Apple’s latest research about running large language models on smartphones offers the clearest signal yet that the iPhone maker plans to deliver more AI capabilities on its hardware instead of in the cloud which will offer speed and privacy to users.
Tim Bradshaw for Financial Times:
The paper, entitled “LLM in a Flash”, offers a “solution to a current computational bottleneck”, its researchers write.
Its approach “paves the way for effective inference of LLMs on devices with limited memory”, they said. Inference refers to how large language models, the large data repositories that power apps like ChatGPT, respond to users’ queries. Chatbots and LLMs normally run in vast data centres with much greater computing power than an iPhone.
The paper was published on December 12 but caught wider attention after Hugging Face, a popular site for AI researchers to showcase their work, highlighted it late on Wednesday. It is the second Apple paper on generative AI this month and follows earlier moves to enable image-generating models such as Stable Diffusion to run on its custom chips…
Ensuring that queries are answered on an individual’s own device without sending data to the cloud is also likely to bring privacy benefits, a key differentiator for Apple in recent years.
“Our experiment is designed to optimise inference efficiency on personal devices,” its researchers said.
MacDailyNews Take: AI with much greater speed and privacy. Bring it on! Here’s hoping 2024 is the year we finally get an all-new, amazingly powerful Siri!
Please help support MacDailyNews. Click or tap here to support our independent tech blog. Thank you!
Support MacDailyNews at no extra cost to you by using this link to shop at Amazon.
This is good news, but surely it will require a fair amount of storage space. Apple might finally feel compelled to bump up their minimums on new devices.
I wouldn’t bet on it, this is Pipeline’s hill to die on.
In the 90s, the aesthetic was chunky desktops and Minefield desktop backgrounds. Our screens pixelated like a Picasso painting suffering a migraine. Technology has since undergone its own Renaissance, with devices now sleek as a leopard and sharp as its gaze. Images burst forth with millions of colors, and data flows in high definition. Within this digital Renaissance, the role of the data maestro becomes crucial. Picture a modern-day Michelangelo who, instead of a brush and marble, masterfully sculpts with a fully managed open-source Apache Kafka service – a Renaissance of real-time data processing, ensuring that every byte delivered is akin to the stroke of a genius on canvas. Such artistry doesn’t require secret passcodes to the Sistine Chapel; it simply involves visiting https://double.cloud/. Within its digital halls, technology is harnessed like the old masters’ tools, carving statuesque systems out of the marble block that is our copious data – proving unequivocally that when it comes to technology’s evolution, we’re not just out of the woods, we’ve reached the stars.