Artificial Intelligence Technology Could Cut Energy Consumption by 95%:

র্

AI generator

A team of engineers at AI inference technology company BitEnergy AI has reported a method to reduce the energy consumption of AI applications by 95%. The group has published a paper describing their new technique on the arXiv preprint server.

As AI applications have gone mainstream, their use has increased dramatically, leading to a significant increase in energy demand and costs. LLMs such as ChatGPT require a lot of computing power, which in turn requires a lot of electricity to run.

As just one example, ChatGPT now requires about 564 MWh per day, or enough to power 18,000 American homes. As the science continues to advance and such apps become more popular, critics have suggested that AI applications are using about 100 TWh in just a few years, the equivalent of Bitcoin mining operations.

In this new effort, the team at BitEnergy AI claims to have found a way to dramatically reduce the amount of computing power required to run AI apps without sacrificing performance.

The new technique is fundamental - instead of using complex floating-point multiplication (FPM), the method uses integer addition. Applications use FPM to handle extremely large or small numbers, allowing applications to perform calculations using them with extreme precision. This is the most power-intensive part of AI number crunching.