How an astrophysicist uses Codex to help simulate black holes

Chan, a researcher at the University of Illinois Urbana-Champaign, found that Copilot reduced the time spent on coding by an estimated 30% to 50% for certain tasks. This AI coding assistant helped him generate code for the Event Horizon Telescope (EHT) project, which captured the first image of a black hole in 2019.

The simulations are crucial for testing Einstein's theory of general relativity in extreme gravitational environments and for understanding phenomena like black hole jets. Chan's work highlights how AI tools can significantly enhance scientific research by automating repetitive coding tasks, allowing scientists to focus more on complex problem-solving and theoretical advancements.

The EHT collaboration involves over 1,000 researchers from more than 200 institutions worldwide, aiming to provide unprecedented insights into the physics of black holes.