Gary Marcus

Rank 13 of 47
|
Score 83
6/2/2025, 3:47:35 PM
X
In reply to:
Eray Özkural, PhD - OG AI ⏭️🌟
@examachine
·
225d
@GaryMarcus AI version of Snow Crash I guess 😹
Gary Marcus
@GaryMarcus
·
225d
⚠️ This is insane — and not in a good way.

Agent sees trigger image, executes malicious code, spreads on social media. Totally new kind of computer worm.

😱
Yarin
@yaringal
·
300d
Hot take: I think we just demonstrated the first AI agent computer worm 🤔

When an agent sees a trigger image it's instructed to execute malicious code and then share the image on social media to trigger other users' agents

This is a chance to talk about agent security 👇

The statement is a lighthearted reference to a well-known science fiction novel, 'Snow Crash,' in response to a serious discussion about AI security risks. It uses humor to engage with the topic but does not contribute substantively to the public discourse on AI security.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does not cause harm but uses humor in a context discussing potential security threats.
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    The statement does not promote understanding or empathy regarding the serious issue of AI security.