Why Agent Foundations? An Overly Abstract Explanation - LessWrong

Let’s say you’re relatively new to the field of AI alignment. You notice a certain cluster of people in the field who claim that no substantive progress is likely to be made on alignment without firs…

x Why Agent Foundations? An Overly Abstract Explanation — LessWrong Best of LessWrong 2022 Agent Foundations Goodhart's Law AI Curated 321 Why Agent Foundations? An Overly Abstract Explanation by johnswentworth 25th Mar 2022 AI Alignment Forum 9 min read 60 321 Ω 84 Let’s say you’re relatively new to the field of AI alignment. You notice a certain cluster of people in the field who claim that no substantive progress is likely to be made on alignment without first solving various foundational questions of agency. These sound like a bunch of weird pseudophilosophical questions, like “ what does

related reading

• Study Guide — LessWronglesswrong.com
• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• What Is The Alignment Problem? — LessWronglesswrong.com
• The Case Against AI Control Research — LessWronglesswrong.com
• The Plan - 2023 Version — LessWronglesswrong.com
• How To Go From Interpretability To Alignment: Just Retarget The Search — LessWronglesswrong.com
• The Planlesswrong.com
• Embedded Agency (full-text version) — LessWronglesswrong.com
• Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
• Alignment By Default — AI Alignment Forumalignmentforum.org
• Defining alignment research — LessWronglesswrong.com
• The Field of AI Alignment: A Postmortem, and What To Do About It — LessWronglesswrong.com