zlacker

[return to "Claude Code for Infrastructure"]
1. latchk+w91[view] [source] 2026-02-05 00:48:46
>>aspect+(OP)
I'm working towards this for actual infrastructure, for serving up AI compute.

"install kimi 2.5 on a 4x mi300x vm and connect the endpoint to opencode, shut it down in 4 hours"

We're getting close.

◧◩
2. verdve+ha1[view] [source] 2026-02-05 00:52:42
>>latchk+w91
this is not the way to do devops, we have IaC, reviews, and promotion for a reason

it's clear infra level decisions are well beyond what LLMs / agents are capable of today, this is area is too high risk, devops is slow to adopt new tooling because of its role and nature

◧◩◪
3. latchk+Ea1[view] [source] 2026-02-05 00:55:55
>>verdve+ha1
wow, you downvoted me.

this is still devops. we use cloud-init to setup the vm.

i run the underlying hardware infrastructure and we've automated the provisioning such that we have an api that can start/stop compute at will. even bare metal.

the point of this is that the current $/token model is awful, especially if you're using a lot of tokens. it should be $/minute. pay for what you use.

◧◩◪◨
4. verdve+Gc1[view] [source] 2026-02-05 01:14:40
>>latchk+Ea1
tokens are a rough proxy for usage over time, so I am paying for what I use, less than running a TPU pod myself, required for the models I use, i.e. I don't saturate the compute so it's cheaper to pay-go
[go to top]