flâneur

7+ tractable directions in AI control — LessWrong

lesswrong.com · 4,121 words · saved by 1 readers

In this post, we list 7 of our favorite easy-to-start directions in AI control. (Really, projects that are at least adjacent to AI control; We include directions which aren’t as centrally AI control and which also have other motivations.) This list is targeted at independent researchers who don't necessarily have a ton of context on AI control (but have at least some context via e.g., having read some of our posts on control) and who don't want to do infrastructure and compute heavy experiments. In the final section, we also list 3 additional directions that are probably a bit more challenging but still tractable. We’ll mostly be highlighting and expanding upon areas that Ryan discussed in an earlier post: An overview of areas of control work. We don’t discuss work on constructing control settings or iterating on methods within control settings because we think good work of that type currently requires somewhat more context. However, Control Arena and other projects might mean that ite

x 7+ tractable directions in AI control — LessWrong AI Control AI Frontpage 93 7+ tractable directions in AI control by Julian Stastny , ryan_greenblatt 28th Apr 2025 AI Alignment Forum 16 min read 1 93 Ω 52 In this post, we list 7 of our favorite easy-to-start directions in AI control. (Really, projects that are at least adjacent to AI control; We include directions which aren’t as centrally AI control and which also have other motivations.) This list is targeted at independent researchers who don't necessarily have a ton of context on AI control (but have at least some context via e.g., havi

related reading