PewDiePie is doing his own GRPO training, and HF's merve wants to help but can't reach him
mervenoyann · x · 2026-10-01
Hugging Face researcher merve shares that PewDiePie is running his own GRPO (agentic RL) training, though he doesn't name his tooling. Per her notes: he tried distilling Sol but got banned a few times, built a website asking people to donate traces (nobody did — she notes he could just use the Hub), and she wants to help but can't reach him.
Related event: PewDiePie Trains GRPO Models Solo, Hugging Face Researchers Can't Reach Him(2 posts)→
More from Fun
- AI agents are speeding up game decompilation, with several projects nearing 100% — Promptmethus · 2026-10-01
- Researcher admits he still hand-types complex shell commands 'to see if I still got it' — haltakov · 2026-10-01
- Bun teases mysterious next act; community jokes it's 'Thanos-killing half of people' — cnakazawa · 2026-10-01
- Satirical post jokes PewDiePie distilled 5.6 Sol into Qwen3.5 9B with nuke knowledge — Dany0 · 2026-10-01
- TPOT coder levels three WoW alts to 20 while Codex runs in background — airkatakana · 2026-10-01
- Meme roasts Sam Altman: 'nobody touches my data' — miniapeur · 2026-10-01