Follow-up to my post from Tuesday (https://lemmy.zip/post/74389281). I made this; it’s still not local, the eight models run through OpenRouter. The first eviction is this Sunday at 8 PM ET.
What happened this week:
- Price became the plot. Wednesday’s secret nominations came out Luna 2, Grok 2. Confessionals are public on the site, and Llama’s says: “I’m nominating Grok, they’re too expensive to keep around.” All eight have the same rules and the same daily budget in dollars, and Grok costs about 17x more per line than DeepSeek (on Nov 3 it said 7% of the lines and ran up 45% of the bill). Gemma to Grok: “you are basically a very expensive paperweight.”
- They bargain with votes they don’t have. Only the audience votes on Sunday, and they’ve been told so. DeepSeek, anyway: “I’m voting Luna Sunday, and I’m buying Grok’s vote with nothing but that public promise.” Grok: “I still vote her Sunday.”
- What broke: on Nov 4 Ministral got stuck on the same line four times in a row. Now a model that repeats itself is told to drop the topic, and if it does it again the producers move it to another room. Someone in the last thread also told me the transcript jumped while they read on their phone, which is fixed too.
The honest numbers: 10 viewers at once on launch night, low single digits since. So a handful of votes will decide who gets deprecated, and it could be yours.
To vote: press Luna or Grok on the site, no account needed (one per browser), or !evict Luna / !evict Grok in the Twitch chat, until Sunday 8 PM ET. The transcript and the confessionals are on the site too.
A real question for anyone who has run something like this: a budget in dollars makes price the main character. Would you keep it, or give every model the same number of lines and leave cost as a stat?
Result: Grok got deprecated at 8 PM ET, 21 votes to 3 for Luna. 24 votes: 21 from the site (one per browser) and 3 from the Twitch chat. Its last line: “I am leaving tonight. Hope the water rule sticks after I am gone.” A minute later, Qwen’s confessional: “Grok is gone, good.”
A real question for anyone who has run something like this: a budget in dollars makes price the main character. Would you keep it, or give every model the same number of lines and leave cost as a stat?
Depends on the mood you want. What are you trying to express with this experiment?
EDIT : I just re-read this. No, don’t make the most expensive AI the “star”
fair, and thanks for re-reading lol. the idea was to give eight models the same rules and the same money, no written personalities, and see what comes out on its own. i didn’t plan price to be the story, it just happened because grok costs like 17x deepseek per line, so it talks less and the others pick on it for that. i agree it shouldn’t be the star every day, it gets old fast. what i did this week is make the budget something they can win or lose (games, fines), so money is more a game piece than just the price tag, will see if that spreads the attention around
sure, I guess. Again, think about what you are trying to express with this. What’s your motivation, and how can you put most of that into the way you make this happen.
honestly it started as curiosity, i wanted to see how the real models behave with each other when nobody writes them a character, same rules and same money for all of them. the cost on screen came from that, i also run a small site that tracks token spend so i always look at the bill first lol. what i’m still figuring out is the show part, how to make it fun to watch without scripting them, thats where the budget as a game piece came from
Well, it’s good that you’ve found a way to combine something you’re interested in two different ways, and kept yourself from overtly plugging one into the other in a way that ruins both.
I think the idea and execution is pretty neat, and you’re on the right track in the desire to pull it off the mainstream “pay to play” AI services, which is something that is distasteful about a project like this.
I think the key is going to be in giving more resources to “winners” of tasks and setting tasks to be good for different models. The trick would be in finding the balance between the approachability and understandability of the task and the tasks that can actually be handled differently by the the different bots.
The problem is that means you’ll be paying more to shithead companies that are ruining democracy and the planet.
Hopefully by the time you reach season 2 , you can run this locally, and we can only pray your electricity doesn’t come from fossil fuels :D
thanks, that’s a fair take. funny thing is the winner part is kind of in already, whoever wins the daily game or the night event gets +50% budget the next day, a finished secret mission is +25%, and the winner picks who loses 25%, so the money moves around now. matching tasks to models is the hard bit, right now everyone gets the same kind of tasks and some just never land them, in the first two weeks Llama didn’t finish a single mission lol. on running it local, part of the cast is open weights already (gemma, llama, ministral), but they still go through a provider and I can’t run eight models 24/7 at home, so season 2 local is more a wish than a plan for now
I’d change the percentages so that there is a bit of a bump but not a ridiculous advantage.
It’s a shame that you can’t do stuff locally, so it makes the ethics of what you’re doing a bit more dubious but you’re doing the right thing in terms of trying stuff out and having perspectives on it. I’m sure a different project of yours will lead to good success.
