OpenAI Shares Preliminary Cybersecurity Evals for Astra Model

OpenAI News · rss · 2026-08-07

OpenAI has announced that it is sharing preliminary cybersecurity capability evaluations for its upcoming Astra model. The company states this move is intended to proactively address the critical cyber threats posed by frontier AI models.

Additionally, OpenAI detailed the specific steps being taken to mitigate these potential risks, including further strengthening the model's safety guardrails and underlying security controls.

Original post →

More from Models

Models channel →