Raaz Dwivedi

Language model agents struggle with oncall RCA, achieving only 25.3% accuracy on realistic tasks, revealing a critical readiness gap for production environments.

Express achieves a groundbreaking reduction in approximation error and memory usage for causal attention, outperforming existing methods and enabling more efficient long-context language modeling.

Ditching reward magnitudes for rankings unlocks faster and better RLHF, especially when judging quality is subjective.