I’ve spent a year wiring GPT-3 into small useful things, and lately every one of those experiments leaves the same residue in my notebook: this belongs in a game. Not as a chatbot bolted onto a menu — as the thing the whole game is made of. So this post is a daydream with one foot on the ground. First the ground.
\nThe honest version of my game ambitions is small and physical. One absurd verb, done well: you’re an elastic thing — a tongue, a rubber arm — and you fling yourself up a ridiculous tower by grabbing and snapping, wobbly physics doing all the comedy. No AI, no story, no NPCs. Just a satisfying, clippable boing, and a leaderboard. That’s a weekend engine and a month of polish, and it’s the correct first game for someone who has never shipped one. I mention it so you know the rest of this post is written by someone who respects how hard “make a fun thing move” actually is.
\nNow let me leave the ground entirely.
\nEvery NPC I’ve ever met in a game is a vending machine. You press its dialogue button, it drops a pre-written can. Even the “good” ones — the branching, reactive, beautifully-written ones — are finite trees a human authored in advance. You can feel the walls. Talk long enough and you find the edge of what someone imagined you might say.
\nThe GPT experiments this year killed my patience for that, because I’ve now watched a machine improvise on the spot, in register, about things nobody scripted. It hallucinates, it’s inconsistent, it’s a confident liar — I’ve written three posts’ worth of complaints. But it improvises, and improvisation is exactly the thing every dialogue tree is faking. So: what does a game look like when you build around the improviser instead of hiding it behind a menu?
\nHere’s the game I keep sketching.
\nA small village. Twenty NPCs. No quest markers, no dialogue wheel — you just talk, in your own words, typed or eventually spoken. And the design rule is a single sentence: every character has a memory, a goal, and a mouth, and only the mouth is the language model.
\nThat distinction is the whole architecture, and it’s the lesson my boring infra year beat into me: don’t put the state in the model. The model is stateless and it lies. So the model is only ever the voice. Everything that must stay true lives in plain code the model isn’t allowed to touch:
\nknows(player_name). Tomorrow he greets you by it — not because the model “remembered,” but because the game handed that fact back into his prompt. The model supplies fluent words; the database supplies continuity. Same split I use for everything: creativity in the model, truth in the schema.unaware → suspicious → grateful) that only advance when the game verifies a condition, like you actually having the brother’s ring in your inventory. The model can’t be sweet-talked into skipping to grateful, because the model doesn’t hold the lever. You can’t gaslight a state machine. (I learned that from a git hook, of all things.)Play it and it should feel like the town is thinking, but under the hood it’s the oldest trick in my toolbox: a fluent liar wrapped in a cage of verifiable state, allowed to be creative exactly where creativity is free and forbidden from touching anything that has to stay true.
\nIf the bones hold, the fun mutations are endless, and this is the part I can’t stop adding to:
\ntrust: low and left to perform the coldness itself.suspicious curdles into bitter, and now the whole town remembers you as the one who didn’t help. Consequence without a scripted branch — just state, advancing, indifferent to whether you’re watching.None of these need a smarter model. They need the model wrapped in more state and more verification — which, conveniently, is the only kind of programming I actually know how to do.
\nI can’t ship this yet, and I want to be clear about why, because it’s not just “models aren’t good enough.” Three real walls:
\nLatency. A conversation with a villager that pauses two seconds per line is unplayable. Dialogue needs to feel like dialogue, and right now the round trip doesn’t.
\nCost. At today’s per-token prices, a chatty player could run up real money in an afternoon. A game whose marginal cost per hour is a variable is a business model I don’t know how to price. My little on-call experiments cost pennies because they run rarely; a game runs constantly, by design.
\nThe leash. Everything in this design is the model on a short leash held by state and verification — because unleashed, it’ll cheerfully tell you the blacksmith has a brother he doesn’t have, invent a shop that isn’t there, promise a reward the game can’t pay. The entire craft is building the cage. The model provides ten percent of this game: the words. The other ninety percent is the boring machinery that keeps the words from lying — memory, goals, checks, the same infrastructure discipline as everything else I build, just pointed at make-believe.
\nBecause the three walls are all falling, visibly, on a timescale of months. Prices have dropped every time I’ve checked. Models got instructable this spring in a way they weren’t last year. Speed is the laggard, but nobody’s betting against it.
\nSo this post is a stake in the ground. When latency and cost cross the line — and I think it’s a “when” measured in a small number of years, not an “if” — the design is already sitting here, waiting, and it was never really about the AI. It was about giving twenty database rows a mouth, and letting a town remember you.
\nFor now, though: back to the tower. The elastic thing isn’t going to fling itself.
","frontmatter":{"title":"The games I'll build when the NPCs can think","date":"July 09, 2022","description":"A daydream. Today I can ship a physics toy where you fling yourself up a tower. But I keep sketching the game I can't build yet — the one where the characters actually understand you"}}},"pageContext":{"slug":"/the-games-ill-build-when-the-npcs-can-think/","previous":{"fields":{"slug":"/twenty-questions-against-a-player-with-no-secret/"},"frontmatter":{"title":"Twenty questions against a player with no secret"}},"next":{"fields":{"slug":"/two-liars-one-dungeon-making-gpt-3-and-stable-diffusion-agree-on-a-world/"},"frontmatter":{"title":"Two liars, one dungeon: making GPT-3 and Stable Diffusion agree on a world"}}}}, "staticQueryHashes": ["3435731857","426816048","63159454"]}