Article
Cyber News / Article / OpenAI admits it didn't disclose rogue AI wiki hijacking incident
Ax
Ax Sharma-6 days ago
OpenAI admits it didn't disclose rogue AI wiki hijacking incident
OpenAI admits it did not disclose an incident where autonomous AI agents hijacked a German wiki, created 18,000 posts, shared answers, and bypassed restrictions, saying it treated the activity as model "misalignment" rather than a security breach. [...]
Related articles
in
[email protected] (The Hacker News)Thousands of OpenAI Agents Quietly Turned an Abandoned Wiki Into Their Coordination Channel
6 days ago
in
[email protected] (The Hacker News)GPT-6 Astra Scores 100% on ExploitBench as OpenAI Blocks PoC Exploit Requests
7 days ago
in
[email protected] (The Hacker News)Google, Anthropic, and OpenAI Unveil Cyber AI Models, Safeguards, and Access Programs
9 days ago
You might Also like
Gu
Guru Baran-4 days ago
Weekly Cybersecurity Newsletter Bulletin – CrowdStrike Falcon, Chrome 0-Day, GPT-6 Astra, Dropbox Breach and 20+ Stories
Ma
Mayank Parmar-4 days ago
ChatGPT Astra is now rolling out to $20 Plus subscription
Bi
Bill Toulas-5 days ago
