Jacqueline Harding
Jacqueline Harding is a PhD Student in Symbolic Systems at Stanford University. Her work engages with the empirical deep learning interpretability literature using ideas from the philosophy of cognitive science; more generally, she is interested in taking a sociotechnical approach to AI ethics and safety, grounding talk of future risks in concrete present harms.
Research:
Operationalising Representation in Natural Language Processing (British Journal for the Philosophy of Science)
AI Language Models Cannot Replace Human Research Participants (co-authored with William D'Alessandro, Robert Long, and Nicholas Laskowski. Published in AI & Society).
Center for AI Safety resources :
