OpenAI claims to have mitigated bias and toxicity in GPT-3

In a study published today, OpenAI, the lab best known for its research on large language models, claims it's discovered a way to improve the "behavior" of language models with respect to ethical, moral, and societal values. The approach, OpenAI says, can give developers the tools to dictate the tone and personality of a model depending on the prompt that the model's given. Despite the potential of natural language models like GPT-3, many blockers exist. The models can't always answer math problems correctly or respond to questions without paraphrasing training data, and it's well-established that they amplify the biases in data on which they were trained. That's problematic in the language domain, because a portion of the data is often sourced from communities with pervasive gender, race, and religious prejudices.