Benjamin Alt

Tag

ai-safety

3 posts

Threat Models & Mitigations from Physical AGI

A summary of my invited talk at Safe AI Germany (SAIGE) on safety threats arising from physical AGI, and a tentative research agenda for grounding the discussion in empirical evaluations on real hardware.

·ai-safety·physical-ai

A(G)I 2022: A Year in Review

A talk I gave at the 2023 Effective Altruism Retreat in Sigmaringen, Germany, outlining how pivotal AI technologies shifted narratives around AI and its impacts on society.

·ai-safety·talk

← all writing