Reinforcement learning at @cognition's scale is a hard infrastructure problem. We are proud to be part of the stack behind it. Congrats to t…

Reinforcement learning at @cognition's scale is a hard infrastructure problem. We are proud to be part of the stack behind it. Congrats to the team on SWE-2! Read more about how we think about RL at Fireworks: https://fireworks.ai/blog/frontier-rl-is-cheaper-than-you-think Introducing SWE-2, our closest model yet to the frontier. On leading evals, it scores on par with recent frontier models – at up to 70% lower cost. We scaled RL to multiple trillions of parameters, with a refined recipe that pushes the Pareto curve on both capabilities & cost.

Related

• The hard part of reinforcement learning on a frontier model is the infrastructure that keeps training and inference numerically identical: z…
• Scaling Reinforcement Learning at Applied Compute
• Reinforcement learning is an infrastructure problem

Source: Fireworks AI (X) | 2026-09-10