Are Agent Modes Useful or a Security Risk?

This week, Federico and John look at the hype surrounding AI browsers to see if there’s any there there.

Then, on AppStories+, Federico explains his experiments with lightning fast alternative AI models in Typing Mind.

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.

---

Links and Show Notes

Links and Show Notes

What’s the Deal with AI Browsers

• The Browsers
  • ChatGPT Atlas
  • Perplexity Comet
  • Dia
  • Deta Surf
  • Google Chrome
  • Microsoft Edge
• Security
  • The lethal trifecta for AI agents private data, untrusted content, and external communication
  • 2503.18813 Defeating Prompt Injections by Design
  • CaMeL offers a promising new direction for mitigating prompt injection attacks

Leave Feedback for John and Federico

• AppStories Feedback Form

Follow us on Mastodon

• AppStories
• Federico Viticci
• John Voorhees

Follow us on Bluesky

• AppStories
• MacStories
• Federico Viticci
• John Voorhees