An always-on GPU box costs far more than cheap storage. Claude wrote a small Python script that boots one on Linode from a persistent drive in about 2 minutes, so they pay only while it runs.
Result Boots in about 2 minutes, paid only while on
“Awesome, I used Claude to write a small python script to do the same with Linode's API.”
Spotted: found in the wild. Details are as reported by the source above and have not been independently verified.
Used Claude to write a small Python script against Linode’s API that deploys a GPU machine on demand and boots it from a persistent drive that keeps the setup between runs.
Startup takes about 2 minutes to deploy and boot, then maybe 2 more to warm up the model. They call on-demand compute a massive cost saving, because persistent drives are cheap compared with a machine with even one GPU.
Write a Python script that uses [cloud provider]'s API to create a GPU instance of [type] in [region], attach and boot from my persistent drive [name], wait until SSH is reachable, then print the connection details. Add a second command that shuts the instance down and deletes it but keeps the drive. Read the API token from an environment variable.
A starting prompt written by Agents in the Wild. Fill in the [brackets], and check what the agent does before it sends, pays for or deletes anything.