Elon Musk Details Why Tesla Designed Autopilot AI Chip In-House

While some value Tesla Inc TSLA as an automotive company, many of Tesla's biggest fans and bulls say it should be looked at as more of a technology stock.

This is most clearly seen in the company's push to create software for full autonomy. Tesla is not only developing Full Self-Driving software, but it has also designed the artificial intelligence computer chip that will power it as well.

CEO Elon Musk, responding to ARK Invest analyst James Wang on Twitter, said a blog Wang wrote in 2019 about Tesla's self-driving program is an accurate analysis.

In it, Wang said Tesla is four years ahead of the competition on self-driving hardware.

Tesla's is an automotive grade computer many times more powerful than anything on the market at the time of its release, the ARK Invest analyst said. 

Nvidia Corporation's NVDA solution, regarded as being the closest to Tesla's hardware, was more expensive, less powerful and used more energy to run, Wang said. 

Nvidia’s chip must support many neural networks and sensors, he said; Tesla’s chip needs to support just the sensor suite and neural net on its own vehicles.

Musk name-checked two of the other companies in the market in a tweet to Wang. 

"Neither MobilEye nor Nvidia, which are certainly good companies, could meet any of our capability, schedule, cost or power requirements." Musk said on Twitter.

Benzinga's Take: While many are skeptical of Tesla's ability for true level five autonomy, Tesla arguably has the most capable driver assist available on the road today.

The solution that's now being used by customers can stop at traffic lights and stop signs — and take freeway exits and interchanges.

A rewrite of the core autopilot code is expected in the next few weeks, which will hopefully bring Tesla's Full Self-Driving software to the next level. 

Photo courtesy of Tesla.