X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=README.txt;h=29344462a3eb95014b1a00c65d31cdd7fd83ea71;hb=fc1de19bf86b2cfd09264dfc6fbda1937248a40a;hp=d5cf6d861245694c9fd2c2c4770486e762d949ae;hpb=cdf7c042612ee3b7e5cc2277e82399693a3bf343;p=culture.git

diff --git a/README.txt b/README.txt
index d5cf6d8..2934446 100644
--- a/README.txt
+++ b/README.txt
@@ -23,9 +23,10 @@ be solved but not by everybody.
 
 There are 5 competing GPTs.
 
-The "world" is a 7x9 grid with three "birds" moving in a straight line
+The "world" is a 6x8 grid with three "birds" moving in a straight line
 and bouncing on the world's borders. It could be another "world", but
-this one has objectness and motion.
+this one has objectness and motion. There are ten colors and 4
+directions of motions, so roughly (6x8x4x10)**3 ~ 7e9 states.
 
 Given a random world state, and the state after two iterations of
 birds moving, a "quiz" is to predict the second frame, given the
@@ -38,15 +39,15 @@ My home-baked GPT-37M trained with 250k solves this with ~99% success
 At every iteration, we select the GPT with the lowest test accuracy,
 and run one epoch.
 
+* Creating new quizzes
+
 If its test accuracy got higher than 97.5%, it will create new
 quizzes. To do so, it generates a large number of pairs of frames, and
 checks which ones of these quizzes are hard but not too hard, which
-means
-
-[THIS IS THE IMPORTANT BIT]:
+means [THIS IS THE IMPORTANT BIT]:
 
-it can be solved, in both time directions, by all the other GPTs **but
-one**
+  it can be solved, in both time directions, by all the other GPTs
+  **but one**
 
 The both time directions is to avoid a simple type of quizzes which is
 simply to deal with noise in the first frame.