I was able to do some rating for a while, and I think the results are fairly cool, but it may not produce anything very interesting for a couple reasons.
The first is that there isn't strong enough evolutionary pressure. There are too many people rating with very different opinions of what sounds good. I think it would be much more interesting to create different channels. Classical, jazz, ambient, electronica, whatever. It's still a very broad definition but not so much that our ratings aren't just noise.
You're right, and this is why we wanted to do the experiment. Nearly a month ago we had 120 Imperial College students do 250 ratings each for us over a week. We replicated the experiment 3 times (40 students per population) and assumed that these students would have a mix of musical and cultural backgrounds. We got 75 generations out of it, and the results were much more musical than the random material we started with, but now we realise that 200+ generations is where it's at!
Secondly, the algorithms used to generate the music are really important. I couldn't find any information on it, but the way the notes are put together seems fairly random. I think it's important to stick to what we do know sounds good... to an extent. For example, the gene could contain information on which way to move the current note, rather than the specific note. That way you could limit it to 2 or 3 steps and lay it over a scale or mode. The willy nillyness of it will guarantee that we pick 'safe' consonant sounding harmonies. 5ths and 4ths with beep boop melodies.
Very interesting though, I can't wait to see what happens with this.
Absolutely, the choice of 4/4 time signature, 12 note scale, tempo etc all have a big effect. As do the types of synths, effects (there's reverb but no delay), quantisation (there's no way to get triplets, for example), no glissando, the list goes on.
We tried to boil it down to the simplest and least arbitrary implementation possible, but that was an infinite task!
And yes, a lot of it does seem to be picking the "non-rubbish" loops, although recently (post-slashdot) I've been hearing some quite adventurous stuff.
Your thoughts are welcome on the Facebook Group :-)