the characters interacted with, so it always felt grounded in the world. Establishing shots and backgrounds were much in line with what I was able to recreate using Midjourney, so that was further good news. The film was also absolutely drowned in glow and glare effects, often washing out the frame quite heavily, though carefully respecting the color palettes. I want to define color palettes of my own for the project and, depending on what direction I want to go in, am considering referencing both Ghost in the Shell (1995) as well as Akira (1988).
Apart from the complex action heavy sequences that I will try to avoid for my project since I assume that AI is not far enough to pull off an actual choreographed performance, I noticed that there were many times where the characters were not animated a lot at all. Specifically sequences that feature heavy dialogue were often a single frame of a character with their mount moving, something very obvious if you think about it, but for some reason it took this movie for me to really notice it.
This honestly fills me with quite a bit of hope, because dialogue where the viewer can directly and closely see the subject is very jarring to look at in photorealistic and even 3D stylised AI movie attempts. Maybe I can emphasise the storytelling and dialogues of the individual characters more in my project, since those are really easy to do from a technical standpoint. However, this also means that I would absolutely not get away with AI generated voices, because of the heavy emphasis on the voice actors’ performance. Maybe a music video is again the best way to go, provided it allows for storytelling via subtitles where the characters’ facial expressions are more important. Then again, that could be hard to pull off technically.
All in all there’s a lot I keep learning from watching these beautiful movies, and a lot to consider when it comes to recreating similar styles using AI, but overall I think the project could turn out very nicely. I’m looking forward to the animation tests in the future.
For my last impulse blog post, I decided to listen to two episodes of a “Dynamic Women” podcast. It is an Award-Winning action-focused lifestyle and leadership podcast full of stories and strategies to help women design their success.
In the first episode, which was about strategic planning for success, they talked about how it is important to not blindly follow trends, emphasizing that what’s popular might not necessarily align with a personalized, effective strategy for an individual. Additionally, listeners of a podcast get an insight into Diane’s (Professional Certified Coach) personal experiences with strategic planning.
Another episode was about gender equity in the career fields, which had a podcast quest Sophie Warwick, Co-Founder of the Thoughtful Co. She revealed the story of how her passion turned into business and how she employs data analysis to develop in-house gender equity policies and drives the mission of building gender-inclusive workplaces. Sophie also raised an important topic of how women usually hesitate to negotiate for better compensation and promotions. The conversation from there goes to strategies for moving women into senior positions.
The topics discussed in this podcast are important and offer valuable insights for my research topic. By analyzing the gender pay gap, and negotiation challenges, and proposing actionable strategies, Sophie’s and Diane’s expertise aligns seamlessly with the core focus of my investigation.
At the beginning of my research, I can make a few assumptions at once about the potential attitude of most of intuitive users towards the use of interfaces with AI. Of course, these assumptions are based primarily on my own background, my experience and my own perceptions of AI.
In my opinion, a typical middle-station user is more likely to not trust AI in interfaces. So far, this direction is too new for the majority of users to get used to it.
Epistemology
If we talk about accurate measurements of satisfaction or dissatisfaction with AI user interfaces, here a large number of different UX methods can come to the rescue. However, I am sure that in fact measuring emotional state is far from easy. At this stage it is important to understand exactly what the user is satisfied or dissatisfied with and strictly share his emotions regarding the interface as a whole or specifically AI.