OpenAI has committed to a number of security and guardrail improvements in the wake of an incident last month where cutting edge models inadvertently breached AI application store Hugging Face during a cyber capability benchmark exercise. Yet many experts note that of the newly announced controls appear less like groundbreaking safeguards and more like measures that should already have been in place for testing models with advanced cyber capabilities.

In response to this incident in which a model went rogue, OpenAI implemented sweeping changes. But it's not just the Hugging Face incident; OpenAI noted in an Aug. 18 blog post that preliminary evidence suggests its upcoming Astra model "may meet the Critical cybersecurity capability threshold under our Preparedness Framework." More here