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

SHOW-1 and Showrunner Agents in Multi-Agent Simulations

fablestudio.github.io

Post reply on HN
Print view View original

21–30 of 54 posts

Re: SHOW-1 and Showrunner Agents in Multi-Agent Simulations

#21

Post by jerpint »

codetrotter wrote: post #18

Was the intro generated as well, or lifted directly from the real show? There is a significant drop in believability as soon as the first scene of the generated show starts after the intro. Look at the first few seconds of the first scene. Here, the three boys are just standing statically in the hall while they are talking. Now take South Park Episode 1, Season 1, from 1997. https://www.southparkstudios.com/episodes/…

I also found the intro to be of very high quality, I wonder if they overfitted on that?

Re: SHOW-1 and Showrunner Agents in Multi-Agent Simulations

#23

Post by madeofpalk »

icoder wrote: post #4

So in addition to worrying about fake AI stuff that is presented as real, we now also have real stuff presented as fake AI.

To be fair, we've always had startups pretending they have "AI" or "machine learning" but it was just mechanical turk or someone on upwork.

Re: SHOW-1 and Showrunner Agents in Multi-Agent Simulations

#25

Post by CSMastermind »

Assuming I'm reading the paper correctly this wasn't AI Generated so much as it was AI Assisted.

They used AI to generate character dialog and voices (easily the worst parts of the video) while the humans guided the plot and picked the lines of dialog that would be used.

Re: SHOW-1 and Showrunner Agents in Multi-Agent Simulations

#26

Post by addandsubtract »

dom96 wrote: post #22

I skimmed the paper and didn't see an answer to this: how much of the video did the AI actually generate? how much of it was touched up by humans and how much of it was actually drawn/animated solely by humans?

Judging by the rendered samples on the page, I'm gonna assume only the assets (backgrounds and characters) were AI generated. Animations, text, and camera movement were all done manually.

Re: SHOW-1 and Showrunner Agents in Multi-Agent Simulations

#27

Post by ryanbrunner »

icoder wrote: post #4

So in addition to worrying about fake AI stuff that is presented as real, we now also have real stuff presented as fake AI.

I don't think I've ever seen a "AI wrote this!" script that wasn't very clearly heavily assisted or often outright created entirely by humans.

Re: SHOW-1 and Showrunner Agents in Multi-Agent Simulations

#28

Post by juujian »

CSMastermind wrote: post #25

Assuming I'm reading the paper correctly this wasn't AI Generated so much as it was AI Assisted. They used AI to generate character dialog and voices (easily the worst parts of the video) while the humans guided the plot and picked the lines of dialog that would be used.

My guess is that they could have produced the same thing in roughly the same time without AI. Possibly with better results. Writing individual lines really is not the bottleneck.

Re: SHOW-1 and Showrunner Agents in Multi-Agent Simulations

#29

Post by Al0neStar »

jerpint wrote: post #21
codetrotter wrote: post #18

Was the intro generated as well, or lifted directly from the real show? There is a significant drop in believability as soon as the first scene of the generated show starts after the intro. Look at the first few seconds of the first scene. Here, the three boys are just standing statically in the hall while they are talking. Now take South Park Episode 1, Season 1, from 1997. https://www.southparkstudios.com/episodes/…

I also found the intro to be of very high quality, I wonder if they overfitted on that?

https://youtu.be/piwB5SJqZ7U

Over-fitted or copied.

Post reply on HN