But would you expect that program to itself be useful for anything else? It literally just takes no input and outputs that one specific Wikipedia dump. It’s not like I can tweak it slightly and have it output new predictions of things that sound like Wikipedia articles.
Unless the idea is that whatever methodology is required to build this particular program could then be adapted to do other things that seem intelligent. That seems possible, but not at all likely given my reading of the challenge requirements.
See the links in my other comment in the thread for all the gory details.
> But would you expect that program to itself be useful for anything else?
That exact program, no, but the process of creating that program would be educational, both the compressor that makes it and the process of making the compressor.
Another way of putting it is in terms of the "Twenty Questions" game. Which pre-selected twenty questions allows you to "cover" the most of the Universe of phenomenon? If one set of 20 allows you to distinguish more of the Universe than some other set, then the first set is somehow a better model of the Universe. Does that help?
> If one set of 20 allows you to distinguish more of the Universe than some other set, then the first set is somehow a better model of the Universe.
Is Akinator’s 20q database available as a dataset for non-commercial research purposes? It’d be beat to attempt to compress it in a way where training with one half predicts the other half at the smallest trained model size.
Unless the idea is that whatever methodology is required to build this particular program could then be adapted to do other things that seem intelligent. That seems possible, but not at all likely given my reading of the challenge requirements.