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

Suno v4.5

suno.com

Post reply on HN
Print view View original

181–190 of 291 posts

Re: Suno v4.5

#181

Post by pclmulqdq »

mjr00 wrote: post #78
XenophileJKO wrote: post #74

Earlier quoted context omitted.

I'm not a pro, but this seems different on the 4.5 model. It seems much crisper.

Yeah 4.5 definitely improves a lot, but I can still hear washiness in the high end. Probably not noticeable to most in isolation or poor audio devices like low-end phone speakers, but would be very noticeable on a good soundsystem in a playlist with professional songs.

It still doesn't capture meter or phrase structure well in classical songs, and there are a lot of weird artifacts. It's better than the old models, but there's still a long way to go.

Re: Suno v4.5

#182

Post by cryptonector »

arnaudsm wrote: post #20

The biggest impact Generative Music had on my life was for wedding skits. Families that wanted a funny song about the bride filled with anecdotes didn't need talent anymore. The first time I heard it, it was incredible. The 2nd wedding that did it, it started to feel boring. The 3rd time, everyone hated it. Similar to image-generation, we're getting tired really fast of cookie-cutter art. I don't know how to feel abo…

I've cousin who's a song writer who for a brief few hours was very excited with the silly poems she could get an AI to write, and she shared them with the family group. The first one or two were ok, but eventually several of us started pointing out how vacuous the poems seemed, and how sad that she -a great song writer in her own right- was excited about that generative AI crap. She stopped right quick.

I'll say that this "Suno" thing makes good-sounding music to these non-musician ears right here, but trying a few of these I'm starting to notice it seems fake. But that's not very interesting. What's interesting is that they're going to get good enough to get past the phoniness.

> I don't know how to feel about it.

I know how I feel about it: I don't like it one bit.

Re: Suno v4.5

#183

Post by userbinator »

I stumbled into the rabbithole of AI-generated music on Youtube several months ago, without realising it was AI, and I don't know if they're using Suno or some other generator, but I was impressed and entertained. I doubt it will replace real concerts but for background music and the like, it definitely does its job.

Re: Suno v4.5

#184

Post by cryptonector »

I put in "milonga" and it didn't know what to do with it. I put in "tango" and it gave me a bandoneon solo that meandered jazz-like -- it wasn't bad, but it wasn't tango either. For "vals" it gave me more of what it gave me for "tango". For "candombé" it gave me nonsense. But all the pre-canned stuff sounded pretty good to me. I guess if I was familiar with "Russian techno" I might find what Suno generates for that to be garbage.

Re: Suno v4.5

#185

Post by cryptonector »

kelseyfrog wrote: post #91

The real potential of tools like Suno isn’t in cranking out radio-ready hits. It’s in creating music that doesn't have commercial incentives to exist. Case in point: Functional Music. I started using it to generate songs that reinforce emotional regulation strategies -things like grounding, breathwork, staying present. Not instructional tracks, which would be unbearable, but actual songs with lyrics that reflect actu…

Oh. Music I know can play repetitively in my mind, which is annoying at sleep time, so I tend to listen to slow music I am not familiar with at bed time. Suno did generate good such music just now for me, even though it failed miserably to generate music for genres I like during daytime. Fascinating.

Re: Suno v4.5

#186

Post by Kiro »

cardanome wrote: post #135
brookst wrote: post #116

Earlier quoted context omitted.

There’s not one right way you art. . . Plenty of artists like Warhol and Dali used mass production and automation. If you enjoy writing music your way, great. But I strongly disagree that it’s a mistake to enable people to approach it differently.

I actually used to have the exact same position when stable diffusion came out. All my artists friends where criticizing it and I was thinking it was some form of Neo-Ludditism that they were following. Why not embrace progress? No one is stopping them to not use it but if it helps lower the barrier of entry isn't that great? Surely generative AI could be used to enhance of the workflow of an artist? Oh, how I have b…

Your initial opinion was the right one. Too bad you let yourself be bullied into changing it by the vocal minority of online personalities. Artists that are not influencers have already embraced AI.

Re: Suno v4.5

#188

Post by IAmGraydon »

I'm a musician and I've been pretty excited about AI music generation, which seems to stand in contrast to most musicians. So far though, the available AI music gens are just plain terrible, including Suno 4.5. Everything sounds exactly like what you would get if you bought a library of really bad loops and just layered some together. Boring rhythms. Boring harmonic progressions. Boring melody. Boring lyrics. It's just terrible. I just listened to around 100 song on Suno and I didn't find one that was even remotely interesting or even just fun to listen to. I'm not a music snob - I'll listen to everything from Sigur Ros to At the Drive-In to Insomnium to Ella Fitzgerald to Taylor Swift to Dua Lipa. I just want something that can grab my attention, show me something interesting, and generate a feeling.

Here's the thing about music - what makes a good song is a sense of unexpected familiarity. In other words, it's based on a set of broad, familiar rules (music theory), but surprises you by implementing those rules in a way that's extremely unique and novel. Because generative AI is kind of like an averaging machine, rounding off the outliers, what you get is an example of the rules in the most boring, typical way possible. It completely lacks the element of surprise, and I'm not sure it will ever be capable of that essential element of surprise because of how it fundamentally works. If you want to generate a bunch of background elevator music, however, this seems to be extremely useful for that.

Re: Suno v4.5

#189

Post by nikkwong »

The mood here is as notoriously cynical as I would expect from HN. Yeah, let's all brush this tech off as unoriginal, uninspiring and bland. Let's all tell ourselves that music requires that 'special human touch' or audiences will become bored, unimpressed and uninterested.

But I'll bet you anything, the average ear won't care. This music is already as good as what's produceable by humans, and will be available for a fraction of the cost without the licensing fees. Be ready to see it popping up everywhere—in cafes, restaurants, on TV ads, on your next spotify playlist. These soundtracks will become ubiquitous, and these far cries in communities like these will become a marginalized minority just like any technology that's been superseded.

Human generated music will still exist, of course, as the deep emotional ties that humans feel towards others (artists) cannot be replaced by this technology. But, there are massive use cases where that type emotional connection is not necessary (everything i noted prior, but also game & movie soundtracks, in waiting areas, tv shows, etc), where I would place a strong bet that this will eventually become even more commonplace than human generated music.

Re: Suno v4.5

#190

Post by 0dayz »

spaceman_2020 wrote: post #179

AI has killed my desire to write and make music. It all feels so pointless I increasingly feel like withdrawing from the internet as well. Half of the users are bots anyway

Let's put it this way, if you know how to listen to music as a musician then you'll quickly notice how it doesn't sound very good.

So never feel discouraged because of slop.

Post reply on HN