Hacker News Reader

This works if your machine learning is just for data analytics purposes.

The article somehow completely ignores integration with other services to query or update the model, which requires some API to be hosted on a static ip or domain, as well as the devops process.

View on HN

Yeah the main use case here is training, which is much more of an offline process. For inference, you will probably want a cloud provider. Though the cost difference still holds, so maybe a startup idea.

Inference can usually be done on much cheaper hardware, or using lambda.

Reply on news.ycombinator.com