In my plan, interpretable world-modeling is a key component of Step 1, but my idea there is to build (possibly just by fine-tuning, but still) a bunch of AI modules specifically for the task of assisting in the construction of interpretable world models. In step 2 we’d throw those AI modules away and construct a completely new AI policy which has no knowledge of the world except via that human-understood world model (no direct access to data, just simulations). This is pretty well covered by your routes numbered 2 and 3 in section 1A, but I worry those points didn’t get enough emphasis and people focused more on route 1 there, which seems much more hopeless.
Ah, now it makes sense. I was wondering how world model interpretability leads to alignment rather than control. After all, I don’t think you will get far controlling something smarter than you against its will. But alignment of value could scale with large gaps in intelligence.
When that 2nd phase, there are a few things you can do. E.g the 2nd phase reward function could include world model concepts like “virtue”, or you could modify the world model before training.
In my plan, interpretable world-modeling is a key component of Step 1, but my idea there is to build (possibly just by fine-tuning, but still) a bunch of AI modules specifically for the task of assisting in the construction of interpretable world models. In step 2 we’d throw those AI modules away and construct a completely new AI policy which has no knowledge of the world except via that human-understood world model (no direct access to data, just simulations). This is pretty well covered by your routes numbered 2 and 3 in section 1A, but I worry those points didn’t get enough emphasis and people focused more on route 1 there, which seems much more hopeless.
Ah, now it makes sense. I was wondering how world model interpretability leads to alignment rather than control. After all, I don’t think you will get far controlling something smarter than you against its will. But alignment of value could scale with large gaps in intelligence.
When that 2nd phase, there are a few things you can do. E.g the 2nd phase reward function could include world model concepts like “virtue”, or you could modify the world model before training.