Artificial Agency Speaker Series

November
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•

Events

You have 0 events pending approval by the calendar admin.
They will show up on the schedule once approved
 
Cover Image for Anti-Scheming: how would we train a model not to scheme? (Bronson Schoen and Marius Hobbhahn, Apollo Research)

Anti-Scheming: how would we train a model not to scheme? (Bronson Schoen and Marius Hobbhahn, Apollo Research)

​
By UK AI Forum
​
Department of Engineering
+89
 
Cover Image for Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments (Chris Schnabl, Pivotal Labs & Uni. of Cambridge)

Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments (Chris Schnabl, Pivotal Labs & Uni. of Cambridge)

​
By UK AI Forum
​
Old Divinity School, St John's College
+3
 
Cover Image for The AI Agent Index: What Deployments Reveal About Safety and Autonomy (Leon Staufer, MATS & University of Cambridge)

The AI Agent Index: What Deployments Reveal About Safety and Autonomy (Leon Staufer, MATS & University of Cambridge)

​
By UK AI Forum
​
Old Divinity School, St John's College
+2
 
Cover Image for AI Agents and Morality: Towards Norm-Aligned Design Choices (Esther Jaromitski, Queen Mary University)

AI Agents and Morality: Towards Norm-Aligned Design Choices (Esther Jaromitski, Queen Mary University)

​
By UK AI Forum
​
Old Divinity School, St John's College