Why imperfect adversarial robustness doesn't doom AI control

blog.redwoodresearch.org · 1,328 words · saved by 1 readers

(thanks to Alex Mallen, Cody Rushing, Zach Stein-Perlman, Hoagy Cunningham, Vlad Mikulik, and Fabien Roger for comments) Sometimes I hear people argue against AI control as follows: if your control measures rely on getting good judgments from "trusted" AI models, you're doomed because AI models aren't adversarially robust. I agree that better adversarial robustness would definitely help with control, but I think this argument misses several important points; my overall take is that current levels of adversarial robustness don’t come close to dooming AI control. The first and most important point is that adversarial robustness is normally researched in a setting that’s much easier for the adversary. In most discussions, if an adversary can ever get a model to do something bad—even after many attempts and with a low success rate—this counts as a failure. But in real control settings, an AI that tries and fails to jailbreak might get caught, which is bad for its chances of success. In add

Why imperfect adversarial robustness doesn't doom AI control There are crucial disanalogies between preventing jailbreaks and preventing misalignment-induced catastrophes. Buck Shlegeris Nov 18, 2024 5 3 Share (thanks to Alex Mallen, Cody Rushing, Zach Stein-Perlman, Hoagy Cunningham, Vlad Mikulik, and Fabien Roger for comments) Sometimes I hear people argue against AI control as follows: if your control measures rely on getting good judgments from "trusted" AI models, you're doomed because AI models aren't adversarially robust. I agree that better adversarial robustness would definitely help

Why imperfect adversarial robustness doesn't doom AI control

related reading