INTELLECT-2 has started another round of training. They're my favorite AI company, I love their branding, their AI, their tech and their mission.

The first decentralized 32B parameter RL training run open to join for anyone with compute — fully permissionless.

Scaling towards frontier reasoning across coding, math and science.

• Fully async, decentralized reinforcement learning
• Eliminating communication overhead
• Scalable across heterogeneous GPUs worldwide

#PrimeIntellect #Intellect2 #AIML
@Dagmawi_Babi