Not sure I understand the problem. Are people just letting AI do anything? I use Claude Code and it asks for permission to run commands, edit files, etc. No need for sandbox
Yes, people very much are, and that's exactly the problem! People run `claude --dangerously-skip-permissions` and `codex --yolo` all the time. And I think one of the appeals of opencode (besides cross-model, which is huge) is that the permissions are looser by default. These options are presumably intended for VM or container environments, but people are running them outside. And of course it works fine the first 100 times people do it, which drives them to take bigger and bigger risks.
After reading their main page I saw that they are just another provider of CI that claims to be faster. Not sure about others but to me the problem with CI/CD has never been that it's slow. The painful points are setting it up and getting it to work. Once that's done everything after it's not that painful
Oh that's just how it is on Windows though. Seems like on mac the minimize button provides a buffer between maximize and close. I'd rather accidentally minimize if I'm trying to maximize than close the window
Did your state chip your pet or was it a private company? I think they are saying that there are no centralized authorities and you depend on private companies
reply