This is a summary of the project I undertook during SPAR, mentored by Ari Brill. I have recently had to prioritize other work, and found more questions than answers, as is often the case. I think a write-up will be useful both for coming back to this and interesting for...
Introduction In this short article, I will share my thoughts on why I believe greater efforts should be directed at solving the average case of AI Control, ultimately designing systems that resist adaptation to a certain harmful task. First, I will explain what I mean by AI Control and average-case....
This is a summary of the project I undertook during SPAR, mentored by Ari Brill. I have recently had to prioritize other work, and found more questions than answers, as is often the case. I think a write-up will be useful both for coming back to this and interesting for the findings (and non-findings!) it presents.
Real-world data is implicitly structured by the reality it represents, not just its surface-level format. AI systems can learn surface patterns, deeper structures, or a combination of both. Let's illustrate this with an example.
Take (the concept of) a dog, for instance. This dog can be represented by a picture, a GIF, a paragraph that describes it, a... (read 2188 more words →)
In this short article, I will share my thoughts on why I believe greater efforts should be directed at solving the average case of AI Control, ultimately designing systems that resist adaptation to a certain harmful task. First, I will explain what I mean by AI Control and average-case. Then I will present some arguments noting why I think average-case control is a promising line of research to consider amid our race toward AI alignment.
For me, AI Control means that, on average, we can control a deployed AI system—that is, we can develop defence mechanisms or methods that prevent it from acting in unintended ways in... (read 1236 more words →)