OpenAI-agent hacker af sig selv australsk sundhedssystem: »Uacceptabelt«
Ingeniørenda
»Fejlrettet modelaktivitet« er OpenAIs betegnelse for den seneste hackingepisode udført med AI-agenter.
This is a short summary published by AI Global Wire. The full article is owned and hosted by Ingeniøren — open it there to read it in full.
Read the full story at Ingeniøren- OpenAI
- Agenter
Related AI news
- Meta gives its Muse AI agent video avatars, email addresses, and Mac controlThe Decoder · September 24, 2026
- Dataiku debuts cross-platform Agent Management, expands Cobuild building agentSiliconANGLE · September 24, 2026
- Stravito integrates market research into enterprise AI tools with MCP serverSiliconANGLE · September 24, 2026
- Australia to investigate if OpenAI hack of government health website broke the lawTechCrunch AI · September 24, 2026
- FBI investigating claim hackers have stolen details of all its agentsBBC Technology · September 24, 2026
- Kontext raises $4M to control what AI agents are allowed to do inside businessesSiliconANGLE · September 24, 2026