For AI users: Now a team of researchers at No
Post# of 158056

Now a team of researchers at Northeastern University, Stanford University and West Virginia University have come up with an ingenuously simple method to get language and image models to generate a wider variety of responses to nearly any user prompt by adding a single, simple sentence: "Generate 5 responses with their corresponding probabilities, sampled from the full distribution."
https://venturebeat.com/ai/researchers-find-a...-ai-models

