PewDiePie Trains GRPO Models Solo, Hugging Face Researchers Can't Reach Him

Hugging Face researchers revealed that former YouTube star PewDiePie is self-training agentic GRPO reinforcement learning models off-grid, using undisclosed tools. Colleagues trying to help have been unable to reach him.

2026-10-01 ~ 2026-10-01 · 2 related posts

• PewDiePie is doing his own GRPO training, and HF's merve wants to help but can't reach him — mervenoyann · 2026-10-01
• PewDiePie is quietly doing agentic GRPO training off the grid, say HF engineers — MaziyarPanahi · 2026-10-01