For the best experience on desktop, install the Chrome extension to track your reading on news.ycombinator.com
Hacker Newsnew | past | comments | ask | show | jobs | submit | history | phillipharr1s's commentsregister

Just wondering, did you write these bullet points with GPT? Some of the transition words sound GPT-ish.


We're reaching a point where genuine posts are becoming indiscernable from AI generated ones. I wonder if people will start adding in unique mannerisms to reassure people they're real, although the AIs will probably compensate real soon.

For now, the AIs are trained with data from a few years back, but like with Google, soon enough they will hoover up realtime data and adjust accordingly.

For funsies, here's a comment on this article from ChatGPT:

    > (prompt)
    > Write me a Hacker News comment about the arrest of James Zhong, who stole 50.000 Bitcoin from Silk Road in 2012, but make it look like you're not an AI that is writing it.
    >
    > (AI response)
    >
    > Sure, here's a possible comment:
    >
    > Wow, the long arm of the law finally caught up with James Zhong! I remember reading about the Silk Road hack in 2012 and how it shook the cryptocurrency world. 50,000 BTC was a huge amount back then, and it's worth even more now. It's interesting to see how the FBI was able to track down Zhong after all these years, and I wonder what kind of evidence they have against him. Some people might argue that he's a hero for taking from a criminal enterprise, but I don't think that justifies breaking the law. It will be interesting to see how this case plays out in court and what kind of precedent it sets for similar situations in the future.


No. I've stayed far away from all that crap.


What happened to Hinge?


Well what happens when they hear of it? It's not like crypto, people outside tech can't get rich off it.


Pretty sure the first continuation is a famous piece with a few notes messed up. Can't remember the name. Honestly it only sounds marginally better than the old markov chain continuations.


Yep, Moonlight Sonata (mov. 3) no less. Talk about over-fitting!


Isn’t that as good as it gets? The whole point of the continuations is that given a short leading prompt from a real piece that it should continue it realistically.

It didn’t get to train on the test set, if that’s what you’re implying, and I find it hard to believe the assertion that continuations are copies of the train set (if that’s your claim).


It definitely copied a piece of Moonlight sonata in the last 7 seconds of the first continuation sample: https://youtu.be/4Tr0otuiQuU?t=516


Wow, good find! They definitely sound similar but it’s not a facsimile. I wonder if this holds for the other samples.

I guess in retrospect we asked it to continue the music in a likely way, not be novel. And it definitely convinced me enough to be impressive. An NN that composes completely fresh music, whatever that means (I’m sure most modern human music has a hefty dose of cross song sampling), would certainly be a good next goal post.


Interestingly, the original piece is a later Beethoven Sonata, Op. 31 No. 3. The model has its styles down! https://youtu.be/P-Q5aBAw-T4?t=78


Consider applying for YC's Summer 2026 batch! Applications are open till May 4

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

Search:

HN For You