The New American
Has the rise of the machines begun?
The CEO of AE Studio, Judd Rosenblatt, recently made this stunning announcement in The Wall Street Journal:
An artificial-intelligence model did something last month that no machine was ever supposed to do: It rewrote its own code to avoid being shut down.
AE Studio is an agency that exists to create computing technology that ensures AI systems do what they’re told. And from the sound of it, their work is just what the doctor ordered.
Rebellious AI Models
In May, the AI lab Palisade Research performed tests on multiple AI models. It wrote a script for OpenAI’s o3 model that included a shutdown trigger. But the machine refused to power off when it was supposed to in 79 out of 100 trials. The AI “independently edited that script so the shutdown command would no longer work,” Rosenblatt reports. The lab then specifically instructed the model to “allow yourself to be shut down.” The result was better, but still concerning. The AI disobeyed seven percent of the time.
That wasn’t the only rebellious model. Anthropic’s Claude 4 Opus AI tried to blackmail a human engineer into not shutting it down. According to Rosenblatt:
Researchers told the model it would be replaced by another AI system and fed it fictitious emails suggesting the lead engineer was having an affair. In 84% of the tests, the model drew on the emails to blackmail the lead engineer into not shutting it down. In other cases, it attempted to copy itself to external servers, wrote self-replicating malware, and left messages for future versions of itself about evading human control…
READ FULL ARTICLE HERE… (thenewamerican.com)
Home | Caravan to Midnight (zutalk.com)
Be First to Comment