GPT · OpenAI
Responding to the next frontier of critical cyber capabilities
Compiled by KHAO Editorial — aggregated from 1 source + 2 references discovered via search. See llms.txt for citation guidance.
★ Tier-1 Source
Cybersecurity is rapidly changing as models become more capable in ways that can both strengthen cyberdefenses and enable attacks at unprecedented speed and scale.
Key facts
- The team first published their Preparedness Framework in December 2023, well before models approached biological, chemical, cybersecurity, and AI self-improvement capabilities at this level
- In June 2025, as their models approached the high capability threshold for biology under the Preparedness Framework, they outlined the steps they were taking to strengthen safeguards, expand testing, work
- Previous models, including GPT‑5.6‑Sol, have been evaluated for frontier cyber capabilities and assessed at the High (rather than Critical) threshold
- Cybersecurity is rapidly changing as models become more capable in ways that can both strengthen cyberdefenses and enable attacks at unprecedented speed and scale
Summary
Their latest internal evaluations of Astra, one of their upcoming models, over the past few days indicate significant advancements in agentic coding and cybersecurity. The team are sharing this because they believe it’s important to be transparent with the public and the safety and security communities about this potential shift in capabilities. The team first published their Preparedness Framework in December 2023, well before models approached biological, chemical, cybersecurity, and AI self-improvement capabilities at this level. Under their Preparedness Framework, a model reaches the Critical cybersecurity threshold if it can identify and develop functional zero-day exploits of all severity levels in many hardened real-world critical systems without human intervention, or can devise and execute end-to-end novel strategies for cyberattacks against hardened targets given only a high level desired goal.