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.
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.
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.
- in Pokemon gen 1 you can wrap your stats back to zero by buffing them too much
- In FF7 you can overflow the damage calculation to kill Ruby in one hit
- Mario 64 has a mountain of usable glitches; "parallel universes" let you skip collisions at high speeds
- GTA 3/VC/SA have crazy mission/wrong warp corruptions involving parallel game simulations
- NES Mario can be corrupted to execute arbitrary code in TAS
- OOT can be heap-corrupted so badly you can write a loader for an entire DLC via controller ("triforce%", my choice for most insane controller based hack of a game)
> Seeing the hype online feels both validating and deeply frustrating.
The post is conflating hype and money with technical innovation, they are not really correlated. Kurzweil is known for saying most innovations succeed based not on technology but on timing. Today, who talks about it might matter even more than timing.
Superior research often gets overlooked in favor of someone raising millions, sometimes people who have produced literally nothing manage to sell it. Not saying that's happening here, but I've seen this pattern a lot over my career.
Someone riding (or manufacturing) a hype wave is playing a completely different game from a researcher. If you're a researcher you can't really feel dejected when someone is making a business on the back of what seems like your research; legal protections are decades out of date, even ignoring vibe coding. If you want to make money/hype/whatever off of your work, do that. But realize that it's a path that's often orthogonal to research.
> It hasn't been literally stolen but indirectly it has been.
It's literally stolen IP.
One minus epsilon of the corpus did not give informed consent, or get compensated. The fact that it's laundered doesn't make it any less literally stolen.
What worries me is the step after this. If god forbid this proves successful and models accurately predict specific outcomes, people will start to ask whether the solution to AI slop lawsuits is to do the judging with AI too.
LLM quants seem to eerily converge to modern/not so modern graphics techniques. You wouldn't think it would apply but it's obvious in hindsight. In fact mining graphics ideas is probably a good inspiration for efficient LLM architecture.
For example, the Hadamard activation transform used here feels a lot like multiplying
Fourier basis ala DFT; strong parallels to how image codecs work to make the residuals more compressible (especially discrete block codecs like are used in GPU compressed textures).
I thought I was being clever suggesting that you could even abuse texture decode units to efficiently sample compressed LLMs with hardware; turns out Apple foundation models are already doing this [1].
This is a "startups = wealth inequality" [1] formatted argument but:
This is 100% about money. The only way to pace the frontier is to make everyone (read: investors) lose all their money (read: no longer expect returns). Then nobody will pay the GPU bill or pay celebrities 10 million dollar salaries to stay at the hot lab. Suddenly the development is paced, almost like magic.
Conversely, it is hard to see how pacing development makes the current bubble justified, i.e. how development could be significantly paced without investors losing their faith in hot returns at current valuations. Faith in a bubble literally equals money, exactly in the way that loans created by a bank literally equals money. You can't have one without the other.
In fact if the whole industry goes bankrupt and investors are burned bigtime (many trillions wiped), this would spread transnationally, fixing the "if we don't do it, China will" loophole.
OpenAI had it right originally, the idea to be a NON profit and vow to never participate in an arms race. It's too bad that was tossed out the window now that there's money.
Social media, prediction markets, politicians, stock markets are all clearly selling on hopes and fears.
When you can't easily quantify and point to the benefits, that's the default and it works.
Not to say the industries mentioned don't have legitimate purposes, but yes it's pretty obvious a large part of the AI industry has joined its peers in selling fear, though they would never admit that.
reply