Currently, he is working on a stealth project involving "Inverse Reinforcement Learning"—teaching AI to understand human values by watching what humans actually do, rather than what they say they do. It is a subtle distinction, but one that could finally bridge the gap between cold logic and human intent.
“Just because a Large Language Model can write an email doesn't mean I want it to,” he warns. “Does it sound like me? Does it capture my irony? If not, you’re just adding noise.” sumanth dintakurthi
“A self-driving car that makes a mistake is a headline,” he explains, leaning back in his chair. “An AI assistant that makes a decision for a CFO and gets it wrong? That’s a catastrophe. We don’t need more automation; we need better augmentation .” Currently, he is working on a stealth project