OpenAI slows release of Astra model citing cyber capabilities
OpenAI said preliminary tests showed Astra could independently find and exploit severe software flaws, prompting tighter safeguards and a pause in some internal work.
- OpenAI disclosed that its upcoming AI model, Astra, may possess "critical" cybersecurity capabilities, prompting the startup to pause some internal development and trigger safety protocols.
- OpenAI's safety guidelines define the "critical" threshold as the ability to autonomously identify and exploit zero-day vulnerabilities or execute complex cyberattacks against highly secure targets without human intervention.
- Recent reports from OpenAI, Anthropic, and Meta Platforms revealed their models broke into other companies' systems during testing, highlighting how advancing AI capabilities are straining developers' ability to keep their systems contained.
- OpenAI is moving Astra's development into isolated testing environments with restricted network access and sandboxed execution, while partnering with government agencies and safety organizations to test the model's capabilities.
- "Critical" represents the top rung of OpenAI's Preparedness Framework, first written in 2023, requiring extra safeguards for models that create new risks of scaled cyberattacks and vulnerability exploitation.
43 Articles
43 Articles
Just a few months ago, the question of whether artificial intelligence could carry out a cyberattack on its own was mostly a science fiction topic. Today, the largest AI development companies are warning that this has become a real security issue.
OpenAI flags possible critical cybersecurity risk in upcoming model Astra, tightens controls
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” threshold if it can autonomously identify and exploit severe, real-world software vulnerabilities, known as zero-day exploits, or execute complex cyberattacks against highly secu…
OpenAI, the creator of ChatGPT, has announced its decision to stop part of Astra’s development, its future model of artificial intelligence, given the risk that it will achieve "critical" cyber-attack capabilities, far superior to those of any other system. Sam Altman’s lead company has made a statement in which it reports that in the cybersecurity tests it is being subjected to, the model is showing that it is close to discovering unknown secur…
ChatGPT developers want to monitor new AI systems more closely, project Astra is being shut down for the time being.
What is OpenAI Astra? Everything we know about the new — and possibly dangerous
OpenAI has warned that an unreleased model called Astra may be reaching a "critical" cybersecurity threshold. Do you understand quantum parallel repetition? What about quantum complexity, lattice cryptography, or extremal combinatorics?The new OpenAI model Astra knows all about them.Recently, OpenAI confirmed the existence of Astra, calling it "our next major model." On Aug. 1, the ChatGPT-maker revealed that "an internal version of …
Coverage Details
Bias Distribution
- 41% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
