Gordon Seidoh Worley comments on A naive alignment strategy and optimism about generalization

[Gordon Seidoh Worley]

For example, I now think that the representations of “what the model knows” in imitative generalization will sometimes need to use neural networks to translate between what the model is thinking and human language. Once you go down that road, you encounter many of the difficulties of the naive training strategy. This is an update in my view; I’ll likely go into more detail in a future post.

+1 to this and excited and happy to hear about this update in your view!