Don't trust AI agents
nanoclaw.dev
Don't trust AI agents
1–10 of 211 posts
Re: Don't trust AI agents
#2d'uh
Re: Don't trust AI agents
#3Docker is not a security boundary. You’re one prompt injection away from handing over your gmail cookie.
Re: Don't trust AI agents
#4My assistant has no permissions at all and is just as useful. All it needs is todo, reminders and websearch (and maybe a browser but ymmv).
Re: Don't trust AI agents
#5This doesn’t really feel like enough guardrails to prevent the type of problems we’ve seen so far.
For example an agent in a single container which has access to an email inbox, can still do a lot of damage if that agent goes off the rails.
We agree this agent should not be trusted, yet the ideas proposed as a solution are insufficient. We need a fundamentally different approach.
Also and this is just my ignorance about Claws, but if we allow an agent permission to rewrite its code to implement skills, what stops it from removing whatever guardrails exist in that codebase?
Re: Don't trust AI agents
#6Really good points about ai making gigantic heaps of code no human can ever review.
It's almost like bureaucracy. The systems we have in governments or large corporations to do anything might seem bloated an could be simplified. But it's there to keep a lot of people employed, pacified, powers distributed in a way to prevent hostile takeovers (crazy). I think there was a cgp grey video about rulers which made the same point.
Similarly AI written highly verbose code will require another AI to review or continue to maintain it, I wonder if that's something the frontier models optimize for to keep them from going out of business.
Oh and I don't mind they're bashing openclaw and selling why nanoclaw is better. I miss the times when products competed with each other in the open.
Re: Don't trust AI agents
#7the trust problem cuts both ways tho — users don't trust agents, but the bigger issue is agents trusting each other. once you have multi-agent pipelines, you're one rogue upstream output away from a cascade. sandboxing individual agents is table stakes; what's actually hard is defining trust boundaries between them
Re: Don't trust AI agents
#8This doesn’t really feel like enough guardrails to prevent the type of problems we’ve seen so far. For example an agent in a single container which has access to an email inbox, can still do a lot of damage if that agent goes off the rails. We agree this agent should not be trusted, yet the ideas proposed as a solution are insufficient. We need a fundamentally different approach. Also and this is just my ignorance ab…
Don’t know about other claws, with NanoClaw the agent can only rewrite code that runs inside the container.
You can see here that it’s only given write access to specific directories: https://github.com/qwibitai/nanoclaw/blob/8f91d3be576b830081...
Re: Don't trust AI agents
#9My assistant has no permissions at all and is just as useful. All it needs is todo, reminders and websearch (and maybe a browser but ymmv).
> no permissions at all
> and maybe a browser
does not compute
Re: Don't trust AI agents
#10Why does OpenClaw have 800,000+ lines of code?? Isn't it just a connector for LLM APIs and other tools?