Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Reviving my 2001 college band with AI

fadingmaize.com

Post reply on HN
Print view View original

61–69 of 69 posts

Re: Show HN: Reviving my 2001 college band with AI

#64

Post by Caracas288 »

nickandbro wrote: post #62

The originals are way better. The AI songs I can tell have a ghost in the shell. It’s like whatever uniqueness of the original was polished out.

The other way around, surely? The ‘ghost’ being the soul, absent in purely robotic beings.

Yes, it’s hard to accept that for many, the notion of quality is conflated with uniformity of texture.

It’s a fun website nevertheless, interesting project.

Re: Show HN: Reviving my 2001 college band with AI

#65

Post by wjnc »

999900000999 wrote: post #58
ToucanLoucan wrote: post #47

Earlier quoted context omitted.

My girlfriend has been using an AI music generator and like, her music is the best generative music I've listened to. Her prompts are crazy, lots of actual like, music theory and specific requests. That said, it still shares these qualities. It sounds like AI images look. Oversmoothed/overtuned. Like as a creative myself, what AI has taught me more than anything is that a lot of what we call artistry happens in the f…

The charm is that as humans it's physically impossible to do the same thing exactly the say way twice. If I play 3 notes, without something like quantization it's always going to be a bit different from you playing the same 3. Anything AI with vocals sounds completely non sensical. I guess you can feed it words, but at that point just record yourself. I'm not all that good , but that's the point.

Like your thoughts! And then mastery is being able to play things exactly the same. But with mastery comes another way for humans to recognize each other. Specific sounds to specific masters (or movements, techniques for say sports). Each master adds individual grace that we can recognize. That might be why we discount AI-creations vs human mastery. There is a grace (I’m stretching) but it is not unique and not acquired via a process of human mastery. (The word ‘bland’ fits very well!)

I bought this Barenboim on Beethoven DVD set 20 yrs ago only for the bonus DVD where he gives a masterclass. These were exceptional students (Lang Lang is rated as one of the worlds best now), and I can’t play piano, but in that video he shows me as a layman the difference between playing with competence and playing with grace. One can hear the difference in depth of the story behind each note. Found one: [1]

[1] https://www.youtube.com/watch?v=3NYfrht6TU8

Re: Show HN: Reviving my 2001 college band with AI

#68

Post by phendrenad2 »

Saw a post on X that showed that AI images and videos have uniform entropy across the entire image, making them easy to detect. I've been unable to "unsee" this across all AI generated things, not just images and videos: It shows up in audio and AI voice (which is why AI has such a weird "compressed" speaking cadence), writing (AI is bad at writing "slow" sections in books, it's non-stop things happening at exactly the same intervals), and I'm sure it applies to coding also somehow.

In the AI version, which I think is inferior to the original human version here, the AI has "filled in all the gaps" and it feels like an endless plateau with no end (AI is also bad at wrapping up songs, lol)

Re: Show HN: Reviving my 2001 college band with AI

#69

Post by causality0 »

zxlk21e wrote: post #6
causality0 wrote: post #5

Have you considered processing the original recordings using AI? I've witnessed some truly amazing results. I've had twenty year old Skype call recordings sound like we were sitting in a recording studio.

how do you do that? I'd love for it to be not-as-generative with music.

Depends on if you're willing to pay or not. You can do it alright locally with DeepFilterNet but honestly the best quality comes from Adobe Podcast's AI Enhance function.
Post reply on HN