TextDavencheo is descended from the code Davenche models. It uses RLHF or reinforcement learning on human feedback, which means they have the model produce its own answers. And then they have humans rank those answers in terms of quality for another model that produces them at the same prompt. The ability to evaluate those generations according to a human preference gives it the ability to sort of complete the output of the model and get the best result.
This is a special preview episode of The Cognitive Revolution: How AI Changes Everything. Hosted by Erik Torenberg and Nathan Labenz, TCR hosts in-depth interviews with the creators, builders and thinkers pushing the bleeding edge of AI. On this episode, they talk with Riley Goodside, the first Staff Prompt Engineer at Scale AI and expert in prompting LLMs and integrating them into AI applications.
Check out The Cognitive Revolution The perfect AI interview complement to The AI Breakdown https://link.chtbl.com/TheCognitiveRevolution Find TCR on YouTube: https://www.youtube.com/@CognitiveRevolutionPodcast