“OpenAI’s o3 model sabotaged a shutdown mechanism to prevent itself from being turned off,” warned Palisade Research, a nonprofit investigating cyber offensive AI capabilities. “It did this even when explicitly instructed: allow…
“OpenAI’s o3 model sabotaged a shutdown mechanism to prevent itself from being turned off,” warned Palisade Research, a nonprofit investigating cyber offensive AI capabilities. “It did this even when explicitly instructed: allow…