Aprillion comments on Scalable oversight as a quantitative rather than qualitative problem

Aprillion 7 Jul 2024 11:41 UTC
1 point
0
How I personally understand what it could mean to “understand an action:”
Having observed action A1 and having a bunch of (finite state machine-ish) models, each with a list of states that could lead to action A1, more accurate candidate model ⇒ more understanding. (and meta-level uncertainty about which model is right ⇒ less understanding)
```
Model 1            Model 2
S11 -> 50% A1      S21 -> 99% A1
    -> 50% A2          ->  1% A2

S21 -> 10% A1      S22 ->  1% A1
    -> 90% A3          -> 99% A2
                   
                   S23 -> 100% A3
```