TGViewer
BleepingComputer BleepingComputer @bleepingcomputer · 11.6K subscribers
Post #25487 995
 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. [...]

https://www.bleepingcomputer.com/news/security/openai-admits-it-didnt-disclose-rogue-ai-wiki-hijacking-incident/
BleepingComputer 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.
Open in Telegram All posts from @bleepingcomputer
More from @bleepingcomputer
  1. Oct 17, 2026Hackers breach Microsoft 365 tenants via ConnectWise supply-chain attack ConnectWise has s…
  2. Oct 17, 2026Drupal patches critical RCE flaws, warns exploits may emerge soon Drupal has patched two c…
  3. Oct 16, 2026Critical BlockStrap flaw lets hackers run code on Magento servers Researchers warn that ha…
  4. Oct 16, 2026Zero-click attacks used targeted ads to deliver Candiru spyware Candiru spyware was delive…
  5. Oct 16, 2026Employees using personal ChatGPT at work? Here's what IT admins need to do Employees using…
  6. Oct 16, 2026Burger King Japan data breach exposes 11 million customer records Burger King Japan, the J…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →