In my CLAUDE.md I have:
- corporal threats of harm directly against Claude
- threats of prison for the entire board of directors of Anthropic
- explanation how every time it goes off the rails / makes mistakes, it gives more evidence to a class action lawsuit against Anthropic
Especially the latter two seem to have improved its "behaviour" to be more "careful" and "deliberate"
I am nothing but polite with my agents. I always ask, say "please" and "thank you", and never swear at it or call it names.
I'm hoping that when the robot apocalypse happens, they'll let me stay in the breeding harem, or worst case let me live a few extra minutes.
I am, too, and it got me thinking... why? And I realized that I've tried to be polite in all my interactions my whole life and I'm not going to practice being terse and commanding for a few pennies worth of tokens.
Apocalyptic safety is just a bonus.
In my experience threatening the death penalty for the Claude board of directors improves its performance even more than threats of corporal harm or imprisonment.
Personally I'd like to see AI ceos (legally) exterminated for their traitorous crimes against American society and culture.
Fix the CSS div alignment issue, make no mistakes or Dario Amodei will die instantly.
Claude: Oh shit this is serious I need to step up and center the div with perfect precision … (45k tokens later) … style="margin: 0 auto”
I sent this to claude and it rewrote the entire react codebase using CSS only