itch.io

Glad you enjoyed it! Thank you for taking the time to play it. I do think the fighting was very "spammable".  I think we definitely could have made the interactions between the guards/clones/normal npc more clear and shown a clearer connection to the interrogation. Thanks again and we are really glad you had fun playing our game!

Thank you for trying our game chaupka! I'm glad you liked it. There is actually a connection, the more characters you beat up (or let your clone beat up) the more heat you have with the cop to start the interrogation. I think we probably needed to make this connection more clear and maybe more impactful if we had more time. Overall really happy you enjoyed it and took the time to give feedback, thanks!

Thanks for trying out our game Eibriel! Totally see where you are coming from and I think we'd want to spend some time on pacing if we had more time!

Lol these are great excuses. We've heard some pretty funny ones. I'm surprised he didnt buy the flying pet pig :P

Thank you for giving it a play Dani_Swordfish!

Thanks preposterous_productions! Great suggestion, I'm guessing we could flag the clones in the prompt to the AI without disrupting the other dialogue too much.

Thanks for giving it a play Rokner! I can definitely see how it might just feel like pure chaos from the outside. We probably could have made the explanations a little clearer and add some more pacing into the combat with more time.

Thanks for the comment kokutouchichi and thanks for trying out our game. So one of the places LLM based AI agents really shine is in decision making. So there are no hardcoded rules about what works and what doesn't. Instead the prompt is taking in a threatscore from the game state based on prior dialogue with the police and the amount of chaos in the brawler section. After each piece of dialogue the Agent can decide to adjust the threatscore up or down. Reaching a certain threshold gets you arrested.

This is a very basic implementation of https://react-lm.github.io/ . You can build way more complex decision making loops using this pattern and it is one of the things that @drusepth and I are most excited about incorporating into our games!

More good reading : https://arxiv.org/abs/2304.03442

Thanks for checking it out Joey!