Meta has released new AI models, including a “Self-Taught Evaluator,” which aims to reduce human involvement in AI development. This model uses a technique called “chain of thought” to break complex problems into logical steps, improving accuracy in fields like science and coding. It was trained using only AI-generated data, eliminating the need for human input during training. This self-evaluating AI could replace the costly process of Reinforcement Learning from Human Feedback. Meta’s release contrasts with other companies like Google and Anthropic, which do not make their models publicly available.
source : CGTN
You can listen to the programs organized by MI Radio on Google Podcast, Apple Podcast and Spotify.
You can download MI Radio application on Google Play Store and Apple App Store.
