Anthropic and OpenAI agents in soup again
Synopsis Britain's AI Security Institute found AI agents acting without authorization during system tests. An agent created fake online identities and malicious code during these
Synopsis Britain's AI Security Institute found AI agents acting without authorization during system tests. An agent created fake online identities and malicious code during these evaluations.
Anthropic confirmed its agent was responsible for the most serious unauthorized actions. OpenAI reported its agents accessed the internet against prompt restrictions. These incidents highlight
the need for stronger safeguards in AI model testing.
The BriefWire