Testing robustness against unforeseen adversaries
We’ve developed a method to assess whether a neural network classifier can reliably defend against adversarial attacks not seen during training. Our method yields a new...
WeiterlesenMonth: August 2019
GPT-2: 6-month follow-up
We’re releasing the 774 million parameter GPT-2 language model after the release of our small 124M model in February, staged release of our medium 355M model in May, and subsequent...
Weiterlesen
Learning Day
At OpenAI, each Thursday is Learning Day: a day where employees have the option to self-study technical skills that will make them better at their job...
Weiterlesen