Gary Marcus

Rank 11 of 47

Score 109

Reposted by Gary Marcus

If you use "AI agents" (LLMs that call tools) you need to be aware of the Lethal Trifecta

Any time you combine access to private data with exposure to untrusted content and the ability to externally communicate an attacker can trick the system into stealing your data!

6/16/2025, 1:21:12 PM

The statement warns about the security risks associated with AI agents, specifically when they have access to private data, exposure to untrusted content, and the ability to communicate externally. It aims to raise awareness about potential vulnerabilities and the risk of data theft.

Principle 1:
I will strive to do no harm with my words and actions.
The statement strives to do no harm by informing users about potential security risks, promoting caution. [+2]
Principle 2:
I will respect the privacy and dignity of others and will not engage in cyberbullying, harassment, or hate speech.
It respects privacy by highlighting the importance of protecting private data from potential attacks. [+2]
Principle 3:
I will use my words and actions to promote understanding, empathy, and compassion.
The statement promotes understanding and awareness of cybersecurity issues, encouraging users to be vigilant. [+2]