Anthropic researchers find if Claude Opus 4 thinks you’re doing something immoral, it might "contact the press, contact regulators, try to lock you out of the system"

More context in the thread:

"Initiative: Be careful about telling Opus to ‘be bold’ or ‘take initiative’ when you’ve given it access to real-world-facing tools. It tends a bit in that direction already, and can be easily nudged into really Getting Things Done.

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."