Thinking Machines Lab reports state-of-the-art text-to-SQL performance from task-expertise reinforcement learning
Thinking Machines Lab published 'Putting Task Expertise into RL Achieves State-of-the-Art Performance on Text-to-SQL' on its company newsroom. Reinforcement learning is the training approach underpinning the architecture of the company's Tinker product, and the scale of its compute agreements with NVIDIA and Google Cloud has been attributed to RL workloads.