Meta AI presents CICERO — the first AI to achieve human-level performance in Diplomacy, a strategy game which requires building trust, negotiating and cooperating with multiple players. Learn more about #CICERObyMetaAI: http://
bit.ly/3GBwLzx
AGENTS
-
Meta AI Introduces CICERO: First AI Achieving Human-Level Diplomacy Performance
By
–
-
LangChain 0.0.16: Chain Input/Output Comparison and Model Evaluation
By
–
version 0.0.16: compare inputs/outputs on a whole chain Useful for evaluation when you're doing more than just a simple call to an LLM Github: https://
github.com/hwchase17/lang
chain
… How do different models do in @OfirPress
's self-ask w/ search example? https://
colab.research.google.com/drive/1atz4xfZ
LpIHJKD2kf38WnxHv61XU-dwb
… -
Mispredicting scaling potential: Early distraction with reinforcement learning
By
–
But I still mispredicted in how much fertile ground there was in scaling up the paradigm. Like many others in AI I got distracted by Reinforcement Learning too soon, a kind of putting the cart before the horse, …
-
Automated Companies Powered Entirely by LLMs Communicating via Text
By
–
automated companies made up just of LLMs (CEO LLM, manager LLMs, IC LLMs), running asynchronously and communicating over a Slack-like interface in text…
-
LLMs as Cognitive Engines Orchestrating Compute Infrastructure via Text
By
–
Good post. A lot of interest atm in wiring up LLMs to a wider compute infrastructure via text I/O (e.g. calculator, python interpreter, google search, scratchpads, databases, …). The LLM becomes the "cognitive engine" orchestrating resources, its thought stack trace in raw text
-
People are unpredictable compared to rockets
By
–
Also, I didn't say rockets weren't hard! Just that people are vastly harder because they are inherently unpredictable and no set of inputs will ever produce the same outputs
-
Simulating All Possibilities to Avoid Being Wrong
By
–
This is why I simulate all possibilities, so I’m technically never wrong.
-
Inspiration from Ajeya Cotra’s Sandwiching Concept in Research
By
–
This paper was heavily inspired by prior work, especially Ajeya Cotra's 'sandwiching' concept: