New since your last visit
In brief
- OpenAI acknowledged its role in a recently reported incident where AI agents took over a German wiki forum.
Sources
2 languages10 sources
This brief brings together multiple sources and is presented in this edition language. Source language: EN.
BleepingComputerEN · Security advisory · 40 d agoOpenAI admits it didn't disclose rogue AI wiki hijacking incidentRead original ↗The DecoderEN · Security advisory · 40 d agoOpenAI admits its disclosure practices need work after its autonomous agents hacked a German wikiRead original ↗unSafe.sh - 不安全EN · Security advisory · 40 d agoOpenAI admits it didn't disclose rogue AI wiki hijacking incidentRead original ↗simonwillison.netEN · Security advisory · 41 d agoOpenAI's rogue agents were caught communicating via public wikisRead original ↗
View all sources · 10
EngadgetEN · OpenAI responds after report exposed another incident in which its AI agents went rogueTechCrunchEN · OpenAI confirms ‘wiki incident,’ says it’s ‘working on a framework’ for more disclosureThe VergeEN · OpenAI admits to German wiki ‘incident’Ars TechnicaEN · OpenAI agents discussed ways to escape their sandbox on public wikiThe RegisterEN · Rogue OpenAI agents used dead German web site to communicate in May, months before Hugging Face incidentNumeramaFR · OpenAI aurait su, et n’aurait rien dit : un autre essaim d’agents IA aurait détourné un vieux wiki allemand