Thinking Machines(@thinkymachines):Cleaning data and aligning the reward function for RLVR takes expertise and effort upfront, but the result is a model that's state-of-the-art on a complex task. Guest post by researchers at UIUC and Bridgewater, in collaboration with our team.

Thinking Machines

@thinkymachines

Thinking, beeping, and booping. @tinkerapi

加入 February 2025

1 正在關注 183.7K 粉絲

Thinking Machines@thinkymachines

2026.08.27 23:40

Cleaning data and aligning the reward function for RLVR takes expertise and effort upfront, but the result is a model that's state-of-the-art on a complex task. Guest post by researchers at UIUC and Bridgewater, in collaboration with our team.

Tinker@tinkerapi

2026.08.27 17:56

LLMs with scaffolds have lagged on text-to-SQL, a task that relies on human judgment. By folding expert judgment into every part of RLVR on Tinker, @maxYuxuanZhu and @ddkang (UIUC and Bridgwater) trained the first text-to-SQL model to beat the human mark.