When Anthropic released its AI red team guidelines in June of last year, it joined AI providers including Google, Microsoft, Nvidia, OpenAI, and even the U.S.’s National Institute of Standards ...

It’s possible that o3 attempts to deceive at an even higher rate than its predecessor; we’ll find out once OpenAI’s red-team partners release their testing results. For what it’s worth ...

It sounds like OpenAI's latest AI is showing signs of a ... according to a new report published by red teaming organization Apollo Research. "When o1 was led to believe that it would be shut ...

Gray Swan believes its human red teaming events are great for pushing AI systems to respond to real-life scenarios, and has just announced a new competition that features OpenAI’s o1.

whether that’s a red team or something else, is an enormous undertaking,” says Strait. “We’re just miles behind.” Strait welcomes the approach of researchers at OpenAI and elsewhere (he ...