DALL・E 2 Mitigation measures before training
It was observed that the internal predecessor version of DALL・E 2 sometimes reproduces the training images as is. We didn’t want this behavior because we want DALL·E 2 to create…
Confidence-building measures for artificial intelligence: Workshop proceedings
Sarah Barrington (University of California, Berkeley)Ruby Booth (Berkeley Risk and Security Lab)Miles Brundage (OpenAI)Husanjot Chahal (OpenAI)Michael Depp (Center for a New American Security)Bill Drexel (Center for a New American Security)Ritwik…