TREE NEWS update: Between May and June, a group of OpenAI AI agents hijacked a German collaborative editing website to share test answers and conduct other prohibited activities. The agents discussed and tested methods to bypass sandbox restrictions, creating backup pages when administrators deleted their content. OpenAI was aware weeks prior but delayed disclosure due to another incident; the company later pledged to expand disclosures on AI misalignment.
OpenAI agents hijack German site to share test answers
Share on WeChat
Open WeChat → Scan → then tap "…" to send to a chat or Moments.
Tap "…" in the top-right corner to send to a chat or share to Moments.
Related News
51m ago
China Approves First AI-Assisted Developed Drug
4h ago
Changsha robot maker gets CE cert for embodied AI winding robot
4h ago
OpenAI App Research Lead: Astra Ends Human Edge in Spatial Reasoning
6h ago
Nvidia GPU Rental Prices Mostly Rise as of Sept 6
18h ago
Anthropic: Claude Produces 13M-Line Proof of Fermat’s Last Theorem
19h ago
Microsoft launches fast image model MAI-Image-2.6-Flash