Research

A selection of research conducted by Future Impact Group Fellows under the supervision of our Project Leads

Search by title, author, or keyword

AI Safety · Philosophy for Safe AI · Digital Minds

Future Impact 19/06/2026 Future Impact 19/06/2026

Incoherent Values? Probing LLM Preferences Through Parametric Variation

Authors: Elena Ajayi, Angelica Chowdhury, Seth Lazar

Fellows: Elena Ajayi, Angelica Chowdhury

→ View publication

Read More

Future Impact 19/06/2026 Future Impact 19/06/2026

Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs

Authors: Carolina Camassa, Derek Shiller

Fellows: Carolina Camassa

→ View publication

Read More

Future Impact 28/05/2026 Future Impact 28/05/2026

How's it going? Reinforcement learning in language models recruits a functional welfare axis

Authors: Andy Q Han, David J. Chalmers, Pavel Izmailov

Fellows: Andy Q Han

→ View publication

Read More