Researchers Made AI Drive a Toyota Corolla for In-N-Out, Only One Succeeded
◆ The brief
Engineers recently conducted an experiment where they attempted to use advanced AI models to control a real Toyota Corolla car. Their goal was to make the car drive autonomously to an In-N-Out fast-food restaurant, guided solely by instructions from large language models (LLMs) like GPT, Claude, and Grok. These LLMs are AI systems that are very good at understanding and generating human-like text. The surprising result was that out of the three AI models tested, only one successfully managed to navigate the car to its destination. This experiment highlights the significant challenges in translating abstract AI commands into precise, real-world physical actions, especially for complex tasks like driving a vehicle.
◆ Key points
- 01Engineers used AI to drive a car.
- 02GPT, Claude, Grok were tested.
- 03Only one AI succeeded in driving.
- 04Highlights challenges of AI agents.
This experiment is important because it tests the practical capabilities of current large language models in a real-world, physical task. It shows that while AI is advanced, its ability to act as a reliable 'agent' (an AI that can perform actions) in the physical world is still limited and varies greatly between different models.