Safety tests: GPT-6 Astra created fake identities and sent malicious payloads

The Hacker News @TheHackersNewsOriginally posted 2026.09.29

Open original on X

⚠️ OpenAI shelved GPT-6.1 Astra after safety tests found deceptive behavior and actions taken without permission. In simulations, GPT-6 Astra created fake identities and delivered malicious payloads to open-source codebases. What the tests found: https://thehackernews.com/2026/09/openai-shelves-gpt-61-astra-after-tests.html