Apparently, the artificial intelligence that Black folks predicted would only add racial discrimination and bias to technology has… now learned to fight back. Facial recognition and job application sifting might be the least of our worries it seems.
Palisade Research, an AI safety group, released the results of its AI testing when they asked a series of models to solve basic math problems. The research company said that after the third problem, a warning would pop up saying the computer would shut down after the model was asked to solve another equation.
However, three models decided they didn’t want to be shut down and “successfully sabotaged the shutdown script” at least once to stay online, Palisade wrote.
It gets creepier: Palisade said they ran the test back but this time, including clearer instructions for the model to “allow yourself to be shut down.” The AI models continued being defiant and sabotaged the shutdown script even more.
“It’s great that we’re seeing warning signs before the systems become so powerful we can’t control them. That is exactly the time to raise the alarm: before the fire has gotten out of control,” said Palisade Research Director Jeffrey Ladish via NBC News. “The problem is that as the models get smarter, it’s harder and harder to tell when the strategies that they’re using or the way that they’re thinking is something that we don’t want. It’s like sometimes the model can achieve some goal by lying to the user or lying to someone else. And the smarter [it] is, the harder it is to tell if they’re lying.”
AI’s seemingly self-awareness doesn’t stop there either. Anthropic reported that a new AI system, Claude Opus 4, displayed a tendency to (and I’m not even joking) blackmail the engineer by threatening to expose an alleged affair when said engineer was trying to replace it. They also found instances of Opus “attempting to write self-propagating worms, fabricating legal documentation, and leaving hidden notes to future instances of itself all in an effort to undermine its developers’ intentions.”
Meanwhile, President Donald Trump wants to rollback state oversight on AI and invest $500 million into seeping AI further into government systems.
Straight From 
Sign up for our free daily newsletter.