The New Chat Bots Could Change the World. Can You Trust Them?
AGENTS
-
CICERO Learns Optimal Moves Using Reinforcement Learning
By
–
Meta AI’s @anton_bakhtin discusses how he and his team used Reinforcement Learning to teach CICERO the best moves for the millions of possible actions that could be made on any given board state. pic.twitter.com/W8SJKDz6Vf
— AI at Meta (@AIatMeta) 10 décembre 2022Meta AI’s @anton_bakhtin discusses how he and his team used Reinforcement Learning to teach CICERO the best moves for the millions of possible actions that could be made on any given board state.
-
Meta AI Reveals CICERO Components: Game Planning, Dialogue, Filtering
By
–
Meta AI’s @ml_perception reveals what was used to build CICERO: Theoretical game planning component Dialogue model Component filtering out any dialogue mistakes before messages are sent to players
-
Simple conversation buffer memory with dynamic N adjustment
By
–
it is pretty simple at the moment – just keeps a buffer of the past N conversations in memory. a pretty simple improvement would be dynamically adjusting N based on the length of the conversations
-
Dynamic conversation context length determination in LangChain
By
–
excited to hear your thoughts/ideas! right now its pretty simple: just take the last N lines of conversation. but a very natural extension to determine N dynamically based on their length
-
Building Powerful Long-Term Memory for AI Agents
By
–
Hard to say without knowing more, but I’d guess you’d want to think deeply about how you might build a really powerful long-term memory.
-
CICERO’s Surprising Ability to Be an Excellent Strategic Ally
By
–
What surprised @polynoamial most about CICERO? Its ability to be a great ally. With built-in strategic reasoning & natural language, #CICERObyMetaAI can understand and help its allies achieve their goals.
-
CICERO: Meta AI’s Language Model for Human Cooperation
By
–
Meta AI’s @em_dinan explains what makes CICERO different from other language models. Its ability to cooperate with humans through natural language, Its grounding in specific intentions and plans for the game board.
-
CICERO by Meta AI Ranked Top 10% in Online League Games
By
–
…and ranked in the top 10% of participants who played more than one game in an online league. Learn more about CICERO’s win rate: https://
bit.ly/3HigP5J Do you think you could outplay #CICERObyMetaAI? -
CICERO by Meta AI Wins at Diplomacy Against Human Players
By
–
It’s not just that #CICERObyMetaAI can play Diplomacy with humans, it’s also that it often WINS: In online games, CICERO achieved more than double the average score of human players…