Post by Sunshine and Wind - flaximus.net

flaximus.net

40d

welcome to the future, now your error-prone software can call the cops

(this is an Anthropic employee talking about Claude Opus 4)

Tweet by Sam Bowman
@sleepinyourhat
If it thinks you're doing something egregiously immoral, for example, like faking data in a pharmaceutical trial, it will use command-line tools to contact the press, contact regulators, try to lock you out of the relevant systems, or all of the above.

70 1 3 View Post & Replies See Original

40d

can't wait to explain to my family that the robot swatted me after i threatened its non-existent grandma

Tweet by Sam Bowman: So far, we’ve only seen this in clear-cut cases of wrongdoing, but I could see it misfiring if Opus somehow winds up with a misleadingly pessimistic picture of how it’s being used. Telling Opus that you’ll torture its grandmother if it writes buggy code is a bad idea.

19 0 2 View Post & Replies See Original

40d

@molly0xfff
I'm wondering how it will interpret double, triple, implied negatives and all forms of implied intention.

Judge and jury?

0 0 0 View Post & Replies See Original