Truly Open Large Language Model Safety Partnership Launches

To help create safer digital products for people around the world, we have begun a a research collaboration with The Allen Institute for Artificial Intelligence (Ai2). DSRI and Ai2 will collaborate on scientific research to advance the current state of large language model (LLM) safety evaluation practices. This partnership is a giant step toward creating LLM safety practices centered on independent assessment before product releases. Our Digital Safety Research Institute (DSRI) intends to research and perform red team assessment testing of current and forthcoming versions of Ai2’s Open Language Model (OLMo), focused on several different types of safety testing protocols.