Shahar Avin reports the findings from an interdisciplinary workshop organised by FHI and CSER on preventing and mitigating AI misuse, just before a big report comes out. The talk covers technical, institutional and research agendas for addressing threats to digital, physical and political security.
In the future, we may post a transcript for this talk, but we haven’t created one yet. If you’d like to create a transcript for this talk, contact Aaron Gertler — he can help you get started.
Shahar Avin: Near-term AI security risks, and what to do about them
Link post
Shahar Avin reports the findings from an interdisciplinary workshop organised by FHI and CSER on preventing and mitigating AI misuse, just before a big report comes out. The talk covers technical, institutional and research agendas for addressing threats to digital, physical and political security.
In the future, we may post a transcript for this talk, but we haven’t created one yet. If you’d like to create a transcript for this talk, contact Aaron Gertler — he can help you get started.