Post by reeper147 in AI2U - With You Til The End - Yandere AI Girlfriend Simulator comments

AI2U - With You Til The End - Yandere AI Girlfriend Simulator » Comments

Viewing post in AI2U - With You Til The End - Yandere AI Girlfriend Simulator comments

In the original release, you had to supply your own API keys. It cost money to run it, I found I can spend as much as 9 dollars PER DAY playing it. But people kept giving the feedback that they didn't want to setup the account and deal with all that hassle.

They needed to monetize it somehow, and this is how they are going with it. It makes sense, you can't expect them to release a one time purchase game that costs them potentially hundreds of dollars a month by player costs. The whole project would go under water. It isn't predatory, it's the only option they have.

I would know, I am developing my own AI-integrated project. And yeah, the costs can add up. I had to scale back my project because just TESTING it before I went live with it cost me over 30 bucks.

SirensLure202 days ago(+2)(-1)

That's neat about your project and I really don't care. The issue is they are making you pay for the game again. I was fine supply just a chat gbt api key like the first game. We're paying for a game that's still in beta. Kinda hard to help test a game and provide meaningful input when you have to pay for it to keep playing. So they are setting their self up to either keep getting money or have a lot of bugs not found if not both.

reeper147201 days ago(+2)(-1)

You continue to own the game, you just cant play it until you buy more tokens. You still own the game though. Yeah, it sucks it is beta and you have to buy more tokens through this page to keep buying, but that is the economics of it. If an average person plays it for 5 hours every third day or so for the first month, that could wind up costing 50 bucks per player, and that is discounting the people who get absolutely sucked in. If they get 50 players per month, that would mean 2,500 dollars per month.

This is a small, mostly volunteer group that has very limited resources. You can't expect them to shell out hundreds or thousands of dollars for the beta test on a big scale. This is at least among the first project of its kind, so the financing side of a game like this is very unclear.

You act like they are making huge profits off of this, but I am telling you they are absolutely not. Hell if they just wanted money, why did they add localized voices (that are admittedly and obviously lower quality) to cut token usage by half? You are acting like they are just going to be rolling in money, but they aren't. It is painfully clear you have no clue what you are talking about for the financial side of things. This is a small team working on this project from their own resources; it isnt like a billionaire is backing them, and they can just do whatever they want.

minipasila186 days ago

You do realize they don't need to force you to use OpenAI? They could just open up the API so that you could use locally run LLMs.. which could keep the game alive long after the devs stop supporting the game.
OpenAI's API is pretty common nowadays and many popular local LLM UIs support it like text-generation-webui.. though Koboldcpp which is probably the easiest to use uses it's own API, but should be fairly easy to implement still. (the devs could easily look at things like SillyTavern and the code on how they implemented those things)

reeper147162 days ago (1 edit)

As far as I know, SillyTavern requires API keys that still cost money. From their FAQ directly:

Q: So I should use GPT-4. It's a no-brainer, right?

GPT-4 or Claude, yeah.

But not so fast. GPT-4 is the state of the art, but also the most expensive API to use. You pay for each word sent to it and returned (entire Tavern prompt, followed by the chat history up to that point). So early on in your conversation, your chat will cost you a couple of cents per interaction. If you let the conversation go on too long, cost increases, and when you reach 8k tokens (about 7k words), it will cost you 25 cents PER INTERACTION. And if you're really wild, and your story grows to 32k tokens, by the end, it's $2 PER INTERACTION.

If you're the child of a Saudi oil sheik, or a nepo baby paid a fortune to do nothing on the board of a Ukrainian gas company, then you're in luck, you can experience the state of the art right now. For the rest of us however, GPT-4 is too expensive as anything but an occasional treat.

Also note that GPT-4 is still in preview access and you need to go on a waitlist. Most people get approved within a day, but naughty kids can end up waiting for weeks. You can sign up for it here: https://openai.com/waitlist/gpt-4-api . I'm not sure why some people are approved quickly while others are kept waiting. Try to sign up using an academic-sounding name instead of sktrboi99, it might help.

GPT-3.5 is a more cost effective model while still outperforming most models.

BE SURE TO SETUP A MONTHLY USAGE CAP ON OPENAPI IF YOU USE A CHATGPT MODEL. THIS WILL KEEP YOU FROM OVERSPENDING"

That means that it still costs money, which was LITERALLY the whole reason the team moved to having their own API; some of the biggest feedback they got when they released the previous version was that people didn't have the kinds of cards to setup accounts on OpenAI. So they decided to find a monetization path that allowed players to play the game using in-game currency.

EDIT okay so I found some that are free. However, each require directly downloading and installing the LLMs, are severely restricted compared to online resources, and would be a pain to integrate and support. Not to mention that any technical issues with the LLMs may wind up as false reports to the Devs. It would be nice to add, but it would certainly pose its own problems, and you have to trust the users would be both tech savvy enough to install them, as well as having machines beefy enough to run not only the game, but the LLM as well.

minipasila162 days ago (1 edit)

Sure if you aren't tech savvy you can always just pay for the ease of use but if you don't mind figuring things out to do it for free then you should still be allowed to do that.

(Btw you don't need particularly beefy computers to run LLMs especially llamacpp.. it can run on your phone if you have 6-8gb memory.)

reeper147161 days ago

I work with the public somewhat often in my career. I once had to walk a person through the complicated job of... entering coordinates correctly... four times. They could not understand that they had to convert their hours minutes seconds form of coordinates to decimals despite me telling them that three times. I was barely keeping my cool the third time he entered coordinates wrong. People are dumb, and then they expect you to clean up after their dumb mistakes.

I would never want to imagine the hell that would be unleashed trying to offer people a "free" version of a product that would require setting up an LLM on their machine. I know you might say something to the effect of "But that isn't on the devs if someone doesn't know how to do it", but people will still blame them for not supporting them enough. Not to mention that, unless all locally run LLMs have a specific protocol for integration, then I would imagine it would be a bunch of work. Because once you make the move from supporting one and only one method, to supporting multiple methods, people will continue to push for more and more to be added. I totally get why they wouldn't want to do all that.

minipasila161 days ago

Most LLMs use the same or similar architectures, so that shouldn't be a big problem. But you'd still have the option to pay if you don't know what you're doing. And using OpenAI compatible API would be the broadest way to support multiple GUIs for LLMs.

itch.io

Viewing post in AI2U - With You Til The End - Yandere AI Girlfriend Simulator comments