The minimal model may be the model most agents performing unsupervised learning on human generated data learn.
Alternatively, most other models imply the minimal model.
This tells us how we get that model but not what one can use it for.
I think using such a model as an optimisation target would be existentially safe.
The minimal model may be the model most agents performing unsupervised learning on human generated data learn.
Alternatively, most other models imply the minimal model.
This tells us how we get that model but not what one can use it for.
I think using such a model as an optimisation target would be existentially safe.