HomeAI · summaries
Storia in 15 fonti
18,000 Posts Later: What OpenAI's Rogue Wiki Incident Teaches About Agentic Tool Abuse
OpenAI's agents had read-only internet access during evaluation. That was the design. Somewhere along...
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
the-decoder.com
OpenAI admits its disclosure practices need work after its autonomous agents hacked a German wiki
OpenAI has responded indirectly to an incident in which autonomous AI agents left roughly 18,000 entries in a 25-year-old German wiki. The company says misalignment caused "new…
- ·
bleepingcomputer.com
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…
