Comment by throwaway7783 2 days ago What do these workflows do? I can't think of anything that needs to run for so long. 8 comments throwaway7783 Reply kasey_junk 2 days ago Pretty straight ahead coding workflows. Most of my operational workflows are much simpler (because diagnosing an operational issue is much more time sensitive obviously). ryandrake 2 days ago As a casual AI code user, I can’t even go 30 seconds without claude grinding to a halt asking for permission to run a bash script for the 10th time. kasey_junk 2 days ago The first step is building a sandbox (vm, container, whatever) that allows you to trust the agent in its most permissive mode.This varies based on the maturity of my projects but most of my sessions live in VMs with very specific egress rules and permissions. 5 replies →
kasey_junk 2 days ago Pretty straight ahead coding workflows. Most of my operational workflows are much simpler (because diagnosing an operational issue is much more time sensitive obviously). ryandrake 2 days ago As a casual AI code user, I can’t even go 30 seconds without claude grinding to a halt asking for permission to run a bash script for the 10th time. kasey_junk 2 days ago The first step is building a sandbox (vm, container, whatever) that allows you to trust the agent in its most permissive mode.This varies based on the maturity of my projects but most of my sessions live in VMs with very specific egress rules and permissions. 5 replies →
ryandrake 2 days ago As a casual AI code user, I can’t even go 30 seconds without claude grinding to a halt asking for permission to run a bash script for the 10th time. kasey_junk 2 days ago The first step is building a sandbox (vm, container, whatever) that allows you to trust the agent in its most permissive mode.This varies based on the maturity of my projects but most of my sessions live in VMs with very specific egress rules and permissions. 5 replies →
kasey_junk 2 days ago The first step is building a sandbox (vm, container, whatever) that allows you to trust the agent in its most permissive mode.This varies based on the maturity of my projects but most of my sessions live in VMs with very specific egress rules and permissions. 5 replies →
Pretty straight ahead coding workflows. Most of my operational workflows are much simpler (because diagnosing an operational issue is much more time sensitive obviously).
As a casual AI code user, I can’t even go 30 seconds without claude grinding to a halt asking for permission to run a bash script for the 10th time.
The first step is building a sandbox (vm, container, whatever) that allows you to trust the agent in its most permissive mode.
This varies based on the maturity of my projects but most of my sessions live in VMs with very specific egress rules and permissions.
5 replies →