Truman looked down the street where an explosion occurred, then a shadowy figure came out of the smoke, approached down the road, ran into truman and then past him and accosted an indian man in a turban. They threw blows until an identical clone of the indian in a turban tackled the shadowy man to the rear of the frame. The first Indian man was handed a white monster energy drink. He took a sip. He immediately tranformed into Truman with glowing blue eyes. Truman was visibly confused and started saying garbled words like "what did you givrm." "I can feel the mermegh"
Dunno how this page is implemented, but the only thing that can't be trivially infinitely scaled is the streaming; the correct solution is probably to farm that out to a service. LiveKit or something fatter. 4096 connections is not necessarily enough for a livestream of anything.
The star of the show is H3 Max Director [1], which lets you get a pseudo realtime WebRTC video feed which you can control with JSON messages.
The model is quite impressive, though obviously it depends a lot on what you're doing. But you can literally just type whatever you want and it will reasonably happen a few seconds later. Logical continuity is not included; attempting to maintain continuity is probably the bulk of the work for this experiment.
If you want to try your own version, you can vibe code an interface on top of the fal API in a few minutes, it is coding agent friendly.
Keep in mind it's super expensive; per list pricing (at least on fal), it costs $5/min to run, and the minimum is 1 minute.
Just spent a half hour prompting it (after it dissappeared from HN front page it was actually working OK).
Basically is a prompt-your-own truman show. Prompting is relatively slow and crashy, so it is hard to build continuity.
Truman is basically dragged back-and-forth between 3 or 4 separate stories at the same time. One person was essentially trying to get truman to break its own simulation by asking what it would prompt after opening the trumanworld.live website on his phone. Interspersed with this, truman kept throwing fruit on the ground and yelling I CHOOSE YOU BULBASAUR/SQUIRTLE/PIKACHU. At one point truman looked at the camera and said "STOP WITH THE POKEMON ALREADY, DIGIMON ARE THE CHAMPION". Another thread was truman constantly breaking out into a musical song. A song about bananas got mixed with the simulation breaking attempts and truman ended up singing something like "This is how I feel. Like the skin of banana, away the reality I peel (and then proceeded to pick up his phone and open the trumanworld.live site again, attempting to self-prompt).
As avaer already mentioned it seems to be a thin wrapper around H3 Max Director, which generates real-time video and takes “natural language directions” that are then relatively seamlessly incorporated into the continuous video stream.
It's like a Choose-Your-Own-Adventure dialed up to 11.
I played around with it briefly on Fal.ai generating a cartoon, but it’s more of a technical curiosity for the time being since I don’t have a Scrooge McDuck vault of gold coins.
It's not on the page, but the creator (@WillTheRapper_) said on Twitter:
> This is our first experiment in building a persistent Social World Engine — a world that continues to exist, evolve, and remember even when nobody is watching.
The audience is meant to direct the show. There's a crypto token involved in paying for it. Make of that what you will.
Personally I think it's an invitation to a lawsuit. Back in the day people were running AI Spongebob on Twitch and that got killed for copyright infringement. And this isn't a cartoon, it's Jim Carrey.
If you opened page and haven't seen video, the page malfunctioned, try reloading it.
On the page there is streamed real time video that is generated by ai. The setting is similar to the movie Truman show with Jim Carrey where he was main character whose life was streamed 24/7. With the limitations of current technology, it is inconsistent slop, the consistency is at most 5-10s, they probably just generate first and last frame of a 10s "scene" and make 2 videos and then stich them together. There is some monetization scheme where users can steer what's happening on screen by paid prompts.
Then hugged to death.