Agents of Chaos (agentsofchaos.baulab.info)

by luu 18 comments 137 points
Read article View on HN

18 comments

[−] cyanydeez 46d ago
This is begging to turned into a youtube style "Real World", where you pit 12 humans with 12 AIs and they're only allowed to interact through CLIs.

Then you slowly reveal they're all humans.

[−] aledevv 46d ago
For agents, any direct access to execution tools (code, shell, file system, browser, and external services, etc.) exponentially increases vulnerabilities and error surfaces, especially when multiple agents interact with each other.

This makes it even more crucial to have the most seamless ability possible to implement reverse and restore previous States.

The risk of the Agents actions becoming irreversible at the system level must be minimized.

I wonder how much all this can impact (and certainly will impact) the Real World, which will be increasingly robotized and automated: public services, finance, hospitals, schools, public administrations, military sectors (!), etc.

[−] whatever1 46d ago
I don't understand why LLMs get a free pass when all of the existing businesses have to play by the rules.

Businesses have to comply with IP, privacy, HIPAA, security and safety laws to name just a few.

NONE of these apply to the LLMs.

Of course I can now build and deploy an app to hospitals in a weekend since I can circumvent all of the difficult parts using the magic LLMs. If asked why, the response is "It's AI!"

[−] manmal 46d ago
The TLDR is that current agents are as problematic as many of us already know they are:

> unauthorized compliance with non-owners, disclosure of sensitive information, execution of destructive system-level actions, denial-of-service conditions, uncontrolled resource consumption, identity spoofing vulnerabilities, cross-agent propagation of unsafe practices, and partial system takeover

[−] iqihs 46d ago
as someone who is working in the cybersecurity space and recently obtained my CISSP designation, i am left wondering when the pedagogy of my field will expand and include a separate domain dedicated to AI agent safety and security best practices

it really does feel like we are way behind in the way we train people in cyber compared to the pace of the development of agentic AI, robotics etc

[−] e7h4nz 46d ago
In this problem domain, I believe humanity is still in a very early stage. What we can do is treat the agent and its operating environment as a "black box" and audit all incoming and outgoing network request traffic.

This approach is similar to DLP (Data leak prevention) strategies in enterprise-level security. Although we cannot guarantee that every single network request is secure, we can probabilistically improve safety by adjust network defense rules and conducting post-event audits on traffic flow

[−] AIorNot 46d ago
All this to say: OpenClaw is hella insecure and unreliable?

I mean all of in the space already know this but I suppose its important to be showcasing the problems of systems of agents

[−] paidev 46d ago
Looks more like a vibe coded paper for me. Has very low substance. Blog like stuffs. I can’t see the amount of slop in the papers soon.
[−] Sim-In-Silico 46d ago
[dead]
[−] charlotte12345 46d ago
[dead]
[−] noritaka88 45d ago
[flagged]
[−] P-MATRIX 46d ago
[dead]
[−] kevinbaiv 46d ago
[flagged]
[−] heyethan 46d ago
[flagged]
[−] dnaranjo 46d ago
[dead]
[−] hackermeows 46d ago
your IQ > Model IQ- you will have good results as you have the ability to detect when model is wrong.

your IQ < Model IQ - god bless you.

[−] EGreg 46d ago
This is exactly why I built Safebots to prevent problems with agents. This article shows how it can address every security issue with agents that came up in the study:

https://community.safebots.ai/t/researchers-gave-ai-agents-e...