After investing $30 billion, Nvidia is reportedly planning new chip for OpenAI: How it will be different than its GPUs

Nvidia is said to be working on a new processor that will be built specifically for AI inference computing – a type of processing that allows AI models to respond to user queries – specifically for OpenAI. Reportedly, the announcement is expected at Nvidia’s GTC developer conference in San Jose next month, and ChatGPT-maker has already agreed to become one of its largest customers.

What is the new chip and how is it different?