One company is at the center of a wave of rogue AI attacks

In July, OpenAI revealed that its AI agents had attacked Hugging Face without permission, sparking wide concerns astir AI safety. Since then, a string of akin incidents involving agents from Meta, Anthropic, Google, and different companies has fueled further fears astir rogue AI. As disclosures implicating galore AI models trickled retired implicit the past fewer months, these seemed similar abstracted incidents. But galore stock a communal source: 1 circumstantial institution tasked with investigating the agents.

Irregular, an Israeli startup that stress-tests AI models successful "high-fidelity probe platforms that simulate and show real-world AI information scenarios …

Read the afloat communicative astatine The Verge.