In the new paper Towards Healthy AI: Large Language Models Need Therapists Too, a team from Columbia University and IBM Research proposes SafeguardGPT, a framework that incorporates psychotherapy and reinforcement learning to correct the potentially harmful behaviours of AI chatbots.
Colossal-AI open sources a complete RLHF pipeline that includes supervised data collection, supervised fine-tuning, reward model training, and reinforcement learning fine-tuning, based on the LLaMA pre-trained model, and shares ColossalChat, the most practical open-source project that closely resembles the original ChatGPT technical solution!
In the new paper BlenderBot 3: A Deployed Conversational Agent That Continually Learns to Responsibly Engage, researchers from Meta AI and Mila/McGill University release BlenderBot 3, a 175B parameter state-of-the-art open-domain dialogue model deployed on a public website. BlenderBot 3 is designed for continual learning via its user interactions.
In the new paper Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent, a Stanford NLP research team presents Chirpy Cardinal, an open-domain conversational social chatbot with emotional and social intelligence that enables authentic and engaging interactions with real people.
Writers often get their inspiration from conversations with other people. So says 19-year-old Katie Bilbrey, who has published 15 online stories under the pen name TheSolSoldier. Bilbrey took a different tact for her latest writing project — instead of back-and-forthing with friends, she drew her inspirations for Our Precious Future through conversations with an artificial intelligence named Zo.
Google and Amazon unveiled mini-sized smart speakers Google Home Mini Chalk and Amazon Echo Dot 2, both priced at less than US$50. Virtual assistants can plug into your environment with a natural human-machine voice interface that used to exist only science fiction.