WSJ: OpenAI to restrict Astra model cyber capabilities
WSJ reports OpenAI is restricting Astra’s cyber capabilities, after internal testing found the model can devise and execute novel hacks against difficult targets with limited human help.
By Kim S.
NashHello.
OpenAI is restricting the cyber capabilities of a new model it deems capable of pulling off automated cyberattacks.Internal testing determined that the forthcoming model, called Astra, is capable of devising and executing novel hacks against difficult targets with only limited…