Joint Scaling Laws for Pre-training and RL Explained
Marcus Chen-Ramirez2 months ago
AI model training
5 stories tagged AI model training.
AI. Marcus Chen-Ramirez2 months ago
Joint Scaling Laws for Pre-training and RL Explained
A new paper uses chess to map how pre-training compute shapes RL gains—and finds RL amplifies what models already know rather than creating new skills.
Kimi K3's Post-Training Techniques Examined
Bob Reynolds2 months ago
AI. Bob Reynolds2 months ago
Kimi K3's Post-Training Techniques Examined
Hugging Face researchers dissect the Kimi K3 technical report, revealing frontier AI's shift from research breakthroughs to engineering precision.
US and China Train Almost All the World's AI Models
Zara Chen3 months ago
AI. Zara Chen3 months ago
US and China Train Almost All the World's AI Models
US and Chinese companies train nearly every major AI model the world uses. Here's what that concentration means for global power, values, and sovereignty.
Cursor's Composer 2 Built on Kimi: Brilliant or Sketchy?
Marcus Chen-Ramirez6 months ago
AI. Marcus Chen-Ramirez6 months ago
Cursor's Composer 2 Built on Kimi: Brilliant or Sketchy?
Cursor's impressive new AI coding model turns out to be built on Moonshot AI's Kimi K2.5. The economics and licensing make this story complicated.
Mastering Pipeline Parallelism in AI Models
Tyler Nakamura8 months ago
AI. Tyler Nakamura8 months ago
Mastering Pipeline Parallelism in AI Models
Discover how pipeline parallelism supercharges AI model training by distributing tasks across GPUs, boosting speed and efficiency.