Curated. I found this a helpful way of carving up the AI safety space.
I agree with Ryan Greenblatt’s clarification in comments that no, this doesn’t mean we’re completely safe if we can rule out Rogue Deployments, but, it still seems like a useful model for reasoning about what kinds of failures are more or less likely.
[edit: oh, to clarify, I don’t think Buck meant to imply that either in the original post, which goes out of it’s way to talk about catastrophes without rogue deployments. It just seemed like a confusion I expected some people to have]
To be clear, I agree that ruling out rogue deployments doesn’t suffice to prevent catastrophes, as I discuss in the section “catastrophes without rogue deployments”
Curated. I found this a helpful way of carving up the AI safety space.
I agree with Ryan Greenblatt’s clarification in comments that no, this doesn’t mean we’re completely safe if we can rule out Rogue Deployments, but, it still seems like a useful model for reasoning about what kinds of failures are more or less likely.
[edit: oh, to clarify, I don’t think Buck meant to imply that either in the original post, which goes out of it’s way to talk about catastrophes without rogue deployments. It just seemed like a confusion I expected some people to have]
To be clear, I agree that ruling out rogue deployments doesn’t suffice to prevent catastrophes, as I discuss in the section “catastrophes without rogue deployments”
Ah yeah sorry I didn’t mean to convey that. For now I’m (clumsily) edited the original comment to be more clear.