Hacker News new | past | comments | ask | show | jobs | submit login

I agree with you that this doesn't reach near the level of good human authors. There's no long term plot or deep human themes in this. I don't think this will ever replace quality human writing, but it may be able to augment it in cool ways. I personally would love if rather than every guard in Skyrim telling the exact same story, if each guard could have their own stories or comments generated based on things about their life. Human authors could provide high level details and let AI generators fill in the smaller details.

I'm not bashing your effort. From the posts I've seen showing the content, it is quite impressive. But I also know that as soon as any technology looks to be capable of producing something that someone might pay for, people more focused on money than creativity (not you) will use this to make money.

It's a bit like modern pop music. We are well beyond the point where software can not only write the music, but even take the once human voice and recreate it to sing the song. Of course it's not great, if one were to really listen - but it is passable, and it makes money. So it drowns out the remaining bits of real human creativity.

Can you give any examples of such a song?

Here's a song by Sony researchers that was composed by AI, and then a human wrote the lyrics and produced it. The intent was to create a Beatles sound, and I think they did quite well. https://youtu.be/LSHZ_b05W7o

Add some Grover-like text for the lyrics (https://grover.allenai.org/), and you're most of the way there. Then use a deepfake singer ( https://youtu.be/k3qJOPrJOQ4 ), and you're most of the way to done.

Depending on the audience, particularly their level of attention or focus on the music, you can probably get away with playing a completely un-human pop song that people will like.


I find the possibilities here very interesting, but I also greatly fear that this will become the norm the same way that nearly every modern song uses autotune.

Humans are really good at vocals, and it would thus be very hard to replace, eg. making a speech synthesis model sing well. Melodies however are more mathematical and could possibly be generated by a computer.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact