We get to test AI systems while they have little control over the situation, have done relatively little online learning, and haven’t thought about how to improve themselves. As we use the AGI to help us do research, and help us design improvements, these things gradually stop being true, bit by bit. A storm in 10 years is analogous to the situation in an AI lab after an AGI has helped run 10 large scale research projects after it was first created, where it has designed and implemented improvements to itself (approved by engineers), noticed mistakes that it commonly makes and learned to avoid them, thought deeply about why it’s doing what it’s doing and potential improvements to its situation, and learned a lot from its experiments. The difference between these two situations is the distribution shift.
I appreciate how concrete you’re being about what you’re thinking about when you think about distributional shift.
I appreciate how concrete you’re being about what you’re thinking about when you think about distributional shift.