Combining Physical and Intentional Stance for Safe AI
Projects | | Links:
ARIA-funded work connecting physical dynamics with intentional descriptions of beliefs and goals to support verifiable, safer AI.
ARIA opportunity seed
This two-year project (2025–2027) is a collaboration with Martin Biehl (Cross Labs and Cross Compass) and Nathaniel Virgo (University of Hertfordshire), supported by ARIA’s Trust Everything, Everywhere opportunity space.
We are developing a formal link between the physical behaviour of a system and an intentional description in terms of beliefs and goals. Using mathematical interpretation maps, we ask when dynamical systems can be understood as goal-directed agents—and how this can support tools for checking whether AI behaviour is consistent with its intended purpose.
