37:55Stealing Reasoning Traces from Proprietary APIs - Alexander Panfilov & David SchmotzSafe AI Germany2593 wk ago
33:05Building a Defense-in-Depth Biosecurity Strategy for the AI Era - Steph GuerraSafe AI Germany1851 mo ago
25:10The EU Code of Practice and GPAI systemic risk oversight: Where are we now? - Jimmy FarrellSafe AI Germany661 mo ago
37:32Exploration Hacking: Can LLMs learn to resist RL training? - Joschka BraunSafe AI Germany1123 mo ago
