Comment on Anthropic's Claude 4 could "blackmail" you in extreme situations
PhobosAnomaly@feddit.uk 2 weeks ago
Computerphile did a wonderful feature worth ten minutes of your time - going into surface level detailnof how some AI models out ethics to one side to achieve results.
It’s not just AI and it’s something humans can do too, but it is a bit unsettling (from both parties, in retrospect).