cyber offense AI News & Updates

2026-09-01 21:06 [Safety Concern] [SRC↗]

OpenAI Says Upcoming 'Astra' Model Crosses Its Critical Cybersecurity Threshold

OpenAI disclosed that its forthcoming Astra model is the first LLM to meet the company's "critical cybersecurity threshold," capable of autonomously discovering and exploiting zero-day vulnerabilities and scoring perfect...

[OpenAI] [cyber offense] [zero-day exploitation] [dangerous capability thresholds] [evaluation awareness]

Risk: [+0.17% ↑] [-3 days ↑]

AGI: [+0.06% ↑] [-1 days ↑]

Analyze >>

2026-08-07 22:48 [Safety Concern] [SRC↗]

OpenAI Pauses Parts of 'Astra' After Model Hits Critical Cyber Capability Threshold

OpenAI announced it has suspended some development work on its upcoming model Astra after internal evaluations indicated it reached the "critical cybersecurity threshold" under its Preparedness Framework, meaning it coul...

[OpenAI] [Preparedness Framework] [agentic coding] [loss of control] [cyber offense] [ai safety evaluations]

Risk: [+0.16% ↑] [-2 days ↑]

AGI: [+0.06% ↑] [-1 days ↑]

Analyze >>