Confidence-Building Measures for Artificial Intelligence: Workshop proceedings

We’re forming a new industry body to promote the safe and responsible development of frontier AI systems: advancing AI safety research, identifying best practices and standards, and facilitating information sharing among policymakers and industry. Post Views: 61

We’re launching $10M in grants to support technical research towards the alignment and safety of superhuman AI systems, including weak-to-strong generalization, interpretability, scalable oversight, and more. Post Views: 52

We’re launching $10M in grants to support technical research towards the alignment and safety of superhuman AI systems, including weak-to-strong generalization, interpretability, scalable oversight, and more. Post Views: 51

Post Content Post Views: 174

We’re developing a blueprint for evaluating the risk that a large language model (LLM) could aid someone in creating a biological threat. In an evaluation involving both biology experts and students, we found that GPT-4 provides at most a mild uplift in biological threat creation accuracy. While this uplift is not large enough to be conclusive,…

We’re launching $10M in grants to support technical research towards the alignment and safety of superhuman AI systems, including weak-to-strong generalization, interpretability, scalable oversight, and more. Post Views: 45