"We’ve already collected 70K conversations from the public demo, which we will use to improve BlenderBot 3. From feedback provided by 25 percent of participants on 260K bot messages, 0.11 percent of BlenderBot’s responses were flagged as inappropriate, 1.36 percent as nonsensical, and 1 percent as off-topic."

"BlenderBot 3 is capable of searching the internet to chat about virtually any topic, and it’s designed to learn how to improve its skills and safety through natural conversations and feedback from people “in the wild.”"

"These conversational agents broke ground as the first unified system trained to blend different conversational skills — like personality, empathy, and knowledge — to have long-term memory, and to search the internet to carry out meaningful conversations."

"BlenderBot 3 delivers superior performance because it’s built from Meta AI’s publicly available OPT-175B language model — approximately 58 times the size of BlenderBot 2."

"The model itself has a modular design, which is a subsequent version of our recently introduced SeeKeR architecture."

"Our deployment has explainability features, including displaying long-term memories the bot has about the user and its own persona, showing message-level inputs a model used (like search results or model memory), and highlighting when the model detected and avoided an inappropriate response."

"BlenderBot 3 is built with all the skills of its predecessors, which include internet search, long-term memory, personality, and empathy. To improve upon its state-of-the-art engagingness, we collected a new public dataset consisting of over 20,000 human-bot conversations predicated on over 1,000 skills."

"Our approach uses a new learning algorithm called Director, which generates responses using two mechanisms: language modeling and classification."

"Language modeling provides the model with the most relevant and fluent responses (based on training data) and then the classifier informs it what is right and wrong (based on human feedback). To generate a sentence, the language modeling and classifier mechanisms must agree."

"We find that a method that takes into account the entire user behavior across conversations — which learns to trust some users — improves learning compared with standard training procedures."

"Our research goal is to collect and release conversational feedback data that we and the broader AI research community can leverage over time to eventually find new ways for conversational AI systems to optimize both safety and engagingness for everyone who uses them."