Sharing more about how we trained and evaluated Beam, our first model, for safety: https://reflection.ai/blog/open-model-safety-lessons
In the coming weeks, we'll release additional safety research, evaluations, and tools under Project Iris, Reflection's open AI safety initiative.
We are committed to prioritizing safety in every model we build—and sharing what we develop and learn so that researchers, developers, policymakers, and enterprises can build on our work, advancing safety across the broader AI ecosystem.