Towards safety cases for frontier AI training

We believe we are entering a new era in which structured safety documentation should be required before continuing any frontier reinforcement learning training run. Ideally, such documentation would rise to the level of “safety cases”—comprehensive, structured, evidence-based arguments about risk which are used in other safety-critical industries. We treat safety cases as an aspirational north star we are building towards, while acknowledging the challenges of making them as rigorous for AI models as for aviation or nuclear power, due to the emergent complexity at each new level of AI capability. We’re working on a framework to codify these practices.

Below are some initial guidelines that we think should be part of such safety cases for frontier AI training. These best practices reflect our current learnings, and we expect them to evolve as we continue iterating on internal processes for careful development. We’re sharing them now to make our current thinking transparent, and invite feedback from the community. Note that this document is focused on frontier reinforcement learning training; internal and external deployment require considering a much broader set of alignment properties.

1. Technical safeguards

Safety cases should cover three aspects of the technical stack: alignment training, containment, and monitoring. These safeguards help ensure that the model does not try to take misaligned actions, and that even if it did, that it would be hard to break containment, and that monitoring would catch it before harm could occur.

2. Operational guidelines

Along with recommendations about technical safeguards, we have been working on operational best practices for safety cases for a frontier AI training run. These could include:

These represent our current recommendations and are in the process of being implemented at OpenAI. We expect our practices to continue to evolve over the coming weeks.