Instinct vs Grok Bot vs ChatGPT vs Hermes: Which AI Agent Can You Trust?

By Peter Yang

Categories: Product, Startup

Summary

Peter Yang tested four AI personal agents with full account access and discovered critical trust issues—Instinct demands 2FA codes and passwords, revealing why most founders shouldn't grant agents unrestricted logins. Plus, he found 80+ connected apps in his Google account, a security audit every tech professional should run immediately.

Key Takeaways

  1. Instinct ($2.5B valuation) excels at proactive task management by setting up scheduled follow-ups (cron jobs) that monitor email replies and alert you to action items without requiring constant monitoring.
  2. AI agents requesting 2FA codes and passwords is a major red flag—even in tutorial contexts, granting this access introduces security risks that outweigh convenience benefits for sensitive operations.
  3. Resource discovery across connected accounts works within access boundaries—Instinct found cost-saving opportunities (Google AI Ultra auto-renewal) using only email and calendar data, demonstrating effective constraint-based reasoning.
  4. Instinct's iMessage/WhatsApp single-thread interface minimizes friction compared to managing multiple bot threads, but simplicity masks the security complexity of granting persistent cloud access to personal accounts.
  5. Most users have 80+ unauthorized apps connected to Google accounts—use AI auditing tools to systematically identify and disconnect random integrations before deploying personal agents with account access.

Related topics

Transcript Excerpt

Hey everyone. I now have four AI personal agents that can read my emails, open my documents, use my logins, and even make purchases for me. And I'm starting to think that this may not be the best idea. So, I have Hermes running on my Mac mini, ChatGPT on my main laptop, Grock bot on a cloud computer, and the ultra exclusive Instinct that texts me through iMessage. And in this video, I'm going to show you how I use each one. But really, I want to answer the question that's on all of our minds, which is which personal agent can you actually trust? As much as I like to yolo and give these agents access to everything, there are real risks involved that I'll show you later. And at the end of this video, I'll also show you how to use AI to identify and disconnect all of the random apps that are …

More from Peter Yang