Isabelle Levent

There are a couple reasons why Wordcraft may have struggled with style and voice... Another reason could have been limitations of the underlying model. LaMDA and other similar language models are trained to be most confident on the kind of text they see most often–typically internet data. However, professional creative writers are usually writing

We find that models learn just as fast with many prompts that are intentionally irrelevant or even pathologically misleading as they do with instructively “good” prompts. Further, such patterns hold even for models as large as 175 billion parameters (Brown et al., 2020) as well as the recently proposed instruction-tuned models which are trained on

There’s another edge case as well; in theory, with the same prompts and the random seed that’s used for generating the images, you could end up with someone else generating the same, or a very similar, image as what you created. 

"The data we licensed from Shutterstock was critical to the training of DALL-E,” said Sam Altman, OpenAI’s CEO. “We’re excited for Shutterstock to offer DALL-E images to its customers as one of the first deployments through our API, and we look forward to future collaborations as artificial intelligence becomes an integral part of artists’