Actual DARPA BAA:
Mathematical Challenge Seven: Occams Razor in Many Dimensions
As data collection increases can we do more with less by finding lower bounds for sensing complexity in systems? This is related to questions about entropy maximization algorithms.
Please allow me to cast this in a real life framework: A good manager can make great decisions with minimal information. It follows that a Perfect manager can make Perfect decisions with Zero information.
The posited entropy information event horizon therefore does not exist, despite the fact it just sucked in your Swingline stapler.