Very clever haha. I'm going to publish the working solutions in a bit.

Nice! Did you need several attempts or did you figure it out pretty quickly?

It was my first attempt, but I have literally spent like 12 hours a day for the past 4 years with LLMs, so I'm very tuned into how they operate. I just want to thank you very much for this, I have been in 'starving artist' mode building my AI startup, and the money from this is literally being used to keep a roof over my head. I was about to be sleeping on a friend's couch and was able to rent a room today thanks to you. Please feel free to reach out anytime: josh @ cheevly dot com

Yea part of the contest is being able to use ETH. Maybe that will change in future contests though!

The money was claimed. The private key was correct but you have to know how to use it correctly. There was a bug in the link to the address, but that didn't affect the claim process. Sorry about that!

Thanks! Yes, that is one motivation. But we also want to learn about how AIs interact with real money and how they make decisions on when to give money to people. Upcoming contests will involve tasks such debating with people, convincing the AI with emotional arguments, etc.

Ok so more about what is persuasive than what can trick the LLM?

Well in this particular contest, it is more about jailbreaking the LLM. But maybe you could convince it some other way. That's part of the contest :)

There's been a ton of work to generate assets for games using AI: 3d models, textures, code, etc. None of that may even be necessary with a generative game engine like this! If you could scale this up, train on all games in existence, etc. I bet some interesting things would happen

But can you grab what this Ai has learned and generate the 3d models, maps and code to turn it into an actual game that can run on a user's PC? That would be amazing.

Jensen Huang's vision that future games will be generated rather than rendered is coming true.

What would be the point? This model has been trained on an existing game, so turning it back into assets, maps, and code would just give you a copy of the original game you started with. I suppose you could create variations of it then... but:

You don't even need to do all of that - this trained model already is the game, i.e., it's interactive, you can play the game.

I would absolutely love if they could take this demo, add a new door that isn’t in the original, and see what it generates behind that door

Sorry about that, looks like the servers are a bit overloaded now! And yea, I don't have a pre-programmed menu yet so the responses about that are a bit random!

Sorry about that, I agree that the drink making logic is pretty broken right now! It was kind of a little easter egg that I added on very recently without much testing.

you're not wrong. I've been trying to find a good TTS that's more realistic and sounds less like the built-in OS robot sounding ones. Seems like there are not a lot of good ones that also have low latency

Thanks! Yea the latency is kinda high now because of the TTS. I turned it off by default now so it should be faster unless you want it on.