OpenAI Pauses Some Work on New Astra Model on Cyber Concerns

OpenAI is expanding its AI cybersecurity defense program Daybreak, and rolling out a new cyber-trained AI model with it.

Tighter safeguards and pauses on internal work follow early tests that left OpenAI unable to rule out critical cyber capabilities in Astra.

A little over a week ago, artificial intelligence company OpenAI announced 10 advances in mathematics and computer science made with its as-yet-unreleased model Astra. The discoveries cover a wide range of mathematical fields, including geometry, cryptography and coding theory.

The AI lab said it could not rule out a new model had reached "Critical" capability, meaning it could launch cyberattacks against sophisticated cyber defenses.

‘It’s important to be transparent’: Citing potentially alarming cybersecurity risks, the ChatGPT maker has paused the launch of Astra, its next-generation autonomous AI agent.

Malte Mueller / Getty Images A little over a week ago, artificial intelligence company OpenAI announced ten advances in mathematics and computer science made with their as-yet unreleased model Astra. The discoveries cover a wide range of mathematical fields, including geometry,…

Under OpenAI's Preparedness Framework, the potential development of such capabilities triggers stricter safeguards, particularly when models could create risks of severe harm.OpenAI said it is "pausing" activities involving Astra while it strengthens its security controls.

Under OpenAI's ‌safety guidelines, a model reaches the "critical" threshold if it can autonomously identify and exploit severe, real-world software vulnerabilities, known as zero-day exploits, or execute complex cyberattacks against highly secure targets without human…

Agent found to be able to find and exploit vulnerabilities without human intervention, and to carry out cyber-attacks OpenAI will pause some work on an artificial intelligence model because of security concerns, the company stated Friday, following a series of incidents in which…

OpenAI said on Friday it cannot rule out that its upcoming AI model, Astra, has “critical” cybersecurity capabilities, prompting the startup to pause some internal development and trigger safety protocols. Under OpenAI’s safety guidelines, a model reaches the “critical”…

OpenAI is planning to make Astra, its upcoming and highly capable AI model, generally available to the public, CEO Sam…

Or how I learned to stop worrying and love dangerous AI

OpenAI is pausing some internal work around one of its upcoming artificial intelligence models to implement stricter safeguards after the system was found to be significantly more adept at cybersecurity tasks.