New research report from AppleLLM in a flash“It gives a clear indication that the company is somewhat interested in running large AI language models directly on smartphones rather than in the cloud,” the reports say. Ars Technica. Succeeding in this poses a huge challenge because today’s large language models need to run across huge data centers that have much more computing power than, say, an iPhone.
Concluding the research report, Apple researchers wrote that they had in any case found a solution to an existing computational bottleneck that could be used as a starting point for future research. The researchers believe that as large language models grow in size and complexity, the method will be able to exploit its full potential across a wide range of devices and applications.
This is Apple’s second research report on artificial intelligence in the past month. The previous report was about making image-generating AI models, such as Stable Diffusion, run on the company’s own chip.
Despite its popular virtual assistant Siri, Apple, unlike Microsoft, Google and Meta, has yet to make any major investment in generative AI after Open AI and Chat GPT sparked massive interest in the technology. Even Apple’s mobile rival, Samsung, has said it plans to release a new type of AI-powered smartphone in 2024.
Apple itself did not comment on the new research report.
Read also: Artificial Intelligence will be a new subject in high school
More Stories
EA President Talks New Dragon Age: 'A Return to What Made Bioware Great'
She thought she had bought a phone – she was shocked by its contents
Rumor: Lots of AI in Google's Pixel 10 and 11 cameras