The most useful data comes from real user interactions, feedback, and traces. With self-distillation, your model can learn from production traces even when the original environment can’t be replayed.

When you have the right checkpoint, deploy it to production with AC2 inference: dedicated, low latency, and 99.9% uptime all while preserving the configuration used during training.

Ari, our research agent, monitors training, reads traces to find failure modes, analyzes results, and turns insights into better data, graders, and experiments.

AC2 turns post-training into a repeatable, engineered process. Use your own harness to train up to multi-trillion-parameter models with all the latest research techniques.

Today, we're introducing AC2, the Applied Compute Agent Cloud, to enable every team to train, serve, and improve their own frontier models.

Over the last six months, AC2 has powered our Applied AI team’s work for Microsoft, NVIDIA, Cognition, Harvey, DoorDash, and others. Now, we’re excited to empower every AI team with their own model factory. AC2 is available in private beta. Reach out to learn more.

Go @benscharfstein 🚀🚀🚀

Let's go @benscharfstein !!!

Go @benscharfstein !!!!!

Slay

🔥🔥🔥

🔥🔥🔥🔥

@benscharfstein 🥵

End the em dashes! Congrats @benscharfstein and team, clear route to using production traces for continual learning

This is incredible @benscharfstein

woo!