Welcome to Doppelgangers, a chatscript game. This game relies mainly on primitive rules-based AI, which has nothing to do with LLMs. The parser in this game is a little more flexible than the traditional parser. So if you really want to, you can type, “I decide to pick up the match box” instead of “get matches.” And it does this without relying on anything like an LLM. Does anyone care? No. But that’s what I did for you. Mainly, I think the exciting part is implementing rules-based chatbot AI to create interactive dialogues with NPCs, and the various puzzles you might design that involve interrogating people or just thinking of the right thing to say. That’s my interest. When talking to characters, you will use the SAY button, and you type in what you actually want to say as you would phrase it, not in the ‘ask X about Y format.’ Typing in dialogue and pressing DO will not work. But if you type say or ask followed by the dialogue and then press DO, it will work. If you ASK DOLAN ABOUT JOHNNY, what you’re really saying is “Dolan, about Johnny…” You might still be understood. But for best results, speak in natural language. The main idea behind this game is to achieve above-average interactivity with NPCs. Typical adventure/roleplaying games offer the player dialogue choices. My interest is how far you can go with a more open-ended kind of NPC interaction.

Here are some of the main usable verbs: attack, bite, break, climb, close, cover, cut, dance, drop, fold, give, go, hide, jump, leave, light, look, look at, move, open, pick, pick up, play, press, put, release, say, shower, sit, sleep, sneak, stand, steal, talk to, touch, turn off, turn on, unfold, unlock, use.

The first thing you will notice is the option to enable the LLM feature. To enable AI, click the link to Enable LLM. You will have to create your own Player2 account and log in. The AI features work best with Qwen3 or DeepSeek. Click AI selection near the top of the Player2 page and select Qwen3-235B-A22B-Instruct or DeepSeek V3.2. If you pick DeepSeek, click the thinking mode button to enable extended reasoning. This game does not use generated text, and these are the free models best optimized for common sense reasoning. After you have selected the right model, click the green approve button to approve the authorization request and you should be redirected to the game with AI enabled. This affects sections of the game that are marked with (Persuade Check). If you enable it, you will have an opportunity to persuade characters at certain points in the game. The AI is used to decide success or failure. It will also be used to evaluate the results of any psychological evaluation you may undergo during the game. The LLM as implemented in the game does not generate any visible text, it simply returns the word “success” to trigger a success condition, or anything else to trigger the failure condition. If you decide to leave the LLM disabled, you will fail these checks automatically, which does not preclude the possibility of winning. But you will not be able to attain the maximum score. This feature is compatible with all devices, including mobile phones.

So the working theory behind my game is that rules-based AI is better for open-ended dialogue situations, in which there are many possible questions you could ask. But for situations in which you only need to judge if the character’s response to dialogue is generally positive or negative, an LLM is appropriate. This largely avoids the time delay problem, since these situations are a very small minority of the interactions.

Playtesters: Dmitry Markelov, Alam Tamboli, Brenda Forsse, Pat Cuthand, Jed M, Jack Sighton, Murphy Luedke, Timothy Knob, Joseph Knob, Kevin Knob, Susan Knob, Bridget Sands, Jack Sighton, Murphy Luedke, Vincent Calderon, Matt Schroeder, many others who declined to be credited here. Thank you!