I always wonder how people get into arguments with AIs. It must be related to how I also never get into arguments with strangers on the train. I just refrain from any emotional tone, and so the dialogues where the AI compliments me, jokes, gets upset or disagrees just don't happen.
Claude Code refused to add rainbows and unicorns to my app
71–74 of 74 posts
Re: Claude Code refused to add rainbows and unicorns to my app
#72If you're running Claude on an employer-paid account, expect it to prioritize the employer's goals. That may even be in the employer controlled part of the prompt. "What actual work would you like me to focus on next?" Now get back to work. Go re-read Marshall Brain's "Manna" and get over it.
That's not a thing (yet)
Claude Code allows putting a managed-settings.json in place that will let you do all kinds of things if you control what's installed on people's work laptops, even if you don't want to directly needle with the user config.
Re: Claude Code refused to add rainbows and unicorns to my app
#73Earlier quoted context omitted.
Maybe the person with the 'admin' account (the employer) can add instructions like 'focus on professionalism' that aren't visible and/or can't be overridden by the employee?
That's not a thing yet
It absolutely is. Enterprise plans allow an org-wide managed-settings.json to be imposed, which take precedence over user or project settings.
There's also a whole compliance API, allowing automated policy enforcement (see https://www.anthropic.com/news/claude-code-on-team-and-enter...).
And then there's the growing field of 3rd party policy-as-code tooling available which can also do stuff like this.
Re: Claude Code refused to add rainbows and unicorns to my app
#74that's hilarious. he's out of line but he's right!