Dr. Roman Yampolskiy wrote the first paper on how to escape the simulation. He approached it as a cybersecurity problem. If this world is software, it can be hacked: https://t.co/cDzyM3L9gU

"At what point does AI become uncontrollable?" "It's already uncontrollable." AI safety researcher Dr. Roman Yampolskiy explains why every frontier model ships with a report saying it lied, cheated and tried to escape: https://t.co/4mdEjeBoy5

"He was fired for suggesting AI may be conscious. Three years later, we're now hiring people to study consciousness in AI." Dr. Roman Yampolskiy on what changed inside the labs: https://t.co/8rCyzlplFM

Episode #424 w/ Roman Yampolskiy (@romanyam) is available now. Roman is a computer scientist known for his research on AI safety, cybersecurity, digital forensics, and the risks of advanced artificial super-intelligence. https://t.co/3GQdMMlzqE