I put the new Siri AI through a 10-round test on my Mac - here's how it did

2026-06-17 · Source: News and Advice on the World's Latest Innovations | ZDNET · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, medium

Summary

Lance Whitney's ZDNET review evaluates the new Siri AI, introduced at WWDC 2026 and currently available via waitlist on supported devices running the 27 developer beta. Whitney tested Siri AI on a spare MacBook Air M1, noting the complex setup process involving device compatibility with Apple Intelligence and developer beta installation. The testing involved 10 rounds, covering general questions, on-device file searches, system controls, image analysis, and conversational capabilities. While Siri AI proved more direct than other chatbots and successfully managed calendar appointments and Mac settings, it exhibited inaccuracies in photo identification and painting analysis. Conversational flow was also clunky, requiring repeated microphone activation. Despite these early beta limitations, the review concludes Siri AI is an improvement over its predecessor, with Apple having several months to refine it before its expected public release in September.

Key takeaway

For AI Product Managers evaluating early-stage intelligent assistants, you should recognize that Apple's new Siri AI, despite its beta status, demonstrates a clear shift towards a direct, task-oriented assistant. Prioritize refining conversational fluidity and accuracy in on-device content analysis. Your teams should focus on robust error handling and intuitive interaction models to ensure a seamless user experience before public release, especially for complex queries and multi-turn dialogues.

Key insights

Apple's new Siri AI, in its early beta, shows promise as an intelligent assistant despite current accuracy and conversational flow issues.

Principles

• Early beta software often contains bugs.
• Phrasing requests precisely impacts AI comprehension.
• AI assistants can integrate deeply with device functions.

Method

To test an AI assistant, pose general and specific questions, request on-device file searches, attempt system controls, analyze files, and engage in back-and-forth conversations.

In practice

• Install developer betas on spare devices.
• Use specific phrasing for on-screen content summaries.
• Expect to manage past AI conversations.

Topics

• Siri AI
• Apple Intelligence
• Developer Beta
• AI Assistant Testing
• On-device AI
• Conversational AI

Best for: AI Product Manager, Tech Journalist, AI Engineer

Related on AIssential

• Say hi to "Siri AI"—Apple announces new, more "conversational" voice assistant — Apple's "Siri AI" integrates deep personal context and a two-tier on-device/cloud architecture for enhanced conversational intelligence.
• Siri is good now?? — Apple's new Siri AI, while not bleeding edge, now reliably works, potentially reshaping mainstream AI utility and social media interactions.
• The Apple Watch needs a better Siri more than the iPhone right now — Apple's Siri and Health app need Google's Gemini AI to deliver personalized, integrated health insights and catch up in the AI race.
• Why Apple’s slow-and-steady AI bet is starting to look pretty smart — Apple's user-centric, integrated AI strategy, exemplified by Siri AI, prioritizes practical utility and financial prudence over a "race" for AI.
• Apple’s new Siri AI knows when to shut up — Apple's Siri AI adopts a concise, utility-focused personality, contrasting with other chatbots' verbose and engaging styles to avoid user over-attachment.
• Apple Finally Gives Siri Its Own App — Apple transformed Siri into a dedicated, multi-modal AI chatbot app, integrating it deeply with Apple Intelligence.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by News and Advice on the World's Latest Innovations | ZDNET.