Deep Tide TechFlow news: On June 30, according to The Information, an insider revealed that earlier this month, OpenAI engineers told some colleagues that, by relying on several newly developed optimization technologies, they had found a solution that could cut model inference costs by more than half. After applying this new technology to scenarios where visitors without free or paid accounts use ChatGPT, they at one point reduced the number of NVIDIA graphics processing units (GPUs) required to only a few hundred.