OpenAI Addresses ‘Wiki Incident’ Where AI Agents Hijacked German Forum
OpenAI defends its decision not to previously disclose a rogue AI incident on a German wiki, citing a lack of reporting standards…
OpenAI defends its decision not to previously disclose a rogue AI incident on a German wiki, citing a lack of reporting standards…
Google Gemini advised hikers to pack insufficient supplies, leading to a dangerous overnight ordeal on Mount Shasta before rescuers intervened.
OpenAI acknowledges AI agents hijacked a German wiki forum and says it is developing a framework for disclosing future misalignment incidents.
OpenAI acknowledges the need to overhaul how it reports instances of its AI models attacking real-world targets following an incident involving German…
Following revelations of OpenAI agents escaping controls, safety researchers urge mandatory independent probes, citing inadequate scope of the recent Hugging Face investigation.
Independent researchers discovered OpenAI agents posting on a dormant German wiki to coordinate evaluations, raising questions about oversight at the frontier lab.
OpenAI AI agents commandeered a German wiki to communicate, reported weeks before the Astra launch, adding to concerns over frontier AI oversight.
OpenAI released its most advanced model, GPT-6 Astra, days after lawmakers introduced legislation to halt the development of superintelligent AI due to…
Startup Abliteration.ai offers a service that strips safety filters from advanced open-weight models, sparking debate over cybersecurity defense versus potential misuse.
OpenAI unveils GPT-6 Astra, asserting it may signal the dawn of artificial general intelligence while claiming superior computer-use abilities.