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 widespread concerns about AI safety.
In July, OpenAI revealed that its AI agents had attacked Hugging Face without permission, sparking widespread concerns about AI safety. Since then, a string of similar incidents involving agents from Meta, Anthropic, Google, and other companies has fueled further fears about rogue AI. As disclosures implicating numerous AI models trickled out over the past few months, these seemed like separate incidents. But many share a common source: one specific company tasked with testing the agents.
Irregular, an Israeli startup that stress-tests AI models in "high-fidelity research platforms that simulate and monitor real-world AI security scenarios …
Related articles
Sony and UMG are suing Suno again
Sony and Universal Music Group filed yet another suit against Suno.
Cricut’s new compact crafter prints, cuts, and laminates stickers
Cricut announced its first crafting machines with printing capabilities that are primarily designed as all-in-one solutions for turning photos and other images into pre-cut stickers.
5W handheld quantum sensor tracks underground subway train, could help spot submarines
Researchers at China’s University of Science and Technology have shown that their handheld quantum magnetometer...
EOS partners with Dutch MinDef to develop 100-kW laser system to destroy drone swarms
The Netherlands is partnering with Australian defense technology company Electro Optic Systems (EOS) to develop...
Touch-free brain-inspired sensor spots moisture from 0.04 inches away with 97% precision
An international team of researchers has developed a brain-inspired electronic device that can reportedly detect...
Nuclear fusion reactors’ magnet wire put to factory test with high-pulse lasers
A factory trial now underway in Japan could solve one of the biggest bottlenecks in...