bkil vs. programming

I always look forward to making natural language processing more intelligent without hardwired rules. I also like the condensed style of the video. Build a Chatbot - ML for Hackers #6 video by Sirajology http://www.wildml.com/2016/04/deep-learning-for-chatbots-part-1-introduction/

I've minified  bkil-open: edu/ai/nanochess.hs  to 19 effective lines of code in Haskell, and I'm running out of ideas. The goal was to construct a tiny snippet of code that illustrates a real chess engine instead of the ever boring 8-queens. It still wouldn't fit on a black board properly without further pruning. At the same time, trivial concurrency has been introduced to bkil-open: edu/ai/minichess.lhs , which seems to give it a linear boost. My next step in the area is to add interaction and eventually introduce a more advanced algorithm like alpha-beta to gain playable speed on a full board with complete rules.

I have been thinking about the previous recommendation of a friend of mine, and it does sound reasonable to expect to read about as narrow subject as possible in a single post. The problem is that it happens to me often that I mix in articles of mine between average blog posts. I think it would be a much better choice to build professional articles for my website in the said topics that could contain figures, statistics, research, references, reviews and comparisons, while I would only post short summaries of the said articles here.