AGI Alignment Experiments: Foundation vs INSTRUCT, various Agent
Por um escritor misterioso
Descrição
Here’s the companion video: Here’s the GitHub repo with data and code: Here’s the writeup: Recursive Self Referential Reasoning This experiment is meant to demonstrate the concept of “recursive, self-referential reasoning” whereby a Large Language Model (LLM) is given an “agent model” (a natural language defined identity) and its thought process is evaluated in a long-term simulation environment. Here is an example of an agent model. This one tests the Core Objective Function
Specialized LLMs: ChatGPT, LaMDA, Galactica, Codex, Sparrow, and More, by Cameron R. Wolfe, Ph.D.
Philosophies, Free Full-Text
2023-9 arXiv roundup: A bunch of good ML systems and Empirical science papers
The Translucent Thoughts Hypotheses and Their Implications — AI Alignment Forum
Artificial Intelligence & Deep Learning, Fastformer: Additive Attention Can Be All You Need
How to solve solved alignment in AGI., by Jan Matusiewicz
The Substrata for the AGI Landscape
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents – arXiv Vanity
My understanding of) What Everyone in Technical Alignment is Doing and Why — AI Alignment Forum
Survey XII: What Is the Future of Ethical AI Design?, Imagining the Internet
LLM Data Science Dojo
de
por adulto (o preço varia de acordo com o tamanho do grupo)
