AppStories
AppStories

All About Siri AI

July 20, 2026

AI Summary

5 min read

"116 years old." That's what Siri AI guessed when host John Voorhees asked how old co-host Federico Viticci is, based on his contact card. The card didn't include a birth year, so the model hallucinated one — and then agreed sycophantically when John joked that Federico must just have a good skincare regimen. That moment captures the central tension of this episode of AppStories: Apple's new Siri AI is a genuine leap forward from the old Siri, but it is not the agentic tool that power users have come to expect from tools like OpenAI's Codex or Anthropic's Claude. The hosts walk through what Siri AI does well, where it falls short, and why managing expectations matters.

What Siri AI Is Actually Good At

Siri AI excels at two broad categories: world knowledge and in-app search within Apple's own system apps. For the first time, asking Siri a factual question no longer returns a list of web links. Instead, it provides a rich, visually formatted answer with photos, maps, and expandable details. John tested it by asking about a local restaurant in Charlotte and got a map, driving directions, a call button, and a link to the website. Federico found it reliably accurate for current events and sports — it knew Wimbledon wasn't over yet when asked, and within hours of a celebrity death, it had updated its answer and linked to the correct Apple News story.

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

What you'll learn

  • 1 (00:11) **Follow-Up on Codex App's UI Changes** - The hosts discuss recent updates to the Codex app's interface, which now forces users to toggle between Codex and Chat GPT modes.
  • 2 (09:08) **Introduction to Siri AI Discussion** - The hosts pivot to the main topic: evaluating Apple's new Siri AI, its capabilities, limitations, and how it fits into their daily use.
  • 3 (14:44) **On-Screen Awareness: A Standout Feature** - The hosts highlight Siri AI's ability to read and act on content currently displayed on the screen, particularly for calendar and map tasks.
  • 4 (17:21) **Limitations vs. Agentic Tools** - The hosts contrast Siri AI's constrained capabilities with the more powerful, autonomous actions of tools like Codex and Claude.
  • 5 (27:15) **Personal Context: Search vs. Proactive Intelligence** - The hosts dissect Apple's definition of "personal context," finding it falls short of their expectations for proactive, inferred assistance.
  • 6 (35:53) **Passing Data Between Apps and Shortcuts** - The hosts test Siri AI's ability to move data between applications, finding it severely limited.
  • 7 (39:30) **Favorite Moments with Siri AI** - Despite criticisms, the hosts share positive experiences that demonstrate Siri AI's practical value.

+ Full timestamped outline available in the app

Guests on this episode

Show Notes

This week, on AppStories, Federico and John look at what Siri AI is good at, where it needs improvement, and where it might be heading.

On AppStories+, the conversation expands to Federico and John’s experiences with the betas of macOS Golden Gate, iOS 27, and iPadOS 27.

Also available on YouTube here.


Subscribe here.

Subscribe here.

We deliver AppStories+ to subscribers with bonus content, ad-free, and at a high bitrate early every week.

To learn more about an AppStories+ subscription, visit our Plans page, or read the AppStories+ FAQ.


This episode is sponsored by:

  • Daylite: The only made-for-mac CRM solution. Start your free trial today.
  • Decagon: The AI concierge for every customer. Get a personalized demo.


All About Siri AI

AppStories+ Post-Show:


Leave Feedback for John and Federico

AppStories

More from this podcast

AppStories →