… As AI models become more capable, we need to keep a close eye on whether they can provide users with dangerous technical knowledge in ways that could threaten national security. …
… We’ve been pleased to see Petri being used by external organizations: for example, the UK’s AI Security Institute AISI made it a major part of how they evaluate models for their propensity to sabotage AI research. …
… Biosecurity Our previous post focused extensively on our biosecurity evaluations, and we have continued this work. …
… But the security and reliability of agents cannot be achieved by any single company working alone. …
… From model evaluations to a security partnership In late 2025, we noticed that Opus 4.5 was close to solving all tasks in CyberGym , a benchmark that tests whether LLMs can reproduce known security vulnerabilities. …
… Out of scope: other cyber-related activities The following are topics that have overlap with cybersecurity, but that are out of the scope of our cybersecurity classifiers. …
… And because of this generalist nature, there are numerous other security threats that could be prioritized. We understand why one might be skeptical of prioritizing biorisk when considering the security implications of AI. …
… Robotics is no different than other domains in this regard, especially since it implicates physical security and individual privacy. …
… With that context, we were pleased to advocate for and join in commitments announced at the White House on July 21 that included “internal and external security testing of our AI systems” to guard against “some of the most significant sources of AI risks, such as biosecurity and cybersecurity.” How… …