Resolved yes if it beats human music at least 50% of the time in a general audience or expert poll across at least 10 samples of different prompts (can be instrumental, no limit on genres).
This is a questionable resolution given that a clear resolution procedure was provided in the comments a few months ago, and in the description. Please vote on whether you think it should be re-resolved, and the mods will discuss what should be done here. And please share your reasoning as well.
@IsaacKing I’m voting YES to this option because I’m very interested in the results, but honestly this seems like a lot of work for mods to have to do. N/A is frustrating because there was never any plan to do this work, but that doesn’t mean the mods have to start doing citizen science. Unless you’re really into doing it! Seems a poor precedent to set unless you want a lot more side projects in the future.
@Noit I think the whole role of the mods is to do community work like this, so it's reasonable to, you know, do it. It's a voluntary position. :)
@VladChituc there are some in the comments below. I don't have the ability to do this now and won't have this kind of resolution criteria on the future.
@NickHeinonen None of those are contenders. Nothing came even close, and you're backing out because you "don't have the ability" to test this when, coincidentally, it very obviously didn't even come close.
@VladChituc While I am also quite annoyed about the NA resolution. I think Nick didn't really back out - he doesn't even have a position on this market. I think he just don't care.
This is probably not the tool you’re looking for, BUT it is closely related: https://www.orchestrai.site
I just created a similar market with very concrete resolution criteria, with multiple options for the year that AI-generated and human-created music become indistinguishable. It resolves when, given 5 similar, full-length human-AI pairs of songs with lyrics, I wrongly guess which is which at least once. https://manifold.markets/CalebBiddulph/when-will-i-mistake-an-aigenerated
@firstuserhere after listening to some voice samples, i am not confident that a poll of random people will be able to distinguish easily.
@firstuserhere P.S. This is not to say that a panel of experts will not be able to judge it. I have much lower confidence in a poll of random people than that, though. So, essentially, this reduces to whoever sets up the poll, their design, methodology and selection of the best music models released in 2023 to these people in 2024 or beyond.
@firstuserhere that's great, the ability to hum etc, but I wouldn't bet on it until I've tried it. I try to confuse every music AI I try and they all suck unless they are given common style to generate. If the ten prompts are wacky memecore fusions, an AI will fail, the humans can figure the performance out, but if it's "Ibiza trance on the beach 2000's sunrise 130 BPM" it's just a coin toss and doesn't prove anything about the AI being generally convincing
@Nostradamnedus , this market has 450 traders by now. Would you mind making a more precise description of what your planned polling/sampling/test would look like? I think a lot of the volatility on this question comes down to different expectations/interpretations of the question description.
I.e.:
– General audience OR expert poll, seems like two quite different questions
– What does "Beats human music" mean? That people deem it better, or indistinguishable?
– Who makes the prompts?
– ...
@HenriThunberg It can be a general audience one. "Beats"= can't tell apart in a Pepsi test. Prompts would be made by whoever makes the poll I guess.
@Nostradamnedus Are you going to be the one to make the poll, or are you going to delegate it to someone else? If the latter, who?