AGI Alignment Experiments: Foundation vs INSTRUCT, various Agent

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

A new era of AI: a practical guide to Large Language Models - Unit8

Specialized LLMs: ChatGPT, LaMDA, Galactica, Codex, Sparrow, and More, by Cameron R. Wolfe, Ph.D.

Opinion Paper: “So what if ChatGPT wrote it?” Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy - ScienceDirect

AI Safety 101 : Reward Misspecification — LessWrong

leewayhertz.com-Auto-GPT Unleashing the power of autonomous AI agents.pdf

What Does It Mean to Align AI With Human Values?

AI Agency Challenge

AI Foundation Models. Part II: Generative AI + Universal World Model Engine

My understanding of) What Everyone in Technical Alignment is Doing and Why — AI Alignment Forum