Apple's iOS 18 AI will be on-device preserving privacy, and not server-side

Over the past few months, we've heard a lot about Apple's endeavors in Artificial Intelligence and the features it aims to introduce later this year with iOS 18 and macOS 15. Various sources have all claimed that Apple would introduce AI-related enhancements.

It looks like the initial batch of features will function without the need for an internet connection.

Bloomberg's Mark Gurman, writing in a section of his weekly PowerOn newsletter said on Sunday that the initial set of AI-related features Apple plans to debut with iOS 18 "will work entirely on device." In practice, these AI features would be able to function without an internet connection or any form of cloud-based processing.

AppleInsider has received information from individuals familiar with the matter that suggest the report's claims are accurate. Apple is working on an in-house large language model, or LLM, known internally as "Ajax."

While more advanced features will ultimately require an internet connection, basic text analysis and response generation features should be available offline.

Regarding individual apps, we will likely see improvements to Messages, Safari, Spotlight Search, and Siri. Apple has been testing on-device text-based response generation for a while, meaning this feature will most likely be among those first previewed or released.

More advanced AI-related features and enhancements will still require an internet connection. Apple reportedly discussed licensing Google and OpenAI's AI technology for use in iOS 18 rather than developing its own online LLM.

The significant increase in popularity of AI projects over the past few years is likely the reason for Apple's apparent interest in artificial intelligence. AI tools have become increasingly accessible to everyday consumers, and issues have arisen in the legal and education sectors.

On-device processes could help eliminate certain controversies found with server-side AI tools. For example, these tools have been known to hallucinate, meaning they make up information confidently.

And, the hallucination problem has only gotten worse, as AI models feed on content generated by other AI models.

With its new "Ajax" LLM, the company likely seeks to build a competitor to the tools currently on the market. By eliminating the requirement for cloud-based processing and improving the quality of text generation, the company could gain a significant advantage over rival AI-powered services and tools.

Apple will reveal its AI plans during WWDC, which starts on June 10.