diff --git a/_posts/2015-05-21-rnn-effectiveness.markdown b/_posts/2015-05-21-rnn-effectiveness.markdown
index 7b4190654..61e0cf57a 100644
--- a/_posts/2015-05-21-rnn-effectiveness.markdown
+++ b/_posts/2015-05-21-rnn-effectiveness.markdown
@@ -324,7 +324,7 @@ static int indicate_policy(void)
 }
 ```
 
-The code looks really quite great overall. Of course, I don't think it compiles but when you scroll through the generate code it feels very much like a giant C code base. Notice that the RNN peppers its code with comments here and there at random. It is also very good at making very few syntactic errors. For example, it uses strings properly, pointer notation, etc. It also opens and closes brackets `{[` correctly and learns to indent its code very well. A common error is that it can't keep track of variable names: It often uses undefined variables (e.g. `rw` above), declares variables it never uses (e.g. `int error`), or returns non-existing variables. Lets see a few more examples. Here's another snippet that shows a wider array of operations that the RNN learns:
+The code looks really quite great overall. Of course, I don't think it compiles but when you scroll through the generated code it feels very much like a giant C code base. Notice that the RNN peppers its code with comments here and there at random. It is also very good at making very few syntactic errors. For example, it uses strings properly, pointer notation, etc. It also opens and closes brackets `{[` correctly and learns to indent its code very well. A common error is that it can't keep track of variable names: It often uses undefined variables (e.g. `rw` above), declares variables it never uses (e.g. `int error`), or returns non-existing variables. Lets see a few more examples. Here's another snippet that shows a wider array of operations that the RNN learns:
 
 ```c
 /*