News for hackers. Stuff that matters.
Re:Foyle: You build it, AI should run it by from-nibly on Wednesday October 16, 2024 @06:51PM (#41864678)
> As developers today, we often know what we need to do but struggle with the how; [deplyment commands, permissioning commands] ... Foyle solves this problem by turning your intent into executable commands.

In my experience, no developers don't know what they need to do. They have an app that does stuff on their laptop. Between that and production they often have no clue.

Infra is plumbing, and plumbing is contextual details. These details are the very specific things that an LLM doesn't have access to.

The fact that there is a Palo firewall between two subnets means deploying your app isn't a kubectl away. The fact that DNS goes through another team means routing myapp.mycompany.com requires a jira ticket. Heck the fact that you use istio means ingress works completely differently.

How does foyle address these kinds of issues?

Re:Foyle: You build it, AI should run it by jlewi on Thursday October 17, 2024 @10:16AM (#41869904)
The premise of Foyle is that you can solve this problem with runbooks that walk you through the steps to deploy your app; in this case setting up appropriate networking. Problem is no one wants to read or write documentation. So Foyle tries to learn by observing what commands people do. So in this case, an expert (e.g. someone on the infra/platform team) deploys an app or troubleshoots a networking problem and they do this by creating a notebook which contains some exposition and the commands. Foyle learns from this. So now when an app developer goes to deploy a new app, they start a document "Deploy Caribou" and Foyle starts suggesting the steps and commands to deploy it.
Re:Foyle: You build it, AI should run it by lernarx on Thursday October 17, 2024 @06:28PM (#41874446)
Why would an expert work towards making himself redundant?