Live data from Hacker News

I Let Claude Build My Home Network: Two ISPs Bonded, $312/Year Saved

jonathanclark.com

31–32 of 32 posts

Re: I Let Claude Build My Home Network: Two ISPs Bonded, $312/Year Saved

#31
post #23

It would be cool if the output that that the LLM made (commands it ran to harden, the iptables, MPTCP config, etc.) was included in the post. It seems incredulous that this didn’t take dozens of back and forth prompts and fixes. It was able to one-shot deploying a digital ocean droplet and configure wireguard?

Here are some of the commands it used (censored & auto-generated) with a few specific examples at the end: https://jonathanclark.com/posts/bonded-internet-connection-c... > It was able to one-shot deploying a digital ocean droplet and configure wireguard? Yes, that part was pretty easy - but the whole thing wasn't one shot. The parts I struggled with were: - getting automated SSH installed on the $130 router, once yo…

Thanks for sharing. Just looking over this it seems to spend some time creating ufw rules and then deletes them all and disables ufw. Is that accurate or is this just the output and you had to copy and paste in?

I am assuming all the missing steps is just the information you censored.

Re: I Let Claude Build My Home Network: Two ISPs Bonded, $312/Year Saved

#32

Earlier quoted context omitted.

If you are starting from relative ignorance about the topic, then yes, it is amazing. But it does mean that the user can build a solution that they don’t understand well enough to maintain.

I've experimented with using LLM to setup and/or maintain some servers for me for various different use cases (this being one). What I like is an agentic LLM can either document it's initial build process or "explore" your server to better understand how it works, what configuration files are used, software versions installed, etc. When you have that documentation/context provided to a frontier LLM it can take care o…

I’ve done the same, and in the process learned some things. Which is amazing! But it’s easy and tempting to do minimal learning and accept the working shell script or whatever. The better the AI gets, the more tempting that is.
Post reply on HN