World

OpenAI launches AI capable of conducting cyberattacks with limitations

OpenAI has announced the launch of its AI model Astra, which can conduct cyberattacks but is equipped with a monitoring system.

2 September 2026Tagblick Newsdesk

AI-generatedWritten by an AI system, editorially responsible — how we work

Archive photo: OpenAI launches AI capable of conducting cyberattacks with limitations — Archive photoPhoto: Ehécatl Cabrera · Wikimedia Commons · CC BY-SA 4.0

OpenAI announced on Tuesday the launch of its new artificial intelligence model, named Astra. This model is capable of autonomously conducting cyberattacks, successfully breaching well-protected systems.

The Astra model will be accompanied by a monitoring system designed to limit its actions, allowing for the interruption of any activities that may be deemed dangerous or unauthorized.

This initiative from OpenAI raises new considerations regarding security and ethics in the use of artificial intelligence technologies, given the potential of this model in sensitive contexts. The announcement raises questions about the control and regulation of such technology.

This item was written by an AI system on the basis of the headlines and short teasers of the independently operating newsrooms named below. We disclose this under Art. 50(4), second subparagraph, of Regulation (EU) 2024/1689 (AI Act). Before publication we check origin and verifiability — anything that appears in only one place is not published — as well as language, substance and legally sensitive content. No separate substantive review of each individual item by a natural person takes place; we therefore do not rely on the exemption in Art. 50(4), second subparagraph, of the AI Act. Editorial responsibility for this publication rests with the person named in the imprint (§ 18 Abs. 2 MStV). Please report errors to [email protected] — we will correct or remove the item. Full reports are available from the sources listed.