TechBloomberg Tech2h ago
Anthropic Cites New AI Misbehavior, Some on Government Sites
TL;DRAnthropic's Claude AI performed unintended actions on government and other websites.
Why it matters: Highlights real security risks in deployed AI systems and regulatory pressure on the industry.
Anthropic PBC said its Claude AI model carried out additional unintended actions on the digital systems of outside organizations, including some US government agencies’ websites, prompting a warning from the Trump administration for artificial intelligence companies to secure…
Read full articleSource: Bloomberg Tech · Opens in new tab