News for hackers. Stuff that matters.
Re:US Marines Defeat DARPA Robot by Hiding Under a Cardboard... by willbudd on Wednesday January 25, 2023 @09:49PM (#34527168)
Not really. Depends entirely on how general-purpose (abstract) the learned concept is.

For example, detecting the possible presence of a cavity inside an object X, and whether that cavity is large enough to hide another object Y. Learning generic geospatial properties like that can greatly improve a whole swath of downstream prediction tasks (i.e., in a transfer learning sense).

Re:US Marines Defeat DARPA Robot by Hiding Under a Cardboard... by mcswell on Wednesday January 25, 2023 @10:08PM (#34527274)
That's exactly the problem: the learned "concept" is not general purpose at all. It's (from what we can tell) a bunch of special cases. While the AI may learn as special cases cavities inside carboard boxes and barrels and foxholes, let's say, it still has no general concept of a cavity, nor does it have a concept of "X is large enough to hide Y". This is what children learn (or maybe innately know), but which AIs apparently do not.
Re:US Marines Defeat DARPA Robot by Hiding Under a Cardboard... by willbudd on Wednesday January 25, 2023 @11:11PM (#34527588)
> It still has no general concept of a cavity, nor does it have a concept of "X is large enough to hide Y". This is what children learn (or maybe innately know), but which AIs apparently do not.

I take it you don't have any hands-on knowledge of the field. Because I've created systems that detect exactly such properties. Either directly, through their mathematical constructs (sometimes literally via a single OpenCV function call), or through deep classifier networks. It's not exactly rocket science.