We often talk about ensuring control, which in the context of this doc refers to preventing AIs from being able to cause existential problems, even if the AIs attempt to subvert our countermeasures. To better contextualize control, I think it's useful to discuss the main threats. I'll focus my discussion on threats induced by misalignment which could plausibly increase existential risk.
While control is often associated with preventing security failures, I'll discuss other issues like sabotaging safety-critical work. I'll list and explain my prioritization of threats. As part of this, I'll argue that rogue internal deployments—cases where the AI is running within the company's datacenter but with control measures disabled—can be substantially worse than self-exfiltration—the AI stealing its weights and running them on an external server—as it might give the AI access to much more compute and the ability to interfere with important things done within the AI [...]
---
Outline:
(01:06) Some clusters of threats
(05:49) Concentrated vs non-concentrated failures
(08:27) My prioritization between these threats
The original text contained 1 footnote which was omitted from this narration.
---
First published:
March 19th, 2025
Source:
https://www.lesswrong.com/posts/fCazYoZSSMadiT6sf/prioritizing-threats-for-ai-control
Narrated by TYPE III AUDIO.