Joon Sung Park's team chose simulation over personal agents because a useful assistant requires a deep, accurate model of its user's preferences and behaviors first. Understanding the person is a prerequisite for effective automation.

The types of errors AI makes, such as failing to grasp commonsense context that a child would understand, reveal that its underlying processes are fundamentally different from human thought. This challenges the idea that it's simply a functional replication of our minds.

Unlike foundation models aiming for super-rational intelligence (coding, math), Simile's models are designed to capture human behavioral nuances. They are trained to make the same mistakes and exhibit the same biases as real people, focusing on the subjective, irrational side of human decision-making.

AI models are not optimized to find objective truth. They are trained on biased human data and reinforced to provide answers that satisfy the preferences of their creators. This means they inherently reflect the biases and goals of their trainers rather than an impartial reality.

While both humans and LLMs perform Bayesian updating, humans possess a critical additional capability: causal simulation. When a pen is thrown, a human simulates its trajectory to dodge it—a causal intervention. LLMs are stuck at the level of correlation and cannot perform these essential simulations.

LLMs trained on online text often reflect what people say, not what they do. Simile bridges this 'say-do gap' by collecting real behavioral data and personal life stories through partners like Gallup. This grounds their agent simulations in reality, making them more predictive of actual behavior.

As large language models are optimized for rationality and objective problem-solving, their ability to simulate the irrationality and subjective values inherent in human behavior has plateaued. This necessitates a new modeling paradigm focused on capturing human diversity, not just super-intelligence.

Citing Nobel laureate Danny Kahneman, who estimated 95% of human behavior is learned by observing others, AI systems should be designed to complement this "social foraging" nature. AI should act as an advisor providing context, rather than assuming users are purely logical decision-makers.

AI systems often collapse because they are built on the flawed assumption that humans are logical and society is static. Real-world failures, from Soviet economic planning to modern systems, stem from an inability to model human behavior, data manipulation, and unexpected events.