Randall Brown & band (including me).
Because White-Box.
agi.blue now has a query language that looks like this:
word types / is plural of / $x $y / is a / $x return $y
This example queries the database for a random word type.
Coarse Procedures. Power Words.
Concepts we need.
Consider this text:
First, I wake up. Then, I get dressed. I walk to school. I do not ride a bike. [...] Question 1: What happens first? 1 Get dressed 2 Wake up 3 Eat lunch 4 Walk to school [+4 more questions]
Program that solves this. (One screen of code as always.)
The engine is pretty generic. It works by correlating words in the text, the question and the answer. The only additional information we put in is a list of "important words"—this time in the form of regular expressions:
"(?<!not )like", "not like", "dinner", "school", "bed"
The first expression matches on "like", but not on "not like" which avoids some confusion.
(Why do we have to put in these regular expressions? Well, the AI is young, so we help it out a little bit. The semantic knowledge the AI gathers in these exercises will eventually allow it to function without human help.)
Now on to more challenges!
Integrating with the world. A friend's room with some bots.
My JavaX Gitter implementation which is about a million times shorter than anyone else's—only one screen of code.
Yeah it's unscripted. Geniuses work like that.
...now with multi-user support. Download here.
No it's not in the play store. Blame Google.
Original post. Oh my! It is on the wrong subsite. What do they do? Do they move it? No—they lock it. Classic StackOverflow admin malfunction.
So we move it ourselves. What will happen next?
Human, computer, objective.
No more working alone!
...and they're (probably) not the ones you think.
Approaching AI, chapter 915423
...should be enough time for a bot to respond.
More edutainment for your pleasure!