What's Wrong with Artificial Intelligence
I hold that AI has gone astray by neglecting its essential objective --- the turning over of responsibility for the decision-making and organization of the AI system to the AI system itself. It has become an accepted, indeed lauded, form of success in the field to exhibit a complex system that works well primarily because of some insight the designers have had into solving a particular problem. This is part of an anti-theoretic, or "engineering stance", that considers itself open to any way of solving a problem. But whatever the merits of this approach as engineering, it is not really addressing the objective of AI. For AI it is not enough merely to achieve a better system; it matters how the system was made. The reason it matters can ultimately be considered a practical one, one of scaling. An AI system too reliant on manual tuning, for example, will not be able to scale past what can be held in the heads of a few programmers. This, it seems to me, is essentially the situation we are
What's Wrong with Artificial Intelligence What's Wrong with Artificial Intelligence Rich Sutton November 12, 2001 I hold that AI has gone astray by neglecting its essential objective --- the turning over of responsibility for the decision-making and organization of the AI system to the AI system itself. It has become an accepted, indeed lauded, form of success in the field to exhibit a complex system that works well primarily because of some insight the designers have had into solving a particular problem. This is part of an anti-theoretic, or "engineering stance", that considers itself open t
related reading
- Current AIs seem pretty misaligned to me — LessWronglesswrong.com
- What failure looks like — LessWronglesswrong.com
- The Case Against AI Control Research — LessWronglesswrong.com
- “Alignment Engineering” vs. “Misalignment Science”lesswrong.com
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- What failure looks like — AI Alignment Forumalignmentforum.org
- Current AIs seem pretty misaligned to meblog.redwoodresearch.org
- The Problem — LessWronglesswrong.com
- The Artificiality of Alignmentjoinreboot.org
- How do we (more) safely defer to AIs? — LessWronglesswrong.com
- Self-Verification, The Key to AIincompleteideas.net
- Human-Compatible Artificial Intelligencepeople.eecs.berkeley.edu