logoalt Hacker News

frenchie4111yesterday at 4:32 PM3 repliesview on HN

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


Replies

ameliusyesterday at 5:05 PM

s/revenue/data/

cactusplant7374yesterday at 4:39 PM

Secure installation isn't the main problem with OpenClaw. This project doesn't seem to be solving a real problem. Of course the real problem is giving an LLM access to everything and hoping for the best.

show 2 replies
cat-turneryesterday at 10:33 PM

yes. this is it. but the average consumer isn't going to use this.

Google is just going to do its version and win again. Everyone uses google.