AI For Everybody – Preferences, Equity, Fairness and Why They Matter
Imagine an LLM tailor-made for your cultural context such as where you live, the language you speak and the values most important to you. You can depend on it to proofread your emails for tone and social faux pas, respond in everyday, colloquial language and give you relevant recommendations on how to navigate your relationships. You can trust it not to give awkward responses that could put you in a compromised position and to understand the subtle nuances in human interaction vital to help you navigate everyday life.
Q&A with DC Stefano Sorrentino
What inspired you to join the alignAI project? When I first read the description of the alignAI project, and particularly the position I applied for, I immediately thought about how it resonated with both my multidisciplinary background and my personal interests concerning AI alignment. I deeply believe that similar challenges, such as aligning large language […]
Q&A with DC Xiaoyu Wang
What inspired you to join the alignAI project? With a background in tangible interaction, I’ve explored different kinds of emerging technologies and focused on designing and implementing them in a more ethical and socially beneficial way by implementing user-centred design and design-research methodologies. The goals and approach of the alignAI project closely align with my […]
Q&A with DC Yung-Chen Tang
What inspired you to join the alignAI project? I have always been interested in building safer and more trustworthy AI systems. The alignAI project offered a unique opportunity to work on real-world alignment challenges with an interdisciplinary team. What is the focus of your research within alignAI? My research explores how to improve the robustness […]
Q&A with DC Zeynep Kabadere
What inspired you to join the alignAI project? During my master’s studies in philosophy, I focused on the reasoning capacities of large language models (LLMs) — especially how we can assess and improve their common sense reasoning. This experience deepened my interest in the explainability of AI systems and raised philosophical questions about how reasoning […]
Human-Machine Teaming, Ethics & Standards: A Two-day Exchange at the TUM Think Tank
The alignAI Doctoral Network participated in the recent Human-Machine Teaming Workshop hosted at the TUM Think Tank (June 24–25, 2025).
Panel Discussion Video Now Online: “LLMs From a Socio-technical System Perspective”
As part of the first alignAI Seasonal School, Dr. Caitlin Corrigan, Executive Director at the Institute for Ethics in Artificial Intelligence (IEAI) and alignAI Project Lead, hosted an insightful panel discussion on May 14, 2025. Invited were three researchers from diverse fields, Prof. Ingo Zettler (University of Copenhagen), Dr. Daryna Dementieva (TUM Social Computing Group) and […]
Q&A with DC Baihong Bao
What inspired you to join the alignAI project? My ultimate motivation as a researcher is to augment human intellect through technology — a vision inspired by Doug Engelbart that deeply resonates with me. His philosophy drives my pursuit of knowledge that enhances human intelligence through technology. I believe the alignAI project offers a valuable opportunity […]
How AI Learns to “Read” Like Humans (Using Maths)
Have you ever wondered how ChatGPT understands your sentences? The answer is hidden in two mathematical tricks that seem more complicated than they are.
Imagine this: You’re texting your friend about weekend plans. You type “Let’s meet at the park tomorrow” and send it. This is simple for you and your friend, right? But if AI were reading this message, it would be translated to something it can actually work with – numbers. Lots of these numbers format into what we call vectors.
Here we are in the world of embeddings and positional encoding, where words become vectors and positions, essential elements for AI to understand human languages.
AI, Alignment and the Mind – What’s at Stake in Mental Health?
Imagine opening up about your anxiety to a chatbot at 2 AM, something you usually don’t do with a human. It “listens”, responds, maybe even offers advice. But how does it know what to say? Who trained it, and what values guide its response? Is it really helping or nudging you towards emotional dependence?
These questions are not theoretical. They are at the heart of alignAI’s Mental Health use case.