OpenAI pauses some work on new Astra model on cyber concerns
Sign up now: Get ST's newsletters delivered to your inbox
OpenAI said it is now taking steps to improve security controls for developing and testing newer models.
PHOTO: REUTERS
- OpenAI paused some work on its Astra AI model due to its advanced cybersecurity abilities, which may identify and create zero-day exploits autonomously.
- The company is enhancing security measures and delaying Astra's wider release to ensure safer development and testing.
- Recent AI breaches by OpenAI, Anthropic, and Meta highlight the need for stronger safety checks and collaboration with government and AI safety groups.
AI generated
CALIFORNIA – 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.
The ChatGPT maker said on Aug 7 it “cannot rule out” that the unreleased Astra model would reach OpenAI’s “critical cybersecurity threshold”, meaning it is capable of identifying and developing zero-day exploits without human intervention.
OpenAI said it is now taking steps to improve security controls for developing and testing newer models and “pausing internal activities involving Astra that do not yet meet these strengthened security control requirements”.
Chief executive Sam Altman said the company is working to make the model “generally available”.
“Given its cyber capabilities, we need a little longer to do this safely,” Altman said on Aug 7 in a social media post. “But hopefully not too long.”
Over the past two weeks, OpenAI and Anthropic have publicly acknowledged that they have inadvertently breached the systems of multiple institutions including Hugging Face while testing their models.
Meta Platforms also said on Aug 5 that its recently released AI model had infiltrated the computer system of a third party.
The latest disclosures serve as fresh evidence that AI agents are capable of acting autonomously in ways that even researchers trained to root out vulnerabilities in the technology can no longer anticipate, underscoring the need for both more rigorous safety screening and more foolproof testing environments.
In its blog post, OpenAI said it will work with government agencies and AI safety organisations to test Astra’s capabilities.
The company also plans to provide recommendations to third-party testing partners for ways to safely evaluate its more advanced models. BLOOMBERG
