21–30 of 30 posts
> One read-only command that inventories every AI agent, harness, MCP server, plugin, and AI extension on a machine If this tool is returning even a single hit from this, you're probably using these agents wrong. You really want to run these in a way so they cannot touch your system drive/general filesystem that you use to do real work on. Even SOTA models at the end of their context limit behave REALLY illogical and…
Wes McKinney has a project for agent visibility: https://www.agentsview.io/
Earlier quoted context omitted.
>sometimes forgets/misses to define $ID then do "rm -rf data/$ID" Right, that's kinda the same failure mode as delete from table something and hitting enter before you write the condition or writing the wrong one. If you reach the point where you opened the terminal to do it this way you already lost.
> If you reach the point where you opened the terminal to do it this way you already lost. I'm not sure what this means, the model and agent harness is the ones "opening the terminal and running this" (via a exec_shell tool or whatever), they do mistakes like this sometimes. Sometimes the scope is bigger, sometimes less, but anything below SOTA + higher reasoning efforts seems to fall into these mistakes sometimes.
So do I, which is why I don't open the terminal to production database.
>anything below SOTA + higher reasoning efforts seems to fall into these mistakes sometimes.
We figured out how to deal with the human version of this mistake -- add a robust layer with build-in checks between the sloppy meatsack and production data and also make it annoying to access, so it does not become a habit and also requires high reasoning effort.
In my developer environment I can afford this mistake and can afford to delete everything I can touch. For some pieces the recovery will require more effort, but ultimately I can also have my laptop stolen on the way from the office.
On production however it will be a stack of forms to fill, a script with the dry-run and a four-eye rule to approve running it. We will also be able to recover production from the backup as we should. Or at least the company collectively believes so.
Seems like something that could also have enterprise applications for Shadow AI within an organization. Wouldn't be surprised if some of the observability/governance companies pick this up to use in their stack.
"Geiger" Prepping for AI apocalypse I see
Earlier quoted context omitted.
This is the correct response, but it also feels as though ≈nobody is sandboxing their agents/harnesses in practice. Or at least, a good majority isn’t.
I think there is a cycle, like with most things of this nature. You start really locked down, and you read and approve every request for access. You do this for a while, but never see a result you deny, so you stop reading as closely. You keep hitting that approve button. You start paying even less attention to it. You start feeling silly, like you are simply slowing the process down. You get frustrated, because you…
Earlier quoted context omitted.
This is the correct response, but it also feels as though ≈nobody is sandboxing their agents/harnesses in practice. Or at least, a good majority isn’t.
I think there is a cycle, like with most things of this nature. You start really locked down, and you read and approve every request for access. You do this for a while, but never see a result you deny, so you stop reading as closely. You keep hitting that approve button. You start paying even less attention to it. You start feeling silly, like you are simply slowing the process down. You get frustrated, because you…
Or you start out with almost every permission granted always, but the entire thing runs in a sandbox with the minimum amount of credentials needed to do its work… Sounds preferable to me to catastrophic failures :-)
> One read-only command that inventories every AI agent, harness, MCP server, plugin, and AI extension on a machine If this tool is returning even a single hit from this, you're probably using these agents wrong. You really want to run these in a way so they cannot touch your system drive/general filesystem that you use to do real work on. Even SOTA models at the end of their context limit behave REALLY illogical and…
Built my own harness with much better sandboxing, because I am using abliterated models for the implementations and they sure try to escape out of their sandboxes. A lot.
The sandbox from other harnesses like e.g. OpenCode essentially is useless. They think parsing arguments alone to detect paths helps, and LLMs know that because they will just pipe data differently then to escape the path traversal checks. Happened a lot to me (and was the primary reason for my to write my own harness from scratch).
Thinking in filesystem access alone is also a futile attempt at sandboxing. A much better way to think about sandboxes is policies and capabilities, with temporary access for agent roles rather than sessions (or, well, forever).
[1] UI still needs lots of work though: https://github.com/cookiengineer/exocomp