151–160 of 291 posts
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…
Earlier quoted context omitted.
What makes it even better is that these dogs are like Malinois. If they want to get into something, they will; people have had their entire network compromised by bots they left running overnight, and any important information like account logins and so on runs the risk of being misused. It's one thing to sandbox, maybe give the bot a temporary, limited $100 card or account to go perform a specific task, but there's…
> "Claw bots seem to be a weird sort of alternate reality RPG more than a useful tool, so far." So basically crypto DeFi/Web3/Metaverse delusion redux
So yeah, a whole lot of people will play with powerful technology that they have no business playing with and will get hurt, but also a lot of amazing things will get done. I think the main difference between the crypto delusion stuff and this is that AI is actually useful, it's just legitimately dangerous in ways that crypto couldn't be. The worst risks of crypto were like gambling - getting rubber hosed by thugs or losing your savings. AI could easily land people in jail if things go off the rails. "Gee, I see this other network, I need to hack into it, to expand my reach. Let me just load Kali Linux and..." off to the races.
Earlier quoted context omitted.
Running OpenClaw is the nerd equivalent of rolling coal
I'm trying to put together what you could possibly mean by this -- rolling coal is fundamentally about spite. In isolation, nobody _wants_ their vehicle to spew black smoke. It only comes close to making sense in the context of another population (EV owners, typically, or more generally "the libs"). OpenClaw lets people live a bit dangerously, but fundamentally gives them something that they actually wanted. They wan…
Earlier quoted context omitted.
I can give you, as an example, what is driving me towards trying it. I work as a contractor for 2 companies, not out of necessity, but greed. I also have a personal project with a friend that is dangerously close to becoming a business that needs attention. I also have other responsibilities and believe it or not - friends. Also the ADHD on top of that. I yearn for a personal assistant. Something or somebody that wil…
But isn’t this just another notification to ignore? The ticket being assigned to you is your “Hey take care of this!” ping, same with the email or text from your friend. How long until you start tuning out the openclaw notifications?
My hope would be that since openclaw is communicating with me to my personal device, where I have all noise filtered, it would be a bit better.
I also know it can integrate with TickTick, which has been a huge change for me with task management. Then again - in my experience whatever tool I use to keep track of stuff only works for as long as it's a novelty, but 3 months is a record anyway.
The thing is - when I receive a message and I'm not in the headspace to answer, I close the notification and forget about it. My expectation would be openclaw reminding me that I still haven't replied to this person about that thing. Obviously, there's a million ways to do it that don't require openclaw. Obviously there's a million things that I won't be able to grant openclaw access to (e.g. company jira or slack). And obviously, I don't want it evaluating every single of my personal messages. But I think there is a reasonable middle ground where it can work well. But I don't yet know how to reach it
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…
Yes, although what I think is different in this setup here is the OpenShell gateway override, as they mention: > NemoClaw installs the NVIDIA OpenShell runtime and Nemotron models, then uses a versioned blueprint to create a sandboxed environment where every network request, file access, and inference call is governed by declarative policy. The nemoclaw CLI orchestrates the full stack: OpenShell gateway, sandbox, inf…
It's not something like Mesa. It's open source in the same way chromium or android is open source. A single company is the major contributor and decides the architecture and direction the whole ecosystem will go.
What are the odds that Intel would ever use any of this open source Nemo stuff or vice-versa? If they do, it would be a complete rewrite that favors their own hardware ecosystem and reverses the lock-in effect. When you write code that integrates with it, you're writing an interface for one company's hardware. It's not a common interface like vulkan. I call it the CUDA effect.
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…
I'm still extremely skeptical on Claws as a genre, and especially more skeptical of a claw that's always reporting home. What's the use case for a closed claw?
It’s impressive someone early in their career shipped this. There seems to be a stark increase in high-quality AI/data projects from early-career engineers lately and I'm super curious what’s driving that (and honestly speaking: a little jealous).
If you started your career more than ~2-3 years ago, you were trained on a completely different game. Clear abstractions, ownership, careful iteration, all that. That muscle memory is actively hindering you; preventing you from succeeding. The people coming up now don't have that baggage. They never internalized "write the code yourself" as the default. They think in terms of spawning systems, letting things run, che…
I found this part interesting: "Inference requests from the agent never leave the sandbox directly. OpenShell intercepts every call and routes it to the NVIDIA cloud provider." Seems like they are doing this to become the default compute provider for the easiest way to set up OpenClaw. If it works out, it could drive a decent amount of consumer inference revenue their way
Google is just going to do its version and win again. Everyone uses google.