preview
Game I’m currently working on, currently in a state where I feel it’s worth sharing. Play Blackjack/Spanish 21 with real strategies and count-based deviations, and a referee that tells you your accuracy.
Still no tutorial, so here you go: You have to place a bet and select D/Deal to play. You can build a bet in the bet menu and save it to a slot for easy reuse, or drag the chips from the rack to the play area. The two games are Blackjack and Spanish 21, which are both games where you try to beat the dealer by drawing close to 21 without going over - if you’re not sure what the correct play is for a hand the answer is located on the table in the Book window, and both games include 22 play deviations that key off of the “True Count” which you will need to learn to achieve perfect accuracy.
Counting cards is relatively straightforward since I do the counting for you - bet high when the count is high and low when it is low, and you should see success even if your accuracy could be better. I like to set my six bet slots to my betting ramp - slot one is for TC +1 and below, slot 2 for TC 2, slot 3 for 3, etc - and the default table stakes of 1-25 mean you can do a 1-25 ramp and get unrealistically high EV. Plus if you bust you can just refresh the page - your settings are saved, your rack resets.
Whatever you do, do NOT think that getting good at this game will make you good at actual card counting and run off to your nearest casino to try it. Card counting in a real environment requires serious practice with high quality training software or a coach who is already a winning counter to test you out, my game is neither of those.
Game I’m currently working on, currently in a state where I feel it’s worth sharing. Play Blackjack/Spanish 21 with real strategies and count-based deviations, and a referee that tells you your accuracy.
Still no tutorial, so here you go: You have to place a bet and select D/Deal to play. You can build a bet in the bet menu and save it to a slot for easy reuse, or drag the chips from the rack to the play area. The two games are Blackjack and Spanish 21, which are both games where you try to beat the dealer by drawing close to 21 without going over - if you’re not sure what the correct play is for a hand the answer is located on the table in the Book window, and both games include 22 play deviations that key off of the “True Count” which you will need to learn to achieve perfect accuracy.
Counting cards is relatively straightforward since I do the counting for you - bet high when the count is high and low when it is low, and you should see success even if your accuracy could be better. I like to set my six bet slots to my betting ramp - slot one is for TC +1 and below, slot 2 for TC 2, slot 3 for 3, etc - and the default table stakes of 1-25 mean you can do a 1-25 ramp and get unrealistically high EV. Plus if you bust you can just refresh the page - your settings are saved, your rack resets.
Whatever you do, do NOT think that getting good at this game will make you good at actual card counting and run off to your nearest casino to try it. Card counting in a real environment requires serious practice with high quality training software or a coach who is already a winning counter to test you out, my game is neither of those.
preview
I wanted to share my in-progress TTRPG enhancement project, The Gold Box

Video: The Gold Box demonstrates its functionality by absolutely smoking the player in a skeleton ambush.
My eventual goal is to enable fully single player play of any adventure for any TTRPG in Foundry VTT - and along the way, the many capabilities of the program will make it a powerful “oracle”-style GM for your roleplaying group, an assistant for your GM, or the brains for a “DMPC” in a group that could use an extra player.
Right now, The Gold Box can interact in chat, roll dice (ACTUALLY roll them and react to the results, not simulate the roll itself), read character sheets/stats and modify them, create and delete combat encounters, and advance the turn order in an ongoing encounter, enough to make it capable of running a simple combat or roleplaying an NPC outside of it.
The Gold Box requires no special account setup and sends your data to nobody that you don’t tell it to, and has been built from the ground up with privacy and security in mind. It is also totally free to use.
You can configure it for both remote and local LLMs, although to get the most functionality you will need a function-capable model with at least 12k tokens of context. I recommend GLM-4.7 via z.ai as the cheapest way to get the necessary performance, although there is also a “legacy mode” that can enable it to work with basic chat functionality on small local models. I’ve run chats with NPCs and generated descriptions with llama3.2:3b
I’d love it if any interested people here gave it a try and gave me feedback on it. Right now I’m working on the problem of spatial awareness on the game board and enabling token movement by the LLM, but I’m always interested in improving features that aren’t up to snuff or add features that people seem to want.
I wanted to share my in-progress TTRPG enhancement project, The Gold Box

Video: The Gold Box demonstrates its functionality by absolutely smoking the player in a skeleton ambush.
My eventual goal is to enable fully single player play of any adventure for any TTRPG in Foundry VTT - and along the way, the many capabilities of the program will make it a powerful “oracle”-style GM for your roleplaying group, an assistant for your GM, or the brains for a “DMPC” in a group that could use an extra player.
Right now, The Gold Box can interact in chat, roll dice (ACTUALLY roll them and react to the results, not simulate the roll itself), read character sheets/stats and modify them, create and delete combat encounters, and advance the turn order in an ongoing encounter, enough to make it capable of running a simple combat or roleplaying an NPC outside of it.
The Gold Box requires no special account setup and sends your data to nobody that you don’t tell it to, and has been built from the ground up with privacy and security in mind. It is also totally free to use.
You can configure it for both remote and local LLMs, although to get the most functionality you will need a function-capable model with at least 12k tokens of context. I recommend GLM-4.7 via z.ai as the cheapest way to get the necessary performance, although there is also a “legacy mode” that can enable it to work with basic chat functionality on small local models. I’ve run chats with NPCs and generated descriptions with llama3.2:3b
I’d love it if any interested people here gave it a try and gave me feedback on it. Right now I’m working on the problem of spatial awareness on the game board and enabling token movement by the LLM, but I’m always interested in improving features that aren’t up to snuff or add features that people seem to want.