From the source
Baseten and Base Labs are building safety evaluation and monitoring infrastructure for the open models Baseten serves, connecting safety research directly to the systems that train and serve those models.
- The company says open models are often wrongly confused with unmonitored ones, and argues that open weights give a broader audience the tooling and visibility to find and fix vulnerabilities.
- The effort covers three areas: training models to follow explicit policies and ask for help when a task cannot be completed legitimately, monitoring inputs, outputs, tool use and internal model states and tying those signals to permissions, isolation and pre-execution checks, and investigating failures to improve training or controls.
- Base Labs will develop and publish methods for training and monitoring, while Baseten integrates that work into its deployment infrastructure at runtime and offers it as a managed service.
- Baseten says the published methods and evidence will be testable by customers and outside evaluators, and invites the open-source community to contribute to safety evaluation protocols.




