Tinker(@tinkerapi):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.

Tinker

@tinkerapi

I tink, therefore I am. Post-training API by @thinkymachines

参加 January 2026

1 フォロー中 14.6K ファン

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.