Really addictive, played for a few hours and ended up with the Rockefeller Center. Wasn’t able to get that space station yet- one thing I noticed is that on the mobile version of the web app you can’t see full item names sometimes. Made it so it was tricky knowing if I’m getting a replica.
Oh awesome, glad you liked it! I can see you on top of the highest value leaderboard with the Rockefeller Center currently haha.
Re not being able to see the full item name on mobile web, good call out, I'll put that on my list of components to restyle. Note you can click on the image of the item being offered on the web app and it will pop up with a modal with its full name and description.
Re the API costs — this is a great property of the "explore an LLM's latent space" game. Once a character has proposed a trade for a given (player item x hidden motivation) pair, I cache it for use again in future plays. This means the inference cost per player trade round will drop over time. Costs are also offset by ads on the mobile versions (I plan to add them to the web version eventually).
Also, GPT-4.1-mini is surprisingly cheap for this operation as well - since posting here a few hours ago total inference spend has been in the low single digit dollars - so not really a concern at this scale.
Really addictive, played for a few hours and ended up with the Rockefeller Center. Wasn’t able to get that space station yet- one thing I noticed is that on the mobile version of the web app you can’t see full item names sometimes. Made it so it was tricky knowing if I’m getting a replica.
Oh awesome, glad you liked it! I can see you on top of the highest value leaderboard with the Rockefeller Center currently haha.
Re not being able to see the full item name on mobile web, good call out, I'll put that on my list of components to restyle. Note you can click on the image of the item being offered on the web app and it will pop up with a modal with its full name and description.
I played it. It was fun. I especially liked how the price was assessed immediately after the exchange, which made it easy to understand.
Is LLM generated every time? If so, I'm worried that the API usage fees must be quite high.
Thanks for playing, glad you enjoyed it!
Re the API costs — this is a great property of the "explore an LLM's latent space" game. Once a character has proposed a trade for a given (player item x hidden motivation) pair, I cache it for use again in future plays. This means the inference cost per player trade round will drop over time. Costs are also offset by ads on the mobile versions (I plan to add them to the web version eventually).
Also, GPT-4.1-mini is surprisingly cheap for this operation as well - since posting here a few hours ago total inference spend has been in the low single digit dollars - so not really a concern at this scale.
This was very helpful. Thank you!