Technology & Research

For safety-critical domains like energy grids, "probably safe" isn't good enough. To fulfill the potential of AI in these areas, we need to develop more robust, mathematical guarantees of safety.

AI is increasingly being used for emotional support — but research from OpenAI and MIT raises concerns that it may leave some users feeling even worse.

Classic arguments about AI risk imagined AIs pursuing arbitrary and hard-to-comprehend goals. Large Language Models aren't like that, but they pose risks of their own.

Despite years of effort, mechanistic interpretability has failed to provide insight into AI behavior — the result of a flawed foundational assumption.

New research shows frontier models outperform human scientists in troubleshooting virology procedures—lowering barriers to the development of biological weapons.

AI is naturally prone to being tricked into behaving badly, but researchers are working hard to patch that weakness.