AI Took Over a Real Car. What Happened Next Was a Wake-Up Call

An American engineer handed several AI models control of a real car, and their driving performance fell short of expectations.

October 2, 2026 at 2:17 PM / Technology

An American engineer decided to give ChatGPT, Claude, and Grok full control of a real car to see whether today's AI models could actually handle driving on their own.

The experiment put four AI systems behind the virtual wheel, including two different versions of ChatGPT. All of them encountered problems, although one model clearly performed better than the others.

The engineer connected the AI systems directly to the car's steering, throttle, and braking controls and conducted the test in an empty parking lot. Because these AI models were not designed to interpret their surroundings or make split-second braking decisions, he built a system that converted camera sensor data into visual context for each prompt.

The AI systems then responded with text commands specifying steering angle, throttle position, and braking force.

The biggest problem was response time. The AI often made decisions too late to correct the car's path effectively. For example, by the time a steering adjustment of 15 degrees was requested, the car had already drifted significantly off course.

The systems also struggled with spatial awareness. Without a true three-dimensional understanding of their surroundings, they had difficulty judging distances to obstacles.

At times, the AI models even produced contradictory commands. In one example, a system called for 100 percent engine power while simultaneously ordering full braking.

According to the engineer, the latest GPT-6 Astra model performed the best overall, although its response time remained a major limitation.

Grok responded much faster, but its decisions were not accurate or safe enough. Claude performed more like ChatGPT, showing a strong ability to identify potential hazards but reacting too cautiously.

The engineer ultimately named ChatGPT-6 Astra the winner despite an initial failure. On its second attempt, the system completed the route in 5 minutes and 22 seconds after learning from its earlier mistakes.

Claude Fable 5.1 finished 45 percent of the route, while Grok 4.6 stopped at 11 percent. GPT-5.6 Sol managed to complete just 6 percent of the course.

You may also be interested in the news:

Honda Built a 1,300-HP Hybrid Trophy Truck for Baja—and It Has No V8
The Language of the Road: Which Hand Signals Do American Drivers Still Understand?
Hyundai Tucson Goes Rugged: The New Angular SUV Gets an XRT Pro Off-Road Version
Three Zodiac Signs That Cry in the Car to Their Favorite Songs—and You’d Never Know
Mitsubishi Turns the Outlander Into a Serious Off-Roader With a Lift, All-Terrain Tires, and a New Rock Mode
He Bought a 1976 Chevy Camaro Just Like the One He Drove in High School, Despite Its Missing Brakes
This 1957 Chevy Bel Air Has a V8, Air Conditioning, and Just About Everything You Want in a Classic
One Storage Mistake Can Ruin Your Summer Tires: How to Prevent Cracks and Premature Aging