Nathan Lambert Advises Mercor on RL Data and Calls for Stronger Real-World Evaluations

Nathan Lambert says he is advising Mercor on research into sample-efficient data for reinforcement learning (RL), with stronger evaluation science and benchmarks tied to areas of clear economic value as priorities for the field. Lambert says the data industry has grown, but low-quality output can amplify behaviors such as reward hacking. He expects major investment in open inference, open post-training and data around frontier labs, focused on expertise in representative real-world evaluations and synthetic data methods for scaling training data around those evaluations. He also sees opportunities to build on open models.

Generated by AI from reports · Updated 5 days ago