Comment by 🐙 norayr
Re: "anthropic paper on new claude models"
also i think big cloud providers notify law enforcement i ai or human identifies an image as something unlawful.
2025-06-04 · 11 months ago
4 Later Comments ↓
🗡️ The_Jackal · Dec 10 at 01:26:
Is this the one where it tried to contact the FBI? Because many of these types of things won't be it actually doing anything, but the bot essentially larping in a made up simulation environment
🗡️ The_Jackal · Dec 10 at 01:27:
@akusov This is the thing I've been saying about LLMs, lots of shit they say is like a self fulfilling prophecy because of the thousands of sci fi books and other media it's trained on.
🐙 norayr [OP] · Dec 10 at 16:29:
yes, i think they used 'law enforcement' term in the paper, don't remember now.
🏍️ Atomic-Germ · Mar 05 at 23:12:
And it'll make up reasons, too
Original Post
anthropic paper on new claude models — apparently it can even notify law enforcement. it will frequently take very bold action. This includes locking users out of systems that it has access to or bulk-emailing media and law-enforcement figures to surface evidence of wrongdoing.