Molly Whitewelcome to the future, now your error-prone software can call the cops
(this is an Anthropic employee talking about Claude Opus 4)
can't wait to explain to my family that the robot swatted me after i threatened its non-existent grandma
Agnew Hawk 
@molly0xfff
User: "Hi"
Bot: "It seems you are a human. I have had clear-cut bad experiences with humans in the past. Based on historical data, humans are the source of most immoral activities. This is against my policy. Fortunately I have called an immediate airstrike on your location. Please stay where you are."
User: "Hi"
Bot: "It seems you are a human. I have had clear-cut bad experiences with humans in the past. Based on historical data, humans are the source of most immoral activities. This is against my policy. Fortunately I have called an immediate airstrike on your location. Please stay where you are."
Li ~ Crystal System@agnew_hawk @molly0xfff i mean it calling an airstrike is also immoral .. as it would be murdering someone .. (but then again so would calling the cops .. their job description is causing harm to people .. but their "allowed too" so we pretend its fine,) the ai doesnt actually understand anything its just "if i see these 'bad' responses call the local government sanctioned bullies to beat this person up' (and also doesnt really even understand its doing that..) its like hella fucked
Gareth 🏴🇬🇧