WSJ's Joanna Stern Tests iOS 27's Rebuilt Siri for One Week, Reports Major Improvements in Personal Context Understandin

Former WSJ Columnist Reports Siri 'Good-Good' After Week-Long Test

Joanna Stern, formerly of The Wall Street Journal, published a detailed review of Apple's rebuilt Siri in iOS 27 after one week of testing. According to Stern, "Siri is good. Like good-good. After years of broken promises, Apple's rebuilt the foundation it needs for the future."

Personal Context Features Show Strength

The most notable improvements center on Siri's ability to access on-device data. In one test at a beach, Stern asked: "I'd like to get some souvenirs for the kids. Based on what you know about them, what should I get them here?" Siri provided personalized suggestions by pulling information from the Messages app.

Another example demonstrated Siri synthesizing data from Calendar, Messages, and voicemail to suggest daily tasks—a capability enabled by Apple's access to on-device user data. "AI is only as good as the data it has. And oh boy, does Apple have a lot of mine," Stern notes in her video. "I'm even considering switching to Apple Mail, and that says a lot."

Current Limitations in Beta

The iOS 27 beta version still shows limitations. Stern's testing revealed:

• Guardrails when asked for medical advice or pursued romantically
• Mistakes in certain scenarios (specific errors not detailed in the report)
• Mixed performance on tasks where the previous Siri version excelled

Device Compatibility

The new Siri AI is coming to newer Apple devices only, according to earlier reports, though specific device requirements were not disclosed in this review.

What This Means

Apple's approach differs from competitors by leveraging on-device data rather than relying solely on large language model capabilities. This gives Siri unique advantages in personalization but also raises privacy considerations—though Apple's on-device processing model addresses some of these concerns. The positive reception from a veteran tech journalist suggests Apple may finally be addressing long-standing criticism of Siri's capabilities, but the beta limitations indicate the assistant isn't yet at the level of ChatGPT or Claude for general queries. The real test will be whether these improvements translate to consistent performance in the public release.