[andreasvc]

I would just like to say that that has absolutely nothing to do with anything by Gödel or Turing. There definitely can exist machine learning algorithms which continually adapt, and I see no technical reason why you couldn't try and model human agency as well. The work by Gödel and Turing you're thinking of is about _formal_ systems such as logic or computer programs, and while it is very common for people to turn (i.e., abuse) their results into a metaphor with seemingly broader implications, this is actually a mistake; their proofs simply don't hold under those more general circumstances.

[cs702]

andreasvc: AFAIK, there is no program in existence today that can successfully model "human agency" (as you put it). Wouldn't that require major breakthroughs in AI?

And my understanding from chatting with friends in the fraud-detection space is that, while current state-of-the-art machine-learning systems can successfully adapt to the data they obtain from users, they cannot adapt to users learning to game or 'route around' the system -- at least not without programmer intervention 'from above.'

The link to Gödel and Turing I saw is that solving this problem without intervention 'from above' would require a computer program that can successfully model itself as it interacts with humans, but then we run into those two guys, no?

[andreasvc]

Yes I see the superficial resemblance with Gödel and Turing, but it's not more than that. The reason I insist on that is because the value of their theorems lies in the fact that they have been mathematically proven, and the proof only holds in very particular conditions. Basically, a system that is strong enough to prove statements about arithmetic cannot prove its own consistency. This hypothesis about the difficulty of certain machine learning tasks is a conjecture, at best. I don't think you could prove it, and if you could, it would look very different from the incompleteness proof. I think it has to do with certain AI problems being hard, but this is a rather vague notion; perhaps we simply lack certain concepts or mathematical tools. The important thing about the incompleteness proofs is that that is completely ruled out: given the right formal conditions, certain things are absolutely impossible to do.

[rhizome]

The trajectories of adaptation then become second-and-beyond-order problems that in turn fall out of sync with reality.

[andreasvc]

I'm puzzled by this statement. The adaptation happens in reality, right? So how could their trajectories be out of sync with reality?