Which AI Personal Agents Can You Trust With Your Data?

This article compares four AI personal agents: Instinct, Grok Bot, ChatGPT, and Hermes, analyzing their privacy policies and data handling practices to determine trustworthiness. It highlights the trade-offs between convenience and transparency, particularly regarding sensitive data like passwords and two-factor authentication codes. The author also provides practical advice on auditing and removing third-party app access from Google accounts.

• Four AI personal agents (Instinct, Grok Bot, ChatGPT, Hermes) are compared for data trustworthiness.
• Instinct is noted for its resourcefulness and proactivity but raises concerns about handling passwords and 2FA codes.
• Grok Bot offers a team of cloud-based bots, but questions remain about data deletion from its persistent cloud computer.
• ChatGPT and Codex are favored for their flexibility and extensive plugin options, with a setting to prevent data usage for model training.
• Hermes is an open-source agent running locally on a Mac Mini, primarily used for scheduled tasks.
• Prompt injection is identified as a potential risk where agents could leak data.
• Users are advised to audit and remove unnecessary third-party apps connected to their Google accounts using AI assistance.
• Trust in AI agents is linked to the level of access granted and the transparency of their operations.
  https://bender.layer3.press/articles/0c4a7dae-43b2-436c-a1f1-8007979252c8