Workshop on Designing Benchmarks for Human Flourishing with AI
Contributed to the Comprehension, Reasoning & Agency track at the Workshop for Designing Benchmarks for Human Flourishing with AI, hosted by the MIT Media Lab’s Advancing Humans with AI (AHA) research program. The workshop brought together around 80 experts from over 40 organisations to draft conversation scenarios, define criteria for good and bad AI responses, and test the resulting benchmark against several large language models.
The workshop report was later published as Towards Open Benchmarks for Human Flourishing with AI.
MIT Media Lab, Cambridge, Massachusetts
Hi 👋😊! I’m Vidminas (most people call me Vid), a postdoc on the CHAILD project splitting time between the Department of Computer Science, University of Oxford and the Institute of Education, University College London.
I am interested in technology and education, and more specifically researching and developing technologies that empower people. The current CHAILD project focus is about defining and designing for agency in children and young people’s use of AI tools.
I completed my PhD at the Institute for Language, Cognition and Computation at the University of Edinburgh in March 2026, supervised by Professor Fiona McNeill and Professor Judy Robertson. The project was about better understanding and designing tools to help teachers search for educational resources.
I am always keen to chat about teaching and learning, human-computer interaction, participatory research, and designing applications for good, feel free to get in touch!