“Reading list on AI agents and associated policy” by Peter Wildeford

I put together this reading list on AI agents, with a tilt more towards AI governance. I hope it may be of help to others working on this area. If you know of other great resources or have comments on these resources, please say so in the comments! Top priority papers: OpenAI – Practices for Governing Agentic AI Systems OpenAI – Research into Agentic AI Systems Deepmind – The Ethics of Advanced AI Assistants Alan Chan et. al – Visibility into AI Agents (see also) A bit about the agents that currently exist: VisualWebArena: EVALUATING MULTIMODAL AGENTS ON REALISTIC VISUAL WEB TASKS WebVoyager : Building an End-to-End Web Agent with Large Multimodal Models METR: An update on our general capability evaluations Good background: METR – Autonomous replication threat models Evaluating Frontier Models for Dangerous Capabilities Introduction to Cooperative AI Governing AI Agents Peter's thoughts on AI loss of [...] --- First published: August 9th, 2024 Source: https://forum.effectivealtruism.org/posts/HYuoSzfHyuKrCGHrn/reading-list-on-ai-agents-and-associated-policy --- Narrated by TYPE III AUDIO.