OpenAI pauses work on new Astra model Over Cyber Concerns

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. Over the past two weeks, OpenAI and Anthropic PBC have publicly acknowledged that they’ve inadvertently breached the systems of multiple institutions, including Hugging Face Inc., while testing their models. Meta Platforms Inc. also said Wednesday 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. Is OpenAI admitting how dangerous it is ?