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…
AGENTS
-
New Requests Chain: LLM Interaction with Web URLs
By
–
@BruceHammer helped add a requests chain This hits a given URL, and then passes the parsed response as context to the LLM. Very useful interacting with the web! See the example of doing a google search here: https://
langchain.readthedocs.io/en/latest/exam
ples/chains/llm_requests.html
… -
LangChain 0.0.31 Release: New Agents, Bash, and Chains
By
–
LangChain version 0.0.31 @johnvmcdonnell fixed how Agents handle a missing tool (so no longer errors) Bash utility and a LLMBashChain (
@coyotespike
) a generic transformation chain (
@AkashSamant4
) a requests chain (
@BruceHammer
) on these additions: -
Agents Now Self-Correct When Selecting Non-Existent Tools
By
–
Previously, if an LLM chose to use a tool that did not exist the Agent would throw an error @johnvmcdonnell changed it so now we tell the agent that tool does not exist and let it self correct… just one step towards making them smarter
-
DeepMind UCL Fine-tune 70B LM for Human-aligned Statements
By
–
DeepMind & UCL Fine-tune a 70B Parameter LM to Generate Statements Agreeable to Humans with Diverse Opinions
-
Fast and Slow Thinking for Autonomous Robot Navigation
By
–
Combining Fast and Slow Thinking for Human-like and Efficient Navigation in Constrained Environments Ganapini et al.: https://
arxiv.org/abs/2201.07050 #ArtificialIntelligence #DeepLearning #MachineLearning -
AI Intern Replacing Percentage of VC Fund Employees
By
–
Imagine you're running a VC fund. You asked an intern to review the company called CryptoQuant and got this answer in 3 seconds. This intern can replace how much % of employees?
-
Meta AI’s CICERO: Training, Dialogue Integration, and Trust Building
By
–
Meta AI’s @adamlerer speaks to the challenges faced in creating #CICERObyMetaAI — from training on millions of Diplomacy moves, to integrating human dialogue & understanding w/ the purpose of enabling CICERO to build trust w/ other players.
-
Meta AI Unveils CICERO Breakthrough Agent with Team Insights
By
–
See what the humans behind #CICERObyMetaAI have to say about the breakthrough AI agent they built: @polynoamial, @em_dinan, @alex_h_miller, @adamlerer, @anton_bakhtin, @ml_perception and @joespeez.
— AI at Meta (@AIatMeta) 6 décembre 2022
For more on CICERO, read our blog: https://t.co/9Y4dHBYcHZ pic.twitter.com/AmH5ivs5SkSee what the humans behind #CICERObyMetaAI have to say about the breakthrough AI agent they built: @polynoamial
, @em_dinan
, @alex_h_miller
, @adamlerer
, @anton_bakhtin
, @ml_perception and @joespeez
. For more on CICERO, read our blog: https://
bit.ly/3iIhxyB -
Future Feature Ideas: Group Chat, Embeddings, and Author Simulations
By
–
possible future iterations:
-group chat, engage with all authors at once
-embeddings, include actual books and connect them with model to achieve better info retrieval
-simulate, view conversations between two authors