Also -- if there's no surprise, then it's not science, right? This is why I describe this as something more like robot ethnography.
I strongly disagree with this view on science. It's extremely valuable to scientifically validate prior assumptions.
On the other hand, this work isn't even framed as a generalizable assumption that needed to be validated. It seems to me to be "just another example of how AI systems can be strategically deceptive for self-preservation."
Really? You're saying that as long as you assume something is true, there's no value in finding out if it's actually true or not?
I am equating learning to surprise, though you could disagree with semantics.
However, there isn't time to test out every single assumption we could generally have.
Therefore, the more worthwhile experiments are ones where we learn something interesting no matter what happens. I'm equating this with "surprise," as in, we have done some meaningful gradient descent or Bayesian update, we've changed our views, we know something that wasn't obvious before.
You could disagree with semantics there, but hopefully we agree with the idea of more vs. less valuable experiments.
I'm just not sure whose model of LLM dynamics was updated by this paper. Then again, I only listened to a couple minutes of their linked YouTube discussion before getting bored.