Will a text prompt based AI music generator that most of the time cannot be told apart from human musicians be publicly available by the end of 2023?
resolved Jan 1

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).

Get Ṁ600 play money
Sort by:
predicted YES

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.

predicted YES

Like this comment to indicate you think the N/A resolution should stick.

predicted YES

Like this comment to indicate you think the mods should run the described test and re-resolve this market according to the result.

predicted NO

@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.

predicted YES

@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. :)

predicted NO

Why resolve N/A? If it didn't happen it should resolve NO.

@harfe There was no opportunity to properly test some of the contenders.

predicted NO

@NickHeinonen What would a proper test entail?

@MattCWilson it's in the question description.

predicted NO

@NickHeinonen what contenders? such a cop out.

@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.

predicted NO

@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.

predicted NO

@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.

predicted NO

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

suno.ai has a pretty good model (though still can be told apart, at least when it has lyrics)

predicted YES

@firstuserhere after listening to some voice samples, i am not confident that a poll of random people will be able to distinguish easily.

bought Ṁ100 YES from 13% to 16%

@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

bought Ṁ10 YES at 21%
predicted NO

@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.

– 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?
– ...

predicted YES

Guess not.

@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.

predicted YES

@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?

@IsaacKing I don't have any plans to do either at this time.

predicted YES

@Nostradamnedus ...Then how is the market going to resolve?

@IsaacKing If someone sets up the poll.

More related questions