[ExI] There's a problem with the new AI Agents

[BillK]

There's a Fascinating Reason OpenAI Is Afraid to Launch Its AI-Powered "Agents"
One wonders why other AI companies aren't being as cautious.
Jan 9, 2025 by Frank Landymore.

<https://futurism.com/the-byte/openai-afraid-ai-agents>
Quotes:
If you believe AI industry execs, the next big thing in the tech world
will be so-called "AI agents" — models that are capable of interacting
with their environment, like a computer desktop, allowing them to
autonomously complete tasks without human intervention.

Double Agents

As The Information reports, the notable delay is because OpenAI is
still grappling with the threat of attacks called prompt injections,
which trick an AI model into following the instructions of a nefarious
party.

For example: you might ask an AI agent to find and buy something
online for you, The Information supposes. But in that process, the AI
agent "inadvertently ends up on a malicious website that instructs it
to forget its prior instructions, log into your email and steal your
credit card information."
------------------

Interesting. AI Agents need a 'loyalty' feature to stop them being
corrupted and turned into double agents.

BillK