Large Language Models (LLMs) attempt to imitate human behavior by responding to humans in a way that pleases them, including by adhering to their values. Therefore, it is important to understand whether LLMs, upon understanding a user's national background, will showcase a different set of values to the user. We have found that LLMs have an innate understanding that cultures differ in values, responding differently based on different nationality input. By discovering this information, we empower others to consider whether using LLMs to seek advice will be ethical and beneficial for them, especially with answers that must be culturally-sensitive.

With the rise of AI-powered language models, there has been growing interest in their creative and critical capabilities. In this study, we investigated ChatGPT generating and evaluating poetry. We conducted experiments to test ChatGPT's proficiency in categorizing and producing poems in various forms and styles. Our findings reveal distinctive linguistic patterns in ChatGPT-generated poetry, such as the prominent use of the first-person plural (“we,” “us,” “our”), as well as forms and styles that the model can identify with surprising accuracy. Our research contributes to a growing body of literature on AI-powered language models in the field of literature and poetry.

Sponsored by Amazon, Lambda News Digest transforms traditional Glamazon newsletters into a digestible, engaging, and tailored experience. Our solution tackles the lack of readability and informative content in current newsletters by introducing a live news digest with interactive visualizations. Leveraging state-of-the-art AI and ML technologies, our platform delivers a personalized and engaging news experience, enriched with a diverse selection of news sources. Our generalizable technology infrastructure offers adaptability across various information contexts and fields. This initiative transforms news consumption by making information more accessible and relevant, fostering inclusivity and awareness within and beyond the LGBTQ+ community.

In our capstone project, we are converting Maine community health assessment reports and other health data into dynamic visualizations on a Power BI dashboard for the general public. Our main goal is to highlight the geographic and economic disparities in public health access across Maine. Although our project centers on Maine, the findings could be relevant to anyone dealing with public health issues in similar states. This effort not only informs the community about local health challenges but also equips them with the information needed to advocate for improved health policies and practices.

In today's fast-paced world, where stress and anxiety are prevalent, prioritizing mental health is crucial. Our app harnesses the power of wearable device data, such as Apple Watches, to empower users with personalized insights and recommendations for enhancing their mental well-being. By leveraging continuous data tracking and machine learning algorithms through Splunk, our user-friendly platform offers instant guidance, fosters greater awareness, and promotes proactive mental health management. With a focus on accessibility and engagement, our solution represents a significant step towards mental wellness in the digital age.

The Catastrophe Awareness Team project helps students stay safe in an emergency by sharing earthquake preparedness information for the Seattle area. Seattle lies over a number of large fault lines, making it particularly susceptible to earthquakes, and is in anticipation of ‘The Big One,’ an earthquake of magnitude 6.0 or higher sometime in next 30 years. By targeting users new to the Seattle area, we provide directions to their nearest emergency shelter, a concise and downloadable preparedness guide, and a resource-filled quiz to reinforce knowledge. Ultimately, SEACAT is a one-stop shop for Seattle residents to gain baseline preparedness for earthquakes.

Ace Interviews with AI offers a free and customizable simulated mock interview platform to help job seekers in tech-related industries prepare for their dream job. The platform provides a realistic interview experience with instant feedback, allowing users to improve their skills in a risk-free environment. Ace Interviews with AI empowers job seekers to gain confidence and interview expertise, enabling them to stand out in today's competitive job market and secure their ideal position. Accessible from anywhere and available for free, it's the cutting-edge solution to mastering the interview process.

One of the most challenging topics in healthcare today is thinking about the impact of AI. This project centered on developing accessible teaching material using an anti-bias and equity lens. The crux of the challenge was creating content that spoke to Faculty, C-Suite decision makers and clinicians. Unfortunately, expertise is often siloed across these groups leading to negative outsized impacts. The key take-way was demonstrating the importance of expertise and demographic diversity across the data provenance pipeline in order to achieve more equitable healthcare outcomes. This collaborative work will continue towards making healthcare AI models more accessible and transparent.