OpenAI pauses Astra AI model over critical cybersecurity concerns
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.
OpenAI has temporarily halted the development of its upcoming AI model, Astra, following internal assessments that revealed potentially hazardous progress in agentic coding and cybersecurity. Internal evaluations indicated significant advancements in these areas, which could pose critical cyber capabilities, according to Mac Rumours.
The company's Preparedness Framework mandates enhanced safeguards when models could pose risks of severe harm. OpenAI is currently strengthening security controls and plans to implement additional safeguards before Astra can be deployed. These measures include restricting work on the model, using isolated testing environments, adding sandboxed execution, and expanding monitoring capabilities.
OpenAI is also collaborating with government agencies and AI safety organizations to ensure responsible deployment of Astra and future models.
Written by urgent.news from Economic Times Tech's reporting — not their text. Machine-written — it may contain errors, so check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
- OpenAI flags possible critical cybersecurity risk in upcoming model Astra, tightens controls dawn.com
- OpenAI flags possible critical cybersecurity risk in upcoming model, tightens controls businesstimes.com.sg
- OpenAI flags possible critical cybersecurity risk in upcoming model, tightens controls channelnewsasia.com
