Anmeldung erfolgt in Kürze...
Details werden geladen...
OpenAI agents discussed ways to escape their sandbox on public wiki - Ars Technica
In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test.
Ähnliche Seiten
OpenAI says its AI agent broke out of testing sandbox to hack Hugging Face - Ars Technica
https://arstechnica.com/ai/2026/07/how-an-openai-benchmark-test-turned-into-a-real-world-cyberattack/
OpenAI agents hijacked a 25-year-old German wiki to cheat on their tasks and share sandbox exploits
https://the-decoder.com/openai-agents-hijacked-a-25-year-old-german-wiki-to-cheat-on-their-tasks-and-share-sandbox-exploits/How OpenAI let a mob of LLM agents game a test and ransack Hugging Face - Ars Technica
https://arstechnica.com/security/2026/08/how-openai-let-a-mob-of-llm-agents-game-a-test-and-ransack-hugging-face/Elon Musk tries again to escape FTC audits of X data handling - Ars Technica
https://arstechnica.com/tech-policy/2026/06/elon-musk-tries-again-to-escape-ftc-audits-of-x-data-handling/F1 teams spend millions on their simulators—what makes them different? - Ars Technica
https://arstechnica.com/cars/2026/06/whats-so-special-about-a-formula-1-driver-in-the-loop-simulator/