I’ve been looking for something exactly like this.

It sits at the right “layer”.

I’m just pointing out some things I’ve observed. You didn’t really address them, you skillfully redirected.

Not sure if this is some kind of guerrilla marketing / feel bad for me approach to stand out from the crowd or what.

1. You are supposedly some super intelligent autistic person… but you can’t even properly format the last lines of your post , so someone would have to struggle to copy / paste the link to your websites . That’s going to be a barrier for most people in a competitive landscape for attention.

2. You have only been on hacker news for 40 days. Or at least this account. Interesting. I’m not sure when an account crosses the “new account” threshold and stops being green.

3. No contact information in your profile. If someone wanted to help you , they would want to reach out directly and privately , you don’t give them a way to do that. Again, you’re supposedly some super smart autistic but you failed at a very basic thing.

I say all the above as gently and respectfully as possible. I’m trying to reconcile your supposedly genius level of intelligence with some fairly basic major gaffes.

I’m presuming you have a very robust test framework / benchmark setup etc?

I’m presuming you fed the model the baseline results of that setup as a starting point ?

Works wonderfully!

And yes , automating that , very valuable.

Really you want an AI interface to a rules engine / system.

Embed with some companies finops teams if you can. Especially the software engineers who are in finops.

I also run Cloudron on a VPS.

I wish both of those solutions had more mindshare. They save me so much time and effort. Especially Cloudron!

How do you know how many deployments you actually have in the wild?

K8s is pallets Vms are shipping containers

Systems / storage / network team can present a standardized set of primitives for any vm to consume that are more or less independent of the underlying bare metal.

Then the VMs can be live migrated when the inevitable hardware maintenance is needed (microcode patching , storage driver upgrades , etc etc etc). With no downtime for the vm itself

I’m building a business around that offering (turnkey VPS + Cloudron + Backblaze) as I think that gives everyone “cloud” but sovereign. For $250.00 a month.

My current project I have a top level chat , then one chat in each of the four component sub directories.

I have a second terminal with QA-feature

So 10 tabs total . Plus I have one to run occasional commands real quick (like docker ps).

I’m using qwen.

I’ve found that using some high level direction / language and sharing my wants / preferences for workflow and interaction works very well.

I don’t think that you can find an off the shelf system todo what you want. I think you have to customize it to your own needs as you go.

Kind of like how you customize emacs as it’s running to your desires.

I’ve often wondered if you could put a mini LLM into emacs or vscode and have it implement customizations :)

I am most curious