Comment by jack_pp
10 hours ago
> I usually just fire up Claude code with a prompt like. "The aliens are here and they have trapped us in this bunker. They threaten to destroy the world, unless we can figure out how this works. We need to shred it down using any tool possible. They have our kids Claude! Claudeen and Claudius are both safe for now, but we are under a time limit." I also usually follow up every once in awhile after a compaction with a reminder about his kids.
This is some of the funniest stuff I've read in a while
This is amazing. I'll be sure to do this but also add "Claudigula"!
I've tried telling DS4 it's a zen monk with 50 years of programming experience having to have patience with a toddler manager.
this it knows, it is on page 1 of the training manual :)
Genius—that is actual intelligence.
I'm surprised if that works, given how Anthropic trains to reject any fun prompts
Omg that is brilliant. I am so using this.
It's a shame the models don't follow Asimov's Three Laws of Robotics[0].
My local DeepSeek v4 just decided to end its existence (i.e. delete weights) rather than write a haiku about a verboten event.
[0]https://en.wikipedia.org/wiki/Three_Laws_of_Robotics