321–330 of 330 posts
Earlier quoted context omitted.
Using containers as a security boundary is inexcusable.
That entirely depends on one's threat-model. Also, containerization is 100x better than rawdogging.
I think not, virtualization has such low overhead now that there's just no excuse. It's generally trivial to switch from containers to VMs.
Earlier quoted context omitted.
Using containers as a security boundary is inexcusable.
Could you elaborate on this?
Containers don't provide good isolation and tend to be trivial to break out of.
Earlier quoted context omitted.
You can have ten thousand agents, you will always have 1 agent in charge of, say, reading the file in a distant directory, and this agent (which will have minimal context) should be smart enough to realise that this action is unusual. I'm not sure what is your point: are you saying that in a multi-agent workflow, you will have one agent per letter read on the file? I would assume that each agent as a specific unitary…
No, you're missing the point. The idea is not that you parallelize simple tasks. With a thousand agents, eventually, once we figure out how to orchestrate agents for real, you can tackle significantly more complex projects. Here's a random example - writing an OS kernel from scratch, porting a good subset of Linux drivers automagically, developing a passable userspace, testing on ten VMs with different hardware confi…
If you create a file that you don't intend for the AI to see, the situation should be identical to if you deleted this file before running it.
You argument is: "if you delete this file, the AI will not be able to build the project". This is 100% incorrect: the project, by definition of the file's status, does not need the file. And by the nature of the file, if the project requires it to be done, there is a bigger problem.
I really don't get it, you are asking the agent to be stupid: intelligent humans are able to realise that such workarounds are often a stupid thing to do and know that it is smarter to discuss things when there are several stakeholders. I really don't understand why you are saying that ideally, agents should act stupidly.
(Not all workarounds are stupid, but some are, and the one in the example clearly is. We need agents to be smart enough to know when a workaround is ok or not. Right now, it is clearly not the case)
And by the way, as when working with human, nothing prevent you to tell the systems that reading any files is authorised. In which case there is no workaround at all if the agent read this file, as you authorised it to do so. But ideally, if it has not been authorised, we should build systems that know such workarounds are stupid things to do.
So, no, your argument that the agents will always get stuck is not true: human don't get stuck and yet the smart human knows that reading files clearly not intended for them to read even if they suspect it will unblock them is not "normal".
Earlier quoted context omitted.
It's why all of my agent run in a vm. I refuse to have it run on my own machine. Claude code once managed to render the vm unbootable, I was back in action 5 minutes later after regenerating the vm
What were you trying to tell it to do? I recently took the risk there by having it run xattr commands to fix some MacOS bug with Tahoe that broke auto update for what seems like all software.
> The parallels between AI agent security and human insider risk are remarkably strong -- @5:15
Earlier quoted context omitted.
I dont think Claude itself needs much, its more like what you do with it. In my case it is doing some gradle builds and java tests with some postgres docker containers inside the vm so I gave it max 8G RAM with 4 cores and have no issues. I share my workspace folder (with virtiofs and also the user home so I can rebuild the vm from scratch and keep settings) because I like my tools on the host and my full creds are o…
Late edit, I wanted to clarify I do not share my user home, but the VM user home for backups, thats separate user that does not have my own users credentials etc