Exploring game intelligence as a pathway to AGI through Othello
In this lecture, we will (1) examine various definitions of intelligence, (2) explore how Othello can serve as a practical testbed for these definitions, and (3) discuss broader implications for AGI.
Intelligence remains one of the most fascinating yet elusive concepts in AI research. To frame our discussion on game intelligence and its relation to AGI, we’ll first examine several influential perspectives on intelligence:
Chollet’s Intelligence Metric (Chollet, 2019): Defines intelligence as “the rate at which a learner turns its experience and prior knowledge into new skills at valuable tasks that involve uncertainty and adaptation.” Chollet emphasizes skill-acquisition efficiency and generalization capability rather than task-specific performance.
Yann LeCun’s Autonomous Machine Intelligence (LeCun, 2022): Focuses on building systems with world models capable of planning, reasoning, and goal-directed behavior - elements critical for strategic games like Othello.
Brandon Lake’s Human-Like Learning (Lake et al., 2017): Argues that human-like learning should be rapid, adaptable, and built on causal models of the world—characteristics we might want in game-playing systems that truly understand their domain.
These perspectives offer complementary views on what constitutes “intelligence” - from adaptation efficiency to world modeling to human-like reasoning - all relevant to our exploration of game-playing intelligence.
Several existing AI systems demonstrate aspects of intelligence that align with our definitions above:
Gato (DeepMind) (Reed et al., 2022): A generalist agent capable of performing hundreds of tasks across different modalities, demonstrating how a single model can generalize across diverse domains and tasks.
AlphaZero (DeepMind) (Silver et al., 2017): Mastered chess, shogi, and Go through self-play reinforcement learning combined with Monte Carlo Tree Search, showcasing how an AI system can discover strategic concepts through experience without human knowledge.
Meta’s Cicero (Meta AI, 2022): Achieved human-level performance in Diplomacy, a game requiring strategic reasoning, negotiation, and understanding of other players’ intentions.
Gemini 1.5 series (Google, 2024): Multimodal general-purpose models demonstrating strong reasoning and abstraction capabilities across diverse tasks.
These systems represent different approaches to intelligence - from specialized game expertise to multi-task generalization to sophisticated reasoning capabilities.
Othello (also known as Reversi) serves as an excellent testbed for exploring aspects of intelligence for several reasons:
Clear rules but complex strategy: While the rules can be learned in minutes, mastering strategic play requires significant experience and insight.
Bounded complexity: The 8x8 board provides enough complexity to be challenging while remaining computationally tractable.
Strategic depth: From opening theory to endgame calculation, Othello involves multiple layers of strategic thinking.
For those unfamiliar with the game, Othello is played on an 8x8 board. Players alternate placing their colored discs, with the objective of having the majority of discs in their color at the end of the game. A player captures opponent’s discs by “sandwiching” them between their own discs in horizontal, vertical, or diagonal lines.
Play here: Othello
The strategic complexity of Othello can be viewed as a progression:
The question becomes:
Can we design AI systems that progress through these levels of understanding, and what would that tell us about their intelligence?
To build an effective Othello-playing AI, we must consider multiple aspects of game understanding and strategic thinking:
How deeply must our AI understand the game’s operational principles?
How much gameplay experience is necessary?
How deep must our AI’s thinking capabilities be?
While structured representations are typically more efficient for Othello (since it has clear rules), a vision-based approach offers interesting possibilities for systems that need to interact with physical boards or human players.
How can we leverage game-specific intelligence as a stepping stone toward more general intelligence?
Adapting an Othello AI to handle variations:
Progressive expansion from similar games to increasingly different ones:
An interesting question arises: can current Large Language Models play Othello effectively?
When asked to play Othello, Grok 3 demonstrated:
Claude 3.7 Sonnet demonstrated:
This difference in capabilities highlights the varying approaches to tool use and interactive content generation among current LLMs.
The journey from specialized game intelligence to artificial general intelligence requires several key developments:
Othello provides an excellent starting point for this journey - complex enough to require sophisticated strategic thinking, yet simple enough to allow us to track an AI system’s progression from basic rule-following to advanced strategic thinking.
The path forward involves creating systems that can not only master individual games but understand the underlying patterns that connect different strategic challenges. As we’ve seen, this might involve combining traditional search algorithms with modern neural approaches, embedding both in a meta-learning framework that allows for transfer across domains.
By studying how AI systems develop mastery in constrained environments like Othello, we gain insights into the nature of intelligence itself - insights that may guide us toward creating truly general artificial intelligence.
You will be asked to design your own strategy to compete with the built-in othello agents.
For those interested in diving deeper into Othello strategy:
For LLM capabilities: