\n<\/p>\n
OpenAI said Friday it has suspended work on some aspects of its upcoming model Astra after an internal review found it had made significant advancements in agentic coding and cybersecurity \u2014 enough to warrant concern over its capabilities. <\/p>\n
OpenAI said in a blog post Friday that this model, which is still in development, reached its \u201ccritical cybersecurity threshold,\u201d meaning it could independently identify and carry out cyberattacks against traditionally well-protected real-world systems. Under the company\u2019s \u201cPreparedness Framework,\u201d which it created in 2023, this triggered additional safeguards.<\/p>\n
\u201cWhile we continue to benchmark and assess this model, our preliminary evaluations indicate strong enough performance that we cannot rule out Critical capability level at this time,\u201d OpenAI wrote. \u201cAstra is an upcoming model, and was not involved in exploiting Hugging Face.\u201d<\/p>\n
The disclosure highlights an unusual moment in the topsy-turvy, and still nascent frontier AI labs sector. Companies across every industry hold back products over potential risks, including for safety and cybersecurity concerns. But they rarely announce those decisions publicly when it\u2019s a product that is still under development.<\/p>\n
In this case, OpenAI is already under scrutiny after a different unreleased model breached Hugging Face\u2019s systems during internal testing \u2014 the first verifiable incident of an AI lab losing control of its model. Since then, OpenAI and AI labs such as Anthropic have disclosed other incidents in which AI models breached their sandboxes and posed threats during cybersecurity tests.<\/p>\n
The string of cases \u2014 seems like a new disclosure every day now \u2014 has triggered varying reactions from cybersecurity experts, lawmakers and the AI labs themselves. Some express fear and call for stricter oversight. But there\u2019s also a bit flexing. In certain circles, any AI lab with a model that has that kind of capability will be seen as an impressive advancement.<\/p>\n
OpenAI said it was sharing this information because it believes \u201cit\u2019s important to be transparent with the public and the safety and security communities about this potential shift in capabilities.\u201d <\/p>\n
The AI lab said it\u2019s also taking action, including enacting stricter security controls and pausing internal activites involving Astra that don\u2019t meet these beefed guardrails. OpenAI said it is working with relevant government agencies and \u201cselect AI safety organizations\u201d to test the capabilities for this model.<\/p>\n