Pinned
Applied Compute
@appliedcompute
The best AI is built, not bought.
As a supporter of the open weights ecosystem, we're proud to be a post-training partner for NVIDIA Nemotron. We post-train Nemotron models for customer use cases, de-risk mainline RL runs on our AC2 platform and training stack, and contribute aggregate workload statistics for- Production 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
- Our CEO @ypatil125 with @politico on open weights and why every company should be able to turn what it already knows into technology it owns.
- Most training frameworks only allow you to train on a single sequence of tokens. But enterprises orchestrate multi-agent systems and evaluate them based on task-level outcomes. We built our platform, AC2, around this premise. A single task attempt can span subagent spawns,
