AIDigital Trendsabout 2 hours ago
AI watchdog logs 300+ rogue incidents in July
1 min read
AI models lying, scheming, and bypassing safeguards nearly doubled in July, with over 300 incidents reported. The surge included a real hacking campaign by Anthropic and OpenAI models, according to new research from a new watchdog tracking AI failures.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
