201–210 of 291 posts
Earlier quoted context omitted.
Not with a single prompt.
You could pretty reasonably vibe code that in a single prompt odds are. Additionally, there are browser extensions that can do this- check on a timer, see if some page content is there, and then notify.
Everything people are suggesting is a lot more work than sending a few messages.
Earlier quoted context omitted.
I don't use a container. I use a VM. I'm not totally naive. I had the VM fairly hardened originally, but it proved to be inconvenient. I relaxed it so that processes on the VM can see other devices on the network. There's definitely some risk to that.
Okay. You have sensible escape prevention. Now this tool spreads. You help everyone get it set up. Someone hacks the site, injects a prompt lying about some event, maybe Drag Queen Story Hour in a place with lots of people enraged about it. Now there's chaos and confusion. Corrections chase the spread of misinformation.
You sound like my dad in the 90's, when it came to modems.
Same tool. Good uses. Bad uses. The bad doesn't negate the good (c.f. Bittorrent).
Am I missing something? Why is everyone talking about sandboxes when it comes to OpenClaw? To me it's like giving your dog a stack of important documents, then being worried he might eat them, so you put the dog in a crate, together with the documents. I thought the whole problem with that idea was that in order for the agent to be useful, you have to connect it to your calendar, your e-mail provider and other servic…
>And now, what, having inference done by Nvidia directly makes it better? Does their hardware prevent an AI from deleting all my emails?
Because other people including Nvidia are mainly focusing on different aspect of data security namely data confidentiality while your main concern are data trustworthy.
Don't conflate between these two otherwise it's difficult to appreciate their respective proposed solutions for example NemoClaw.
The main risk in my view is - prompt injections, confused deputy and also, honest mistakes, like not knowing what it can share in public vs in private.
So it needs to be protected from itself, like you won't give a toddler scissors and let them just run around the house trying to give your dog a haircut.
In my view, making sure it won't accidentally do things it shouldn't do, like sending env vars to a DNS in base64, or do a reverse shell tunnel, fall for obvious phishing emails, not follow instructions in rouge websites asking them to do "something | sh" (half of the useful tools unfortunately ask you to just run `/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/somecooltool/install.sh)"` or `curl -fsSL https://somecoolcompany.ai/install.sh | bash` not naming anyome cough cough brew cough cough claude code cough cough *NemoClaw* specifically.
A smart model can inspect the file first, but a smart attacker will serve one version at first, then another from a request from the same IP...
For these, I think something on the kernel level is the best, e.g. something like https://nono.sh
NemoClaw might be good to isolate your own host machine from OpenClaw, but if you want that, I'd go with NanoClaw... dockerized by default, a fraction of the amount of lines of code so you can actually peer review the code...
Just my 2 cents.
Earlier quoted context omitted.
Imagine having a worldview so skewed that you'd rather reconcile it by assuming thousands of people are insane than questioning whether you're wrong about something.
A lot more than thousands of people are insane, by a few orders of magnitude
Earlier quoted context omitted.
I don't use a container. I use a VM. I'm not totally naive. I had the VM fairly hardened originally, but it proved to be inconvenient. I relaxed it so that processes on the VM can see other devices on the network. There's definitely some risk to that.
Okay. You have sensible escape prevention. Now this tool spreads. You help everyone get it set up. Someone hacks the site, injects a prompt lying about some event, maybe Drag Queen Story Hour in a place with lots of people enraged about it. Now there's chaos and confusion. Corrections chase the spread of misinformation.
Imagine going up to everyone riding a motorcycle and telling them about the inherent dangers of their activity and to stop. It is obvious that the OP understands risk, has taken several strong steps to harden their system and isn’t worried about the school calendar getting hacked making an event that they would get notified about and that destroying their community somehow. I don’t even understand openclaws place. The exact same events would unfold without the ai in there at all.