Source Alignment Forum · Published · Open the original ↗
Lab notes
Monitorability evaluations and policy proposals
There has been a lot of discussion recently of policy proposals around monitorability, such as Redwood's proposal and my counter-proposal . I'd like to say a bit more generally about how I'm thinking about monitorability. Note that nothing here is an official Anthropic position; these are just my personal thoughts.
First, a categorization. I currently think about four different types of monitorability:
Second, some notes on trustedness, which is currently my biggest conceptual uncertainty with how to think about monitorability. A basic fact that is true about at least all of the non-diffuse forms of monitorability is that you should be able to in some sense get a perfect score by just using the same model as the monitor and policy. That is because for any bad thing that the policy can think to do, if the monitor is the same model, it too should be able to come up with and detect that.
The opening of the post, quoted unchanged from Alignment Forum. The full text continues at the source.