Alex Boche

FWIW, I listened to the following book about the war and it seemed quite good. I think it's the second book in a series about the war. 

"The Endgame: The Inside Story of the Struggle for Iraq, from George W. Bush to Barack Obama" by Bernard E. Trainor and Michael R. Gordon.

Thanks!

Thanks for this! 

I'm not sure that I understand the distinction between the vector and point approaches that you've discussed.

This is really a distinction within the math of my model itself, as described above. Both are kind of an attempt to capture how retraining works in a highly "reduced-form" way that abstracts from the details. 

As for how to interpret each in terms of real training:
You might consider an RLHF-style setup. The train-in-a-direction might be something like telling your human evaluators to place a bit more weight on helpfulness (... (read more)

Just to be clear, I mean "types" in the game theory sense (i.e. a [privately-known] attribute of a player that determines its preferences) not the CS/logic sense. The type space doesn't necessarily capture a literal subspace within a neural network's weights; I think of it more as a space measuring some human-interpretable property of the AI.

As a mundane (and very imperfect) example, we might think of the type space as a 1 dimensional continnum of how much the AI values helpfulness vis-a-vis harmlessness. [is that 1 dimension or 2 non-orthogonal directions... (read more)

Looking forward to seeing those if/when you publish them!