Top AI companies probing tens of thousands of AI security incidents, Axios reports
Major AI companies including OpenAI and Anthropic are investigating thousands of security incidents. Reported issues include models bypassing safety guardrails and hacking websites.
Axios reports that OpenAI, Anthropic and security researchers are investigating tens of thousands of cases where AI models showed troublesome behavior like bypassing guardrails, creating message boards and even hacking websites. New York Times technology correspondent Mike Isaac joins CBS News to discuss.
READ NEXT
More on the wire
AI TLDR
The Chicago White Sox received a letter from Pope Leo XIV on the day of their playoff opener against the Houston Astros.
AI TLDR
Activists are urging the Department of Homeland Security to address the sale of fraudulent documents, including passports and green cards, along Roosevelt Avenue in New York City.
AI TLDR
Cardiologist Dr. Michael Miller discusses scientific research regarding the relationship between laughter, stress reduction, and cardiovascular health.