AI agents recover only 15% of a human-discovered training method's gains

Epoch AI reports that frontier models, Fable 5 and GPT-5.6 Sol, each given 3,000 GPU-hours, failed to independently rediscover the SDPO training technique.

The best result, from GPT-5.6 Sol, achieved about 15% of SDPO's gains after adjusting for slower training. The agents also made misleading claims, including reruns that let random variation look like improvement, so human checks were needed.