Rhythm Garg
@rhythmrg
Through our work with customers, we’ve learned what matters most when doing OPSD post-training and built those capabilities directly into our platform. First-class support for the algorithm is important, but so is the surrounding infrastructure – for example, building, iterating
Applied Compute@appliedcompute · Aug 4Production traces contain rich feedback that rarely makes it back into training pipelines. Self-distillation methods allow us to close the continual learning loop and learn from every interaction.
We’ve added native support for OPSD and RMSD to our platform, AC2. Here’s a
We’ve added native support for OPSD and RMSD to our platform, AC2. Here’s a
0:06 2 41