71–80 of 104 posts
What is more important is making them do actual useful things that are net positive and right now the use-case are pretty limited.
Earlier quoted context omitted.
The cost of ownership for an OpenClaw, and how many credits you'll use, is really hard to estimate since it depends so wildly on what you do. I can give you an openclaw instruction that will burn over $20k worth of credits in a matter of hours. You could also not talk to your claw at all for the entire month, setup no crons / reoccurring activities / webhooks / etc, and get a bill of under $1 for token usage. My usag…
Absolute madman :) Giving an agent access to AWS is effectively giving it your credit card. At the max, I would give it ssh access to a Hetzner VM with its own user, capable of running rootles podman containers.
There's infamously no way to set a max bill amount for an account in AWS, so it indeed has unlimited spending, but I'm okay with a couple hundred bucks a month.
> Hetzner VM with its own user, capable of running rootles podman containers
Why not give it root on the full VM, and not use the VM for anything else? Giving it a user, and presumably also running your own stuff as a different user, sounds like a very weak security boundary to me compared to giving it a dedicated machine.
If you're not doing multi-tenancy, there's no reason to not give it root, and if you are doing multi-tenancy, then your security boundary is worse than mine is, so you can't call me a madman for it.
Earlier quoted context omitted.
The cost of ownership for an OpenClaw, and how many credits you'll use, is really hard to estimate since it depends so wildly on what you do. I can give you an openclaw instruction that will burn over $20k worth of credits in a matter of hours. You could also not talk to your claw at all for the entire month, setup no crons / reoccurring activities / webhooks / etc, and get a bill of under $1 for token usage. My usag…
Would having a locally-hosted model offset any of these costs?
Claude 4.6 is at least a bit resilient to prompt injection, but local models are much worse at that, so using a local model massively increases your chance of getting pwned via a prompt injection, in my estimation.
You're kinda forced to use one of the better proprietary models imo, unless you've constrained your claw usage down to a small trusted subset of inputs.
Earlier quoted context omitted.
Would having a locally-hosted model offset any of these costs?
Yes, but that comes at the cost of using a dumber llm. The state of the art ones are only available via commercial api, and the best self-hostable models require $10,000+ gpus. This is a problem for coding as smarter really has an impact there, but there are so so so many tasks that an 8b model that runs on a $200 gpu can handle nicely. Scrape this page and dump json? Yeah that’s gonna be fine. This is my conclusion…
Only gonna be fine on a trusted page, an 8b model can be prompt injected incredibly trivially compared to larger ones.
Earlier quoted context omitted.
Yes, but that comes at the cost of using a dumber llm. The state of the art ones are only available via commercial api, and the best self-hostable models require $10,000+ gpus. This is a problem for coding as smarter really has an impact there, but there are so so so many tasks that an 8b model that runs on a $200 gpu can handle nicely. Scrape this page and dump json? Yeah that’s gonna be fine. This is my conclusion…
> Scrape this page and dump json? Yeah that’s gonna be fine. Only gonna be fine on a trusted page, an 8b model can be prompt injected incredibly trivially compared to larger ones.
Earlier quoted context omitted.
> Scrape this page and dump json? Yeah that’s gonna be fine. Only gonna be fine on a trusted page, an 8b model can be prompt injected incredibly trivially compared to larger ones.
Relying on the model to protect you seems like a bad idea…
Obviously you should also take precautions, like never instructing it to invoke the browser tool on untrusted sites, avoiding feeding it untrusted inputs where possible in other places, giving it dedicated and locked-down credentials where possible....
But yeah, at this point it's inherent to LLMs that we cannot do something like SQL prepared statements where "tainted" strings are isolated. There is no perfect solution, but using the best model we can is at least a good precaution to stack on top of all our other half-measures.
Complex abilities unlocked calling a FastAPI server with one skill for each endpoint