To ensure that AI systems remain safe as they start to exceed human capabilities, we’ll need to develop techniques for scalable oversight: the problem of supervising systems’ behavior without assuming that the overseer understands the task better than the system being trained.
AGENTS
-
Leveraging Model Capabilities While Maintaining Supervisory Control
By
–
This is tricky: To do this, we’ll need ways for the human who’s supervising the model to use any relevant knowledge or skills that the model already has, even though they can’t trust the model to be reliably helpful.
-
Path to Autonomous Learners in Deep Learning Research
By
–
The Path to Autonomous Learners Hanna Abi Akl : https://
arxiv.org/abs/2211.02403 #ArtificialIntelligence #DeepLearning #MachineLearning -
Would You Trust a Robot Chef to Cook Your Meals?
By
–
Would you let a robot chef cook for you? 🤖 🍲 👨🍳
— Bernard Marr (@BernardMarr) 7 novembre 2022
📽️ @gigadgets_ pic.twitter.com/6MJapxLbJRWould you let a robot chef cook for you? @gigadgets_
-
Prompt Engineering for AI Agents: Step-by-Step Operation Sequencing
By
–
The game is “least to most” — have it write out the most mechanical, reliably performed operations first. Then gradually move up to more interpretive and analytical steps, so it’s never asked to do anything multi-step in its head. The prompt should feel like an income tax form.
-
AGI Token Launch: Nodes Meet Agents for Economic Value
By
–
$AGI : AGI Token AGI Agents will likely generate transformative economic value: AGI Nodes X AGI Agents = AGI Token ($AGI) Hence, we’re preparing a new international organization and the AGI Token : $AGI http://
MONTREAL.AI: Winning the #AGI Race #AGI #MontrealAI -
AI Agents Presentation: Nodes and Tokens Framework
By
–
Here's another presentation: https://
montreal.ai/aiagents.pdf #AIAgent #AINode #AIToken -
Scaling Laws for Multi-Agent Reinforcement Learning
By
–
Scaling Laws for a Multi-Agent Reinforcement Learning Model Oren Neumann, Claudius Gros : https://
arxiv.org/abs/2210.00849 #ArtificialIntelligence #DeepLearning #ReinforcementLearning -
AGI Nodes Agents Token Generate Unprecedented Value
By
–
$AGI AGI Nodes X AGI Agents X AGI Token ($AGI) “The combination of the #AGINode, the #AGIAgent and the #AGIToken could generate unprecedented value.” — Vincent Boucher, President of http://
MONTREAL.AI http://
MONTREAL.AI: Winning the #AGI Race #AGI #MontrealAI -
Understanding Complexity Science for AI Systems
By
–
And to understand the science of complexity, this site is a great place to start. https://t.co/bv4wUcf51C
— Ethan Mollick (@emollick) 5 novembre 2022And to understand the science of complexity, this site is a great place to start.