Tweet by garrytan

June 11, 2025

AI coding agents hit a wall when codebases get massive. Even with 2M token context windows, a 10M line codebase needs 100M tokens. The real bottleneck isn't just ingesting code - it's getting models to actually pay attention to all that context effectively. https://t.co/LQu6sq5EZk

Author
garrytan
Date
June 11, 2025