Why Greatness Cannot Be Planned: The Myth of the Objective

by Kenneth O. Stanley

Instead of worrying about where we want to be, we could compare where we are now to where we have been.

The more stepping stones we find, the more opportunities there are to depart to somewhere greater.

To achieve our highest goals, we must be willing to abandon them.

The idea is that AI researchers’ expert understanding of search also applies to how the AI community as a whole searches for new algorithms. In other words, how search is programmed in the best algorithms in AI should relate somehow to how researchers search for new algorithms. Because whether you’re searching for algorithms or for parameters, you’re still searching. But it turns out that this meta-level of AI research is rarely discussed. That is, not many people talk about the connection between the AI community’s search and the insights gained from searching algorithms. While many papers in AI analyze what makes search work on the algorithm level, little is said of the AI community’s meta-search for the algorithms themselves. But similar principles must apply there as well. After all, search is still search on whatever level.

Most retarded paragraph ive ever read. What is wuth the repetition??

Anyone can say that performance should improve, but who has the courage to see the beauty of an idea? We could use a few more brave experts like that.