Denna artikel utforskar artificiell intelligens (AI) som en kreativ partner inom digitalbildproduktion och dess potential att förändra och komplettera traditionella designmetoder.Artikeln undersöker AI:s roll inom designprocessen, främst inriktat mot AI-baserade systemsom kan syntetisera visuellt material, diskuterar dess styrkor, svagheter och begränsningarsamt reflekterar över hur AI påverkar kreativitet, effektivisering och idégenerering. Som ettkomplement till artikeln har en fotobok skapats för att på ett visuellt engagerande sättpresentera resultaten av en AI:s försök till tolkning av textbeskrivningar, med hjälp avAI-verktyget Midjourney och GPT-4. Vidare granskas hur AI-drivna designprocesser kansamverka med traditionella metoder och på så sätt belysa hur AI kan integreras i designerskreativa verktygslåda och därmed utnyttjas för att skapa intressanta och unika resultat.Artikeln bidrar till förståelsen av AI:s växande roll inom designområdet och erbjuder insikter ihur designers kan använda AI som en kreativ partner.

Syftet med denna studie är att undersöka hur AI framställs i de två största kvällstidningarnadå ChatGPT-3 lanserades i november 2022 fram till mars 2023. Studien syftar till att ta reda på om framställningen av ämnet AI har varit övervägande negativt eller positivt genom att undersöka 50 publicerade artiklar från vardera tidning samt vidare analys av två artiklar.  Som metod har vi utgått från kvantitativ innehållsanalys samt Faircloughs tredimensionella kritiska diskursanalys där fokus har varit på textanalys. Som huvudresultat har vi kommit fram till att majoriteten av de analyserade artiklarna har övervägande negativ framställning och att tidningarnas rubriker, genom starka ordval tenderar att vara kraftfulla. I många av artiklarna förekom ord som var djupt förknippade med negativa associationer såsom dödlig, kriminella, risk mot mänskligheten som exempel.

Large Language Models (LLMs) have become ever larger in recent years, typically demonstrating improved performance as the number of parameters increases. This thesis investigates how the probability distributions output by language models differ depending on the size of the model. For this purpose, three features for capturing the differences between the distributions are defined, namely the difference in entropy, the difference in probability mass in different slices of the distribution, and the difference in the number of tokens covering the top-p probability mass. The distributions are then put into different distribution classes based on how they differ from the distributions of the differently-sized model. Finally, the distributions are transformed to be more similar to the distributions of the other model. The results suggest that classifying distributions before transforming them, and adapting the transformations based on which class a distribution is in, improves the transformation results. It is also shown that letting a classifier choose the class label for each distribution yields better results than using random labels. Furthermore, the findings indicate that transforming the distributions using entropy and the number of tokens in the top-p probability mass makes the distributions more similar to the targets, while transforming them based on the probability mass of individual slices of the distributions makes the distributions more dissimilar.

In this research project, we aim to explore the use of Large Language Models (LLMs) as an interface to interact with API tools in natural language. Bubeck et al. [1] shed some light on how LLMs could be used to interact with API tools. Since then, new versions of LLMs have been launched and the question of how reliable a LLM can be in this task remains unanswered. The main goal of our thesis is to investigate the designs of the available system prompts for LLMs, identify the best-performing prompts, and evaluate the reliability of different LLMs when using the best-identified prompts. We will employ a multiple-stage controlled experiment: A literature review where we reveal the available system prompts used in the scientific community and open-source projects; then, using F1-score as a metric we will analyse the precision and recall of the system prompts aiming to select the best-performing system prompts in interacting with API tools; and in a latter stage, we compare a selection of LLMs with the best-performing prompts identified earlier. From these experiences, we realize that AI-generated system prompts perform better than the current prompts used in open-source and literature with GPT-4, zero-shot prompts have better performance in this specific task with GPT-4 and that a good system prompt in one model does not generalize well into other models.

This thesis investigates the applications and implications of Generative Pretrained Transformer (GPT) technology in international entrepreneurship. The research questions focus on how GPT can serve as a strategic tool, communication tool, and knowledge leverage tool, and how these applications influence decision-making, enhance performance, The findings from the analysis chapters highlights that GPT significantly contributes to strategic planning, market analysis, and operational management, thereby enhancing decision-making and performance. GPT technology, acting as a potent communication tool, nurtures more robust client relationships and eases cross-cultural interactions, courtesy of its superior language processing capabilities. The thesis discusses how these capabilities of GPT can lead to reduced miscommunications and enhanced client satisfaction. This, in turn, contributes to cost savings by retaining existing customers and attracting new ones, thereby enhancing profits. Moreover, The main theoretical implications that this  thesis has resulted in will showcase the time efficiency brought by automated, high-quality communication that reduces man-hours spent on routine interactions, freeing resources for strategic tasks for international entrepreneurship.  Furthermore, this study enriches the literature on generative AI exemplified by models like GPT in the world of international business, particularly within the context of international entrepreneurship. It offers essential insights that can guide international entrepreneurs in understanding the potential advantages of integrating GPT technology into their business operations.

No description available.

In this thesis, I delve into how Rhetorical Genre Study and Systemic-Functional Grammar can be used to assess the extent to which GPT-4 adheres to generic features and can be deemed adapted for its function. The objective is to establish a systematic model for objectively evaluating the degree to which AI-generated text is suitable for its intended purpose. To achieve this, I perform a rhetorical genre analysis on a crisis communication genre, which I subsequently quantify. I utilize the concept of topoi to pinpoint the arguments that serve to fulfill the functions of crisis communication. Subsequently, I prompt GPT-4 to produce texts within the genre and contrast them with my discoveries. Alongside this, I investigate the disparate results produced when using text and meta-text as input. The findings reveal a functional model to appraise the degree of text adaptation for its purpose within the analyzed genre. Although the model necessitates further fine-tuning, it effectively distinguishes nongeneric texts. The scope of the material selected was too limited to indicate any disparities in outcomes between different types of input. However, all input models generated texts that substantially conformed to the generic features.

In this thesis, a context-aware, personalized virtual assistant for use in automobiles is presented. With the increasing use of technology in automobiles, there is a growing need for safer and more practical ways for drivers to access information and perform tasks while driving. Voice-based interfaces, such as natural language processing, provide a solution to this problem as they do not require visual or manual input. In this thesis, a fine-tuned model of GPT-3 is used to understand user intentions and identify the user’s needs. The voice assistant is trained to understand the environment and the actions it can perform. The use of triggers such as drowsiness detection is also implemented to make the virtual assistant proactive in ensuring the user’s safety. User testing and evaluation was conducted to demonstrate the effectiveness of the context-aware, personalized virtual assistant in improving the driving experience and promoting safe driving practices.

Advancements within Large Language Models(LLMs) have opened a world of opportunities within the software development domain. This thesis, through an controlled experiment, aims to investigate how LLMs can be utilized within software testing, more specifically unit testing. The controlled experiment was performed using a Python script interfacing with the gpt-3.5-turbo model, to automatically generate unit tests for React Native components written in TypeScript. The pipeline described, performs the calls to the OpenAI Application Programming Interface(API) iterative. To evaluate and retrieve the metric code coverage, the unit tests were executed with Jest. Additionally, manual execution of failing tests, both compilable and non-compilable tests were executed and the different kind of errors with their frequency were documented. The experiment shows that LLMs can be used to generate comprehensive and accurate unit tests, with high potential of future improvements. While the amount of generated tests that compiled were low, their nature was often good, failing because of easy correctable syntax errors, faulty imports or missing dependencies. The errors found, were at large part due to project configurations while others would probably be less frequent through more extensive prompt-engineering or by the use of an newer model. The experiment also shows that the temperature affected the outcome and that the type of errors were different between compiling and non-compiling tests. A lower temperature parameter to the OpenAI API generally achieved better results, whilst a higher temperature showed greater coverage at compiled failing tests. This thesis also shows that future opportunities and improvements are widely available. Through better project optimization, newer models and better prompting, a better result is to be expected. The script could with further development be turned into a working product, making software testing faster and more efficient, saving both time and money while simultaneously improving the test case quality.

In recent years, there has been an increase in the issue of bullying, particularly in academic settings. This degree project examines the use of supervised machine learning techniques to identify bullying in text data from school surveys provided by the Friends Foundation. It evaluates various traditional algorithms such as Logistic Regression, Naive Bayes, SVM, Convolutional neural networks (CNN), alongside a Retrieval-Augmented Generation (RAG) model using Llama 3, with a primary goal of achieving high recall on the texts consisting of bullying while also considering precision, which is reflected in the use of the F3-score. The SVM model emerged as the most effective among the traditional methods, achieving the highest F3-score of 0.83. Although the RAG model showed promising recall, it suffered from very low precision, resulting in a slightly lower F3-score of 0.79. The study also addresses challenges such as the small and imbalanced dataset as well as emphasizes the importance of retaining stop words to maintain context in the text data. The findings highlight the potential of advanced machine learning models to significantly assist in bullying detection with adequate resources and further refinement.