# Real game AI, not a chatbot: why these opponents don't use an LLM > Source: > Published: 2026-09-16 23:02:28+00:00 Syndicated from the original on **[lkforge.com](https://lkforge.com/blog/game-ai-not-llms/)**. The engines are playable in your browser at [lkforge.com/games](https://lkforge.com/games/); the harness that produced these numbers is public and seeded. Every "AI" in a product now seems to mean a large language model. The AI that plays against you on my site **doesn't** — it's classical game-tree search: minimax, expectimax, breadth-first search. That's a deliberate engineering choice, and it's the difference between an opponent that's **provably correct and instant** and one that's **plausible and slow**. My [tic-tac-toe](https://lkforge.com/games/tictactoe/) engine returns a provably-optimal move in about **0.3 ms**, on your device, with **zero network calls** — and it has lost **0 of 1,200** test games. Those are properties a language model, by construction, cannot offer: **determinism, a correctness proof, and sub-frame latency without a server.** Fair question in 2026 — you could prompt a model with the board and ask for a move. The reason I don't: a language model is trained to predict the next token of text, **not to search a game tree**. It can explain tic-tac-toe strategy fluently and still play a losing move, because fluent text and optimal play are different objectives. Winning a solved game is a *search* problem, and we already have exact, fast algorithms for it. The three engines — minimax + alpha-beta for tic-tac-toe, expectimax for [2048](https://lkforge.com/games/2048/), and BFS for [Color Lines](https://lkforge.com/games/lines/) — are textbook, deterministic, and run in well under a millisecond in a browser tab. | | Game-tree search (mine) | A language model | |---|---|---| | Decides a move by | searching the tree of legal positions | predicting likely next tokens | | Correctness | provable at full depth | none — fluent ≠ optimal | | Same board → | same move (deterministic) | varies with sampling/phrasing | | Latency | sub-millisecond, on-device | a network round-trip | | Needs a server | no | yes | Every row is an *architectural* difference — how each system decides — not a quoted benchmark. The only measured numbers here are mine. Because the engines are deterministic, I can put an **exact** figure on how strong they are — run the shipped code headlessly, hundreds of times, and count. That's far harder for a model whose output shifts with sampling and phrasing. **2048 solver, 250 self-play games:** 69.6% of games reach the 2048 tile, 30% reach 4096, and **none of the 250 reached 8192** — the honest ceiling of a corner-snake expectimax search at ~0.5 ms/move. A number, with error bars you could compute, precisely because the same board always drives the same search. **Tic-tac-toe** is the cleaner case: full-depth minimax is provably optimal, so "unbeatable" is a theorem, not a vibe. Across **1,200 self-play games** (1,000 vs random, 200 vs a perfect copy) it lost none. Alpha-beta keeps full depth cheap: **36,528 nodes instead of 549,945** at the opening move — a **93% cut** — in about 0.3 ms. None of this is anti-LLM. Language models are extraordinary at *language* — and a couple of the tools on my site that are genuinely language tasks could use one. But a board game with fixed rules and a finite tree is exactly the problem classical search was invented for. *Full write-up with charts: **[lkforge.com/blog/game-ai-not-llms](https://lkforge.com/blog/game-ai-not-llms/)**. Related: [Six Games, Three Classic Algorithms](https://lkforge.com/blog/game-ai-three-algorithms/) · [Minimax & Alpha-Beta, Visualized](https://lkforge.com/blog/minimax-alpha-beta-explained/) · and the companion experiment, [We Asked ChatGPT and Grok to Benchmark Our Game AI](https://lkforge.com/blog/chatgpt-vs-grok-game-ai-benchmark/).*