Tech News
← Home  ·  All topics

Model Safeguards

1 GoKawiil brief on this topic

AI lab designates 'Astra' model as first to cross critical cybersecurity risk threshold

The company behind the Astra model says new testing shows it has crossed a 'Critical' cybersecurity capability threshold under its Preparedness Framework, meaning it could independently discover unknown vulnerabilities and craft exploits against well-defended systems without step-by-step human guidance. This is the first model the company has classified at that severity level, prompting delays to strengthen safeguards before release.