ChatGPT fueled the ongoing AI craze. Recently, news has emerged that tech giant Microsoft is developing its own artificial intelligence (AI) chip to power the key technologies behind the ChatGPT chatbot.
The report states that both sources are people with direct knowledge of the project. They mentioned that Microsoft began developing this AI chip as early as 2019, internally codenamed "Athena."
One of them stated that the chips have been provided to a small group of Microsoft employees, as well as employees of OpenAI, the developer of ChatGPT, who are testing and using them. Their primary purpose is to train large language models and support reasoning, making them a key technology behind generative artificial intelligence (AIGC).
When users use ChatGPT, the software needs to recognize human commands and mimic human responses to corresponding questions. This process requires processing massive amounts of data and places extremely high demands on chip computing power. Microsoft hopes that its self-developed chips will outperform those purchased from other suppliers, thereby saving it time and costs on its expensive AI business.
The "Athena" chip is reportedly intended for training large language models required for generative AI. This will put it in direct competition with Nvidia, which currently dominates the market for such chips. It's worth noting that while tech giants like Amazon, Google, and Facebook are also developing their own AI chips, they still rely on Nvidia's chips to support the training of large language models.
