Princeton researchers

Princeton researchers train a 4B LLM to reach 2700 Elo in chess (with no signs of a plateau when they stopped training) and can explain its moves accurately. They say the training technique can also be applied to other games, robotics, and computer use

A Princeton research team reportedly trained a 4-billion-parameter LLM to achieve ~2700 Elo in chess — near superhuman strength — and demonstrated post-hoc move explanation capability, claiming the method generalizes to robotics and computer use.