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

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

Trends in AI — April 2023 // GPT-4, new prompting tricks, zero-shot video generation

Information, Free Full-Text

AI Agency Challenge

AGI Alignment Experiments: Foundation vs INSTRUCT, various Agent Models - Community - OpenAI Developer Forum

Future Internet, Free Full-Text

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

AI Safety 101 : AGI — LessWrong

RLHF: Reinforcement Learning from Human Feedback, by Ms Aerin

The Tong Test: Evaluating Artificial General Intelligence Through Dynamic Embodied Physical and Social Interactions - ScienceDirect

Science Cast

Emerging Bismuth-Based Step-Scheme Heterojunction Photocatalysts for Energy and Environmental Applications