According to Chris Olah on Twitter, the interpretability team is expanding its mentorship program for AI fellows, with applications due by August 17, 2025 (source: Chris Olah, Twitter, Aug 12, 2025). This initiative aims to advance research into explainable AI and machine learning interpretability, providing hands-on opportunities for researchers to contribute to safer, more transparent AI systems. The fellowship is expected to foster talent development and accelerate innovation in AI explainability, meeting growing business and regulatory demands for interpretable AI solutions.